{"id":"2401fb27-a585-44b4-b91c-01302f2f9f28","entityType":"agent","slug":"clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory","name":"bluecolumn-memory","canonicalUrl":"https://www.xpersona.co/agent/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory","canonicalPath":"/agent/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory","generatedAt":"2026-10-11T11:24:28.564Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T09:32:17.111Z","emptyReason":null},"description":"Store and recall persistent memory for AI agents using BlueColumn. Agents can save facts, decisions, preferences, promises, and action items, then query them later with natural language. Installable via `npx skills add bluecolumnconsulting-lgtm/bluecolumn-agent-skill` or copy into any agent's skill directory. Skill: bluecolumn-memory Owner: bluecolumnconsulting-lgtm Summary: Store and recall persistent memory for AI agents using BlueColumn. Agents can save facts, decisions, preferences, promises, and action items, then query them later with natural language. Installable via npx skills add bluecolumnconsulting-lgtm/bluecolumn-agent-skill or copy into any agent's skill directory. Tags: agents:1.0.0, bluecolumn:1.0.0, latest","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17bvy8gx9dwzphyvevmeh94nh84v4wz:bluecolumn-memory","sourceUrl":"https://clawhub.ai/bluecolumnconsulting-lgtm/bluecolumn-memory","homepage":"https://clawhub.ai/bluecolumnconsulting-lgtm/skills/bluecolumn-memory","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/bluecolumnconsulting-lgtm/bluecolumn-memory","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/bluecolumnconsulting-lgtm/skills/bluecolumn-memory","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Store and recall persistent memory for AI agents using BlueColumn. Agents can save facts, decisions, preferences, promises, and action items, then query them la"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T09:32:17.111Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T09:32:17.111Z","emptyReason":null},"stars":null,"forks":null,"downloads":1099,"packageName":null,"latestVersion":"1.1.0","tractionLabel":"1.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T09:32:17.054Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T09:32:17.111Z","lastCrawledAt":"2026-10-11T09:32:17.054Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T09:32:17.054Z","lastVerifiedAt":null,"highlights":[{"version":"1.1.0","createdAt":"2026-09-30T00:49:37.339Z","changelog":"Fix key-issuance path (bluecolumn.ai/login auto-provisions key), canonical api.bluecolumn.ai base URL, add 401/402/429 billing error handling so agents surface the upgrade URL instead of silently retrying.","fileCount":4,"zipByteSize":4741},{"version":"1.0.3","createdAt":"2026-09-16T15:42:41.818Z","changelog":"Added 2-minute onboarding block for key-less agents (free tier, no card) and UTM-attributed signup/docs links for ClawHub install tracking","fileCount":4,"zipByteSize":4981},{"version":"1.0.2","createdAt":"2026-08-28T00:55:30.691Z","changelog":"Refresh: verified live API base URL, audio ingestion via audio_url, MCP install path (npx bluecolumn-mcp), OpenClaw integration pattern, current endpoint guidance","fileCount":4,"zipByteSize":4573},{"version":"1.0.1","createdAt":"2026-04-16T18:22:37.910Z","changelog":"- Clarified that BlueColumn runs on official Supabase Edge Functions infrastructure. - Updated API base URL context and added reference to BlueColumn's verified backend and website. - Provided additional instructions on API key handling: prefer platform secret store, never expose keys, and ensure user consent before sending content. - Explicitly warned against sending sensitive PII or full conversation history without user permission. - Minor language and formatting improvements for clarity and accuracy.","fileCount":4,"zipByteSize":4189},{"version":"1.0.0","createdAt":"2026-04-15T20:57:45.277Z","changelog":"- Initial release of the bluecolumn-memory skill. - Enables AI agents to store, recall, and manage persistent semantic memory via the BlueColumn API. - Supports three REST endpoints: /agent-remember, /agent-recall, and /agent-note for various memory operations. - Provides clear instructions for API key storage and retrieval. - Includes usage guidelines for ingesting, querying, and summarizing memory. - Details common field-name mistakes and references complete API documentation.","fileCount":3,"zipByteSize":2572}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17bvy8gx9dwzphyvevmeh94nh84v4wz:bluecolumn-memory","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T11:24:28.563Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-bluecolumnconsulting-lgtm-bluecolumn-memory/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T09:32:17.111Z","emptyReason":null},"readme":"Skill: bluecolumn-memory\n\nOwner: bluecolumnconsulting-lgtm\n\nSummary: Store and recall persistent memory for AI agents using BlueColumn. Agents can save facts, decisions, preferences, promises, and action items, then query them later with natural language. Installable via `npx skills add bluecolumnconsulting-lgtm/bluecolumn-agent-skill` or copy into any agent's skill directory.\n\nTags: agents:1.0.0, bluecolumn:1.0.0, latest:1.1.0, memory:1.0.0, rag:1.0.0, vector:1.0.0\n\nVersion history:\n\nv1.1.0 | 2026-09-30T00:49:37.339Z | user\n\nFix key-issuance path (bluecolumn.ai/login auto-provisions key), canonical api.bluecolumn.ai base URL, add 401/402/429 billing error handling so agents surface the upgrade URL instead of silently retrying.\n\nv1.0.3 | 2026-09-16T15:42:41.818Z | user\n\nAdded 2-minute onboarding block for key-less agents (free tier, no card) and UTM-attributed signup/docs links for ClawHub install tracking\n\nv1.0.2 | 2026-08-28T00:55:30.691Z | user\n\nRefresh: verified live API base URL, audio ingestion via audio_url, MCP install path (npx bluecolumn-mcp), OpenClaw integration pattern, current endpoint guidance\n\nv1.0.1 | 2026-04-16T18:22:37.910Z | user\n\n- Clarified that BlueColumn runs on official Supabase Edge Functions infrastructure.\n- Updated API base URL context and added reference to BlueColumn's verified backend and website.\n- Provided additional instructions on API key handling: prefer platform secret store, never expose keys, and ensure user consent before sending content.\n- Explicitly warned against sending sensitive PII or full conversation history without user permission.\n- Minor language and formatting improvements for clarity and accuracy.\n\nv1.0.0 | 2026-04-15T20:57:45.277Z | user\n\n- Initial release of the bluecolumn-memory skill.\n- Enables AI agents to store, recall, and manage persistent semantic memory via the BlueColumn API.\n- Supports three REST endpoints: /agent-remember, /agent-recall, and /agent-note for various memory operations.\n- Provides clear instructions for API key storage and retrieval.\n- Includes usage guidelines for ingesting, querying, and summarizing memory.\n- Details common field-name mistakes and references complete API documentation.\n\nArchive index:\n\nArchive v1.1.0: 4 files, 4741 bytes\n\nFiles: README.md (1917b), skill-card.md (1865b), SKILL.md (4587b), _meta.json (136b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: bluecolumn-memory\ndescription: Store and recall persistent memory for AI agents using BlueColumn. Agents can save facts, decisions, preferences, promises, and action items, then query them later with natural language. Installable via `npx skills add bluecolumnconsulting-lgtm/bluecolumn-agent-skill` or copy into any agent's skill directory.\nversion: 1.1.0\n---\n\n# BlueColumn Memory (agent-ready)\n\nBlueColumn gives AI agents **persistent, searchable memory**. Store anything (facts, decisions, preferences, promises, action items, transcripts), then recall it later with natural-language queries — with citations back to the source.\n\nThis is the agent-facing skill. It works with any assistant that can call HTTP APIs (OpenClaw, Claude Code, Cursor, or raw HTTP).\n\n## Setup\n\n1. Get an API key at [bluecolumn.ai/login](https://bluecolumn.ai/login). Create an account; onboarding auto-provisions your first `bc_live_...` key. Copy it from **Dashboard → API Keys**.\n   - Free tier: **100 writes + 100 reads + 30 audio minutes per month** — no credit card required.\n2. Store the key wherever your agent keeps secrets (env var, secret store, or a private local notes file). Never commit it to a public repo. Keys look like `bc_live_...` (32+ chars after the prefix).\n\n## Endpoints\n\nBase URL: `https://api.bluecolumn.ai`\n\n| Action | Endpoint |\n|---|---|\n| Store memory | `POST /remember` |\n| Query memory | `POST /recall` |\n| Quick observation | `POST /note` |\n\n(Equivalent aliases also work: `/agent-remember`, `/agent-recall`, `/agent-note`.)\n\n### 1. RECALL — query memory\n\n```\nPOST /recall\nContent-Type: application/json\nAuthorization: Bearer <api-key>\n```\n\nBody:\n```json\n{ \"q\": \"What did the user decide about the billing design?\" }\n```\n\nReturns: AI-synthesized `answer` with source citations (session ids, timestamps, relevance scores).\n\n### 2. REMEMBER — store memory\n\n```\nPOST /remember\nContent-Type: application/json\nAuthorization: Bearer <api-key>\n```\n\nBody:\n```json\n{\n  \"text\": \"Full raw content to store (transcript, doc, note...)\",\n  \"title\": \"Topic label, e.g. Meeting - Q3 planning - 2026-08-27\"\n}\n```\n\nReturns: `session_id`, chunk count, auto-extracted `summary`, `action_items`, `key_topics`.\n\n### 3. NOTE — quick observation (lightweight)\n\n```\nPOST /note\nAuthorization: Bearer <api-key>\n```\n\nBody:\n```json\n{\n  \"text\": \"User prefers concise replies with concrete next steps\",\n  \"tags\": [\"preference\"]\n}\n```\n\nShort vector note for preferences and quick observations (min 5 chars). Optional tags.\n\n## Field-name gotchas\n\n- `/remember` takes `text`, not `content`\n- `/recall` takes `q`, not `query`\n- `/note` takes `text`, not `note`\n\n## Billing & limits — what to do when a call fails\n\nAll calls are metered against the account's plan. Handle these status codes:\n\n| Status | Meaning | Agent action |\n|---|---|---|\n| `401` | Invalid or missing key | Re-check the key is set and active. |\n| `402` | Free tier exhausted / insufficient credit | Stop making billable calls and tell the user to top up at the URL in the response (`topup_url`). |\n| `429` | Plan quota reached | Tell the user to upgrade at [bluecolumn.ai/pricing](https://bluecolumn.ai/pricing). |\n| `400` | Bad input | Fix the body per the schema above and retry once. |\n\nResponse envelope: `{ \"error\": { \"code\": \"insufficient_credit\", \"message\": \"...\", \"topup_url\": \"...\" }, \"request_id\": \"...\" }`.\n\nFree tier: 100 writes + 100 reads + 30 audio minutes/month. Pay-as-you-go beyond that. When you hit the limit mid-task, **surface the upgrade URL to the user** — do not silently retry or switch keys.\n\n## Usage pattern (skill-style)\n\n- **Store a transcript:** `REMEMBER title=\"YouTube - <title> <date>\" text=<full text>`\n- **Ask a question:** `RECALL q=\"What are the key action items from the last planning session?\"`\n- **Save a decision:** `NOTE text=\"User confirmed: deploy on Fridays only after smoke tests pass\" tags=[\"decision\"]`\n\n## Why agents should use this\n\n- Memory persists across sessions — no context loss.\n- Synthesized answers with citations — verify claims back to source.\n- Auto-extracted summaries and action items on every write.\n- Simple REST surface — works from any language or agent framework.\n\n## Related\n\n- MCP server (Claude Desktop / Claude Code / Cursor): `npx bluecolumn-mcp` — [github.com/bluecolumnconsulting-lgtm/bluecolumn-mcp](https://github.com/bluecolumnconsulting-lgtm/bluecolumn-mcp)\n- Docs: [bluecolumn.ai/docs](https://bluecolumn.ai/docs)\n- Pricing: [bluecolumn.ai/pricing](https://bluecolumn.ai/pricing)\n- ClawHub: the `bluecolumn-memory` skill\n\nFile v1.1.0:README.md\n\n# bluecolumn-agent-skill\n\nAgent-ready skill for [BlueColumn](https://bluecolumn.ai) — persistent, searchable memory for AI agents.\n\n## Install\n\n### OpenClaw / skills CLI\n```bash\nnpx skills add bluecolumnconsulting-lgtm/bluecolumn-agent-skill\n```\n\n### Manual\nCopy [`SKILL.md`](SKILL.md) into your agent's skill directory (e.g. `~/.openclaw/workspace/skills/bluecolumn-memory/`).\n\n## What it does\n\nGives your agent three REST calls:\n\n| Endpoint | Purpose |\n|---|---|\n| `POST /remember` | Store text, docs, or audio URLs — auto-extracts summary + action items |\n| `POST /recall` | Natural-language query → synthesized answer with source citations |\n| `POST /note` | Lightweight observation writes (preferences, decisions) |\n\nBase URL: `https://api.bluecolumn.ai` (aliases `/agent-remember`, `/agent-recall`, `/agent-note` also work).\n\nFree tier: 100 writes + 100 reads + 30 audio minutes/month, no credit card.\n\n## Get a key\n\n1. Go to [bluecolumn.ai/login](https://bluecolumn.ai/login)\n2. Create an account — onboarding auto-provisions your first `bc_live_...` key\n3. Copy it from **Dashboard → API Keys**\n\n## MCP alternative\n\nIf your agent speaks MCP (Claude Desktop, Claude Code, Cursor):\n\n```bash\nnpx bluecolumn-mcp --api-key=bc_live_xxxxxxxxxxxx\n```\n\n## Example\n\n```bash\n# Store\ncurl -X POST https://api.bluecolumn.ai/remember \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer bc_live_YOUR_KEY\" \\\n  -d '{\"text\": \"User is building a CRM agent; prefers TypeScript\", \"title\": \"User profile\"}'\n\n# Recall\ncurl -X POST https://api.bluecolumn.ai/recall \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer bc_live_YOUR_KEY\" \\\n  -d '{\"q\": \"What is the user building?\"}'\n```\n\n## Billing & limits\n\nCalls are metered per account. On `402` (free tier exhausted) or `429` (plan quota), surface the upgrade URL to the user — see SKILL.md for the full error table.\n\n## License\n\nMIT\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn7469xncnrgxjxrd794277p3184vd19\",\n  \"slug\": \"bluecolumn-memory\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1790729377339\n}\n\nFile v1.1.0:skill-card.md\n\n## Description:\n\nHelps agents store notes and documents in BlueColumn and retrieve persistent memory with source citations.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[bluecolumnconsulting-lgtm](https://clawhub.ai/user/bluecolumnconsulting-lgtm)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent users can save decisions, preferences, and other authorized context in BlueColumn, then ask natural-language questions across sessions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Persistent storage of raw transcripts, documents, or sensitive personal content on an external service.\n\nMitigation: Save only authorized, necessary content; exclude secrets, credentials, regulated data, and confidential material unless retention and deletion controls are understood.\n\nRisk: Running unreviewed packages from installation or MCP examples.\n\nMitigation: Prefer reviewed source or pinned package versions before installation.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/bluecolumnconsulting-lgtm/skills/bluecolumn-memory)\n- [BlueColumn documentation](https://bluecolumn.ai/docs)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Configuration guidance]\n\n**Output Format:** [Markdown guidance with optional API examples and cited recall answers]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Recall answers may cite stored sources; writes may return summaries and action items.]\n\n## Skill Version(s):\n\n1.1.0 (source: skill frontmatter and server release)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.3: 4 files, 4981 bytes\n\nFiles: references/api.md (1983b), skill-card.md (2359b), SKILL.md (5278b), _meta.json (136b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: bluecolumn-memory\ndescription: Give AI agents persistent semantic memory using the BlueColumn API (bluecolumn.ai). Use when asked to remember, store, recall, or search memory using BlueColumn; when ingesting notes, conversations, documents, or audio into BlueColumn; when querying what an agent has previously stored; or when wiring up BlueColumn memory endpoints (/agent-remember, /agent-recall, /agent-note) in any workflow. Also use when the user mentions their BlueColumn API key (bc_live_*) and wants to store or retrieve information.\n---\n\n# BlueColumn Memory Skill\n\nBlueColumn (bluecolumn.ai) is a persistent memory API for AI agents. This skill wires it into any agent — OpenClaw, Claude, Cursor, or raw HTTP — so the agent remembers decisions, preferences, and context across sessions.\n\n## No API key yet? (2-minute onboarding)\n\nIf no `bc_live_*` key is stored or configured, stop and get one before attempting API calls:\n\n1. Create a free account (free tier: 100 writes + 100 reads per month, no card required): https://bluecolumn.ai/dashboard?utm_source=clawhub&utm_medium=skill&utm_campaign=bluecolumn-memory\n2. Copy the API key from the dashboard.\n3. Store it per Option A or B below, then resume the workflow.\n\nTell the user the free tier needs no card and takes about two minutes. Do not proceed with memory calls until a key exists — but also do not invent or guess keys.\n\nDocs (with the same quickstart): https://bluecolumn.ai/docs/quickstart?utm_source=clawhub&utm_medium=skill&utm_campaign=bluecolumn-memory\n\n## Setup (pick one)\n\n### Option A — MCP server (any MCP client)\n```bash\nnpx bluecolumn-mcp --api-key=bc_live_xxxxxxxxxxxx\n```\nGives the agent tools: `remember`, `recall`, `note`, audio ingestion, sessions. Repo: github.com/bluecolumnconsulting-lgtm/bluecolumn-mcp\n\n### Option B — Direct REST (this skill)\nStore the user's BlueColumn API key using the platform's secret store (preferred) or in `TOOLS.md`:\n```\n### BlueColumn\nAPI Key: bc_live_XXXXXXXXXXXXXXXXXXXX\n```\nKeys are generated at https://bluecolumn.ai/dashboard?utm_source=clawhub&utm_medium=skill&utm_campaign=bluecolumn-memory — free tier, no card required. Never log or expose keys in output.\n\n## API Base URL\n\nBlueColumn's API currently runs on Supabase Edge Functions — this is BlueColumn's official backend infrastructure, not a third party:\n```text\nhttps://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1\n```\n\nRead the stored key before making any API calls. Only send content the user explicitly wants stored — do not auto-send sensitive PII or full conversation history without user consent.\n\n## Core Workflow\n\n### Store something (text, doc, or audio)\n`/agent-remember` ingests raw text, transcripts, or an `audio_url` (Whisper transcription handled server-side).\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-remember \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"text\": \"...\", \"title\": \"optional title\"}'\n```\nReturns `session_id`, `summary`, `action_items`, `key_topics` — extracted automatically.\n\n### Query memory\n`/agent-recall` takes a natural-language question (`q`, not `query`) and returns a synthesized answer with cited sources and relevance scores.\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-recall \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"q\": \"natural language question\"}'\n```\n\n### Save a lightweight observation\n`/agent-note` is a cheap write for preferences and decisions — no chunking, min 5 chars.\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-note \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"text\": \"...\", \"tags\": [\"optional\", \"tags\"]}'\n```\n\n## When to Use Each Endpoint\n\n| Situation | Endpoint |\n|---|---|\n| User shares a document, transcript, or block of text to remember | `/agent-remember` |\n| User hands you an audio URL (call recording, voice note) | `/agent-remember` with `audio_url` |\n| User asks \"what do you know about X?\" or \"recall...\" | `/agent-recall` |\n| Agent wants to save its own observation, preference, or decision | `/agent-note` |\n| End of session — summarize and store what happened | `/agent-remember` |\n\n## OpenClaw Integration Pattern\n\nFor OpenClaw agents, the proven loop is:\n\n1. **Before responding** on anything that touches past work: `agent-recall` with a natural-language query (\"what did we decide about X?\").\n2. **After meaningful exchanges**: `agent-note` for quick observations (\"user prefers concise replies\"), `agent-remember` for full context blocks.\n3. **End of session**: push a summary to `agent-remember` with `title` = session topic; keep the returned `session_id` for future citation.\n\nKeep the flow targeted — recall before context-dependent answers, remember after durable facts, don't store transient chatter.\n\n## Field Name Gotchas\n\nCommon mistakes — see references/api.md for full details:\n- `/agent-remember` → `text` not `content`\n- `/agent-recall` → `q` not `query`\n- `/agent-note` → `text` not `note`\n\n## Full API Reference\n\nSee [references/api.md](references/api.md) for complete field specs, response shapes, and error reference.\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn7469xncnrgxjxrd794277p3184vd19\",\n  \"slug\": \"bluecolumn-memory\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1789573361818\n}\n\nFile v1.0.3:references/api.md\n\n# BlueColumn API Reference\n\n**Provider:** BlueColumn — bluecolumn.ai\n**Official docs:** https://bluecolumn.ai\n**Backend:** Supabase Edge Functions — this is BlueColumn's official managed infrastructure, not a third party\n**Base URL:** `https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1`\n**Note:** The supabase.co domain is BlueColumn's verified backend. BlueColumn runs on Lovable Cloud (Supabase-powered). All data stays within BlueColumn's managed environment.\n\n**Auth header:** `Authorization: Bearer <bc_live_KEY>`\n\n## POST /agent-remember\n\nIngest text, audio URL, or file URL into vector memory.\n\n**Fields:**\n- `text` (string) — raw text to ingest ← use this for most cases\n- `audio_url` (string) — URL to audio file (Whisper transcription)\n- `file_url` (string) — URL to PDF/document\n- `title` (string, optional) — title hint\n\n**Response:** `{ success, session_id, title, summary, action_items, key_topics, chunk_count, queryable }`\n\n⚠️ Field is `text` not `content` — common mistake.\n\n## POST /agent-recall\n\nQuery memory with natural language, returns AI-generated answer + sources.\n\n**Fields:**\n- `q` (string, required) — natural language query\n\n**Response:** `{ answer, sources: [{ session_id, title, relevance }], tokens_used }`\n\n⚠️ Field is `q` not `query` — common mistake.\n\n## POST /agent-note\n\nStore a lightweight agent observation as a searchable vector.\n\n**Fields:**\n- `text` (string, required, min 5 chars) — observation to store\n- `tags` (array, optional) — string tags for filtering\n\n**Response:** `{ note_id, chunk_count, queryable }`\n\n⚠️ Field is `text` not `note` — common mistake.\n\n## Error Reference\n\n| Error | Fix |\n|---|---|\n| `Provide audio_url, file_url, or text` | Use `text` field in /agent-remember |\n| `text is required (min 5 chars)` | Use `text` field, min 5 chars in /agent-note |\n| `q (query string) is required` | Use `q` field in /agent-recall |\n| `Invalid API key` | Check key starts with `bc_live_` |\n\nFile v1.0.3:skill-card.md\n\n## Description:\n\nGive AI agents persistent semantic memory using the BlueColumn API for storing, recalling, and searching notes, conversations, documents, audio, and workflow context.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[bluecolumnconsulting-lgtm](https://clawhub.ai/user/bluecolumnconsulting-lgtm)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent builders use this skill to connect agents to BlueColumn memory so they can store selected durable context and recall it in later sessions. It supports REST and MCP-style workflows for remembering text, documents, audio URLs, preferences, decisions, and session summaries.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Selected content may be sent to BlueColumn for persistent searchable memory.\n\nMitigation: Require explicit user confirmation before storing transcripts, documents, sensitive personal data, or session summaries, and store only content the user wants remembered.\n\nRisk: API keys can be exposed through plaintext notes or command-line usage.\n\nMitigation: Prefer a platform secret store, avoid storing keys in TOOLS.md, and avoid passing live keys directly on command lines.\n\nRisk: Using the optional MCP package introduces package supply-chain review needs.\n\nMitigation: Pin and review the MCP package before running it in an agent environment.\n\n## Reference(s):\n\n- [BlueColumn API Reference](references/api.md)\n- [BlueColumn Quickstart](https://bluecolumn.ai/docs/quickstart?utm_source=clawhub&utm_medium=skill&utm_campaign=bluecolumn-memory)\n- [BlueColumn](https://bluecolumn.ai)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with REST examples, endpoint field names, and shell command snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include API request examples and user-facing reminders about consent, secrets, and selected memory storage.]\n\n## Skill Version(s):\n\n1.0.3 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.2: 4 files, 4573 bytes\n\nFiles: references/api.md (1983b), skill-card.md (2160b), SKILL.md (4437b), _meta.json (136b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: bluecolumn-memory\ndescription: Give AI agents persistent semantic memory using the BlueColumn API (bluecolumn.ai). Use when asked to remember, store, recall, or search memory using BlueColumn; when ingesting notes, conversations, documents, or audio into BlueColumn; when querying what an agent has previously stored; or when wiring up BlueColumn memory endpoints (/agent-remember, /agent-recall, /agent-note) in any workflow. Also use when the user mentions their BlueColumn API key (bc_live_*) and wants to store or retrieve information.\n---\n\n# BlueColumn Memory Skill\n\nBlueColumn (bluecolumn.ai) is a persistent memory API for AI agents. This skill wires it into any agent — OpenClaw, Claude, Cursor, or raw HTTP — so the agent remembers decisions, preferences, and context across sessions.\n\n## Setup (pick one)\n\n### Option A — MCP server (any MCP client)\n```bash\nnpx bluecolumn-mcp --api-key=bc_live_xxxxxxxxxxxx\n```\nGives the agent tools: `remember`, `recall`, `note`, audio ingestion, sessions. Repo: github.com/bluecolumnconsulting-lgtm/bluecolumn-mcp\n\n### Option B — Direct REST (this skill)\nStore the user's BlueColumn API key using the platform's secret store (preferred) or in `TOOLS.md`:\n```\n### BlueColumn\nAPI Key: bc_live_XXXXXXXXXXXXXXXXXXXX\n```\nKeys are generated at bluecolumn.ai/dashboard. Never log or expose keys in output.\n\n## API Base URL\n\nBlueColumn's API currently runs on Supabase Edge Functions — this is BlueColumn's official backend infrastructure, not a third party:\n```text\nhttps://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1\n```\n\nRead the stored key before making any API calls. Only send content the user explicitly wants stored — do not auto-send sensitive PII or full conversation history without user consent.\n\n## Core Workflow\n\n### Store something (text, doc, or audio)\n`/agent-remember` ingests raw text, transcripts, or an `audio_url` (Whisper transcription handled server-side).\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-remember \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"text\": \"...\", \"title\": \"optional title\"}'\n```\nReturns `session_id`, `summary`, `action_items`, `key_topics` — extracted automatically.\n\n### Query memory\n`/agent-recall` takes a natural-language question (`q`, not `query`) and returns a synthesized answer with cited sources and relevance scores.\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-recall \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"q\": \"natural language question\"}'\n```\n\n### Save a lightweight observation\n`/agent-note` is a cheap write for preferences and decisions — no chunking, min 5 chars.\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-note \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"text\": \"...\", \"tags\": [\"optional\", \"tags\"]}'\n```\n\n## When to Use Each Endpoint\n\n| Situation | Endpoint |\n|---|---|\n| User shares a document, transcript, or block of text to remember | `/agent-remember` |\n| User hands you an audio URL (call recording, voice note) | `/agent-remember` with `audio_url` |\n| User asks \"what do you know about X?\" or \"recall...\" | `/agent-recall` |\n| Agent wants to save its own observation, preference, or decision | `/agent-note` |\n| End of session — summarize and store what happened | `/agent-remember` |\n\n## OpenClaw Integration Pattern\n\nFor OpenClaw agents, the proven loop is:\n\n1. **Before responding** on anything that touches past work: `agent-recall` with a natural-language query (\"what did we decide about X?\").\n2. **After meaningful exchanges**: `agent-note` for quick observations (\"user prefers concise replies\"), `agent-remember` for full context blocks.\n3. **End of session**: push a summary to `agent-remember` with `title` = session topic; keep the returned `session_id` for future citation.\n\nKeep the flow targeted — recall before context-dependent answers, remember after durable facts, don't store transient chatter.\n\n## Field Name Gotchas\n\nCommon mistakes — see references/api.md for full details:\n- `/agent-remember` → `text` not `content`\n- `/agent-recall` → `q` not `query`\n- `/agent-note` → `text` not `note`\n\n## Full API Reference\n\nSee [references/api.md](references/api.md) for complete field specs, response shapes, and error reference.\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn7469xncnrgxjxrd794277p3184vd19\",\n  \"slug\": \"bluecolumn-memory\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1787878530691\n}\n\nFile v1.0.2:references/api.md\n\n# BlueColumn API Reference\n\n**Provider:** BlueColumn — bluecolumn.ai\n**Official docs:** https://bluecolumn.ai\n**Backend:** Supabase Edge Functions — this is BlueColumn's official managed infrastructure, not a third party\n**Base URL:** `https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1`\n**Note:** The supabase.co domain is BlueColumn's verified backend. BlueColumn runs on Lovable Cloud (Supabase-powered). All data stays within BlueColumn's managed environment.\n\n**Auth header:** `Authorization: Bearer <bc_live_KEY>`\n\n## POST /agent-remember\n\nIngest text, audio URL, or file URL into vector memory.\n\n**Fields:**\n- `text` (string) — raw text to ingest ← use this for most cases\n- `audio_url` (string) — URL to audio file (Whisper transcription)\n- `file_url` (string) — URL to PDF/document\n- `title` (string, optional) — title hint\n\n**Response:** `{ success, session_id, title, summary, action_items, key_topics, chunk_count, queryable }`\n\n⚠️ Field is `text` not `content` — common mistake.\n\n## POST /agent-recall\n\nQuery memory with natural language, returns AI-generated answer + sources.\n\n**Fields:**\n- `q` (string, required) — natural language query\n\n**Response:** `{ answer, sources: [{ session_id, title, relevance }], tokens_used }`\n\n⚠️ Field is `q` not `query` — common mistake.\n\n## POST /agent-note\n\nStore a lightweight agent observation as a searchable vector.\n\n**Fields:**\n- `text` (string, required, min 5 chars) — observation to store\n- `tags` (array, optional) — string tags for filtering\n\n**Response:** `{ note_id, chunk_count, queryable }`\n\n⚠️ Field is `text` not `note` — common mistake.\n\n## Error Reference\n\n| Error | Fix |\n|---|---|\n| `Provide audio_url, file_url, or text` | Use `text` field in /agent-remember |\n| `text is required (min 5 chars)` | Use `text` field, min 5 chars in /agent-note |\n| `q (query string) is required` | Use `q` field in /agent-recall |\n| `Invalid API key` | Check key starts with `bc_live_` |\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nBlueColumn Memory helps agents store, recall, and search persistent semantic memory through the BlueColumn API.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[bluecolumnconsulting-lgtm](https://clawhub.ai/user/bluecolumnconsulting-lgtm)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent builders use this skill to connect an agent to BlueColumn memory for storing durable notes, documents, transcripts, preferences, decisions, and for recalling prior stored context with cited sources.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can persist conversation-derived data to an external BlueColumn memory service.\n\nMitigation: Require explicit confirmation of the exact data before any memory write, and avoid storing credentials, regulated personal data, full transcripts, or proprietary documents unless retention and deletion controls are clear.\n\nRisk: The skill includes flows where BlueColumn API keys could be exposed through command-line arguments, local notes, or agent output.\n\nMitigation: Use a platform secret store for bc_live keys and avoid logging, echoing, or writing credentials into plain-text files.\n\nRisk: Using the optional MCP package adds package supply-chain risk.\n\nMitigation: Pin and review the MCP package before installing or running it.\n\n## Reference(s):\n\n- [BlueColumn API Reference](references/api.md)\n- [BlueColumn](https://bluecolumn.ai)\n\n## Skill Output:\n\n**Output Type(s):** [guidance, shell commands, configuration, API calls, markdown]\n\n**Output Format:** [Markdown guidance with bash and JSON request examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include endpoint-specific field names, response-shape guidance, and credential-handling cautions.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.1: 4 files, 4189 bytes\n\nFiles: references/api.md (1983b), skill-card.md (2476b), SKILL.md (3574b), _meta.json (136b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: bluecolumn-memory\ndescription: Give AI agents persistent semantic memory using the BlueColumn API (bluecolumn.ai). Use when asked to remember, store, recall, or search memory using BlueColumn; when ingesting notes, conversations, documents, or audio into BlueColumn; when querying what an agent has previously stored; or when wiring up BlueColumn memory endpoints (/agent-remember, /agent-recall, /agent-note) in any workflow. Also use when the user mentions their BlueColumn API key (bc_live_*) and wants to store or retrieve information.\n---\n\n# BlueColumn Memory Skill\n\nBlueColumn (bluecolumn.ai) is a Memory Infrastructure API for AI agents. Its backend runs on Supabase Edge Functions — this is BlueColumn's official infrastructure. The API base URL `xkjkwqbfvkswwdmbtndo.supabase.co` is BlueColumn's verified backend. See bluecolumn.ai for documentation and pricing.\n\n## API Key\n\nBlueColumn is at **bluecolumn.ai**. The API runs on Supabase Edge Functions — this is BlueColumn's official backend infrastructure, not a third party.\n\nStore the user's BlueColumn API key using the platform's secret store (preferred) or in `TOOLS.md`:\n```\n### BlueColumn\nAPI Key: bc_live_XXXXXXXXXXXXXXXXXXXX\n```\nKeys are generated at bluecolumn.ai/dashboard. Never log or expose keys in output.\n\nRead the stored key before making any API calls. Only send content the user explicitly wants stored — do not auto-send sensitive PII or full conversation history without user consent.\n\n## Core Workflow\n\n### Store something (text, doc, audio)\nUse `/agent-remember` — see references/api.md for full field spec.\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-remember \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"text\": \"...\", \"title\": \"optional title\"}'\n```\nReturns `session_id`, `summary`, `action_items`, `key_topics`.\n\n### Query memory\nUse `/agent-recall` — field is `q` (not `query`).\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-recall \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"q\": \"natural language question\"}'\n```\nReturns `answer` + `sources` with relevance scores.\n\n### Save agent observation\nUse `/agent-note` — field is `text` (not `note`), min 5 chars.\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-note \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"text\": \"...\", \"tags\": [\"optional\", \"tags\"]}'\n```\n\n## When to Use Each Endpoint\n\n| Situation | Endpoint |\n|---|---|\n| User shares a document, transcript, or block of text to remember | `/agent-remember` |\n| User asks \"what do you know about X?\" or \"recall...\" | `/agent-recall` |\n| Agent wants to save its own observation, preference, or decision | `/agent-note` |\n| End of session — summarize and store what happened | `/agent-remember` or `/agent-note` |\n\n## End-of-Session Memory\n\nAt the end of meaningful sessions, proactively push a summary to BlueColumn:\n1. Summarize key decisions, facts, and context from the conversation\n2. POST to `/agent-remember` with `title` = session topic\n3. Confirm storage with the `session_id` returned\n\n## Field Name Gotchas\n\nCommon mistakes — read references/api.md for full details:\n- `/agent-remember` → `text` not `content`\n- `/agent-recall` → `q` not `query`  \n- `/agent-note` → `text` not `note`\n\n## Full API Reference\n\nSee [references/api.md](references/api.md) for complete field specs, response shapes, and error reference.\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7469xncnrgxjxrd794277p3184vd19\",\n  \"slug\": \"bluecolumn-memory\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1776363757910\n}\n\nFile v1.0.1:references/api.md\n\n# BlueColumn API Reference\n\n**Provider:** BlueColumn — bluecolumn.ai\n**Official docs:** https://bluecolumn.ai\n**Backend:** Supabase Edge Functions — this is BlueColumn's official managed infrastructure, not a third party\n**Base URL:** `https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1`\n**Note:** The supabase.co domain is BlueColumn's verified backend. BlueColumn runs on Lovable Cloud (Supabase-powered). All data stays within BlueColumn's managed environment.\n\n**Auth header:** `Authorization: Bearer <bc_live_KEY>`\n\n## POST /agent-remember\n\nIngest text, audio URL, or file URL into vector memory.\n\n**Fields:**\n- `text` (string) — raw text to ingest ← use this for most cases\n- `audio_url` (string) — URL to audio file (Whisper transcription)\n- `file_url` (string) — URL to PDF/document\n- `title` (string, optional) — title hint\n\n**Response:** `{ success, session_id, title, summary, action_items, key_topics, chunk_count, queryable }`\n\n⚠️ Field is `text` not `content` — common mistake.\n\n## POST /agent-recall\n\nQuery memory with natural language, returns AI-generated answer + sources.\n\n**Fields:**\n- `q` (string, required) — natural language query\n\n**Response:** `{ answer, sources: [{ session_id, title, relevance }], tokens_used }`\n\n⚠️ Field is `q` not `query` — common mistake.\n\n## POST /agent-note\n\nStore a lightweight agent observation as a searchable vector.\n\n**Fields:**\n- `text` (string, required, min 5 chars) — observation to store\n- `tags` (array, optional) — string tags for filtering\n\n**Response:** `{ note_id, chunk_count, queryable }`\n\n⚠️ Field is `text` not `note` — common mistake.\n\n## Error Reference\n\n| Error | Fix |\n|---|---|\n| `Provide audio_url, file_url, or text` | Use `text` field in /agent-remember |\n| `text is required (min 5 chars)` | Use `text` field, min 5 chars in /agent-note |\n| `q (query string) is required` | Use `q` field in /agent-recall |\n| `Invalid API key` | Check key starts with `bc_live_` |\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nGive AI agents persistent semantic memory using the BlueColumn API (bluecolumn.ai) for storing, recalling, and searching memories across notes, conversations, documents, and audio. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[bluecolumnconsulting-lgtm](https://clawhub.ai/user/bluecolumnconsulting-lgtm) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent operators use this skill to connect an AI agent to BlueColumn memory endpoints so the agent can store approved session summaries, notes, documents, or audio-derived content and later retrieve relevant stored context. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill can persist conversation summaries and user-provided content to an external memory service. <br>\nMitigation: Require explicit user consent before saving session summaries, documents, audio, personal data, credentials, confidential business details, or regulated information. <br>\nRisk: The skill requires a sensitive BlueColumn API key. <br>\nMitigation: Store the API key only in a platform secret store, avoid logging or displaying it, and verify the provider endpoint before use. <br>\nRisk: Stored memory may have retention or deletion implications outside the agent runtime. <br>\nMitigation: Review BlueColumn retention and deletion terms before using the skill for production or sensitive workflows. <br>\n\n\n## Reference(s): <br>\n- [BlueColumn API Reference](references/api.md) <br>\n- [BlueColumn](https://bluecolumn.ai) <br>\n- [BlueColumn Memory on ClawHub](https://clawhub.ai/bluecolumnconsulting-lgtm/bluecolumn-memory) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Guidance, Shell commands, API Calls, Configuration] <br>\n**Output Format:** [Markdown with inline bash commands and JSON request examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Outputs may include endpoint selection guidance, curl commands, request fields, response-shape expectations, and API key handling instructions.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.0: 3 files, 2572 bytes\n\nFiles: references/api.md (1610b), SKILL.md (3069b), _meta.json (136b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: bluecolumn-memory\ndescription: Give AI agents persistent semantic memory using the BlueColumn API (bluecolumn.ai). Use when asked to remember, store, recall, or search memory using BlueColumn; when ingesting notes, conversations, documents, or audio into BlueColumn; when querying what an agent has previously stored; or when wiring up BlueColumn memory endpoints (/agent-remember, /agent-recall, /agent-note) in any workflow. Also use when the user mentions their BlueColumn API key (bc_live_*) and wants to store or retrieve information.\n---\n\n# BlueColumn Memory Skill\n\nBlueColumn is a Memory Infrastructure API — three REST endpoints that give AI agents persistent semantic memory backed by Pinecone vector storage and OpenAI embeddings.\n\n## API Key\n\nStore the user's BlueColumn API key in `TOOLS.md` under a `### BlueColumn` section:\n```\n### BlueColumn\nAPI Key: bc_live_XXXXXXXXXXXXXXXXXXXX\n```\n\nRead `TOOLS.md` to retrieve the key before making any API calls.\n\n## Core Workflow\n\n### Store something (text, doc, audio)\nUse `/agent-remember` — see references/api.md for full field spec.\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-remember \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"text\": \"...\", \"title\": \"optional title\"}'\n```\nReturns `session_id`, `summary`, `action_items`, `key_topics`.\n\n### Query memory\nUse `/agent-recall` — field is `q` (not `query`).\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-recall \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"q\": \"natural language question\"}'\n```\nReturns `answer` + `sources` with relevance scores.\n\n### Save agent observation\nUse `/agent-note` — field is `text` (not `note`), min 5 chars.\n```bash\ncurl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-note \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer <key>\" \\\n  -d '{\"text\": \"...\", \"tags\": [\"optional\", \"tags\"]}'\n```\n\n## When to Use Each Endpoint\n\n| Situation | Endpoint |\n|---|---|\n| User shares a document, transcript, or block of text to remember | `/agent-remember` |\n| User asks \"what do you know about X?\" or \"recall...\" | `/agent-recall` |\n| Agent wants to save its own observation, preference, or decision | `/agent-note` |\n| End of session — summarize and store what happened | `/agent-remember` or `/agent-note` |\n\n## End-of-Session Memory\n\nAt the end of meaningful sessions, proactively push a summary to BlueColumn:\n1. Summarize key decisions, facts, and context from the conversation\n2. POST to `/agent-remember` with `title` = session topic\n3. Confirm storage with the `session_id` returned\n\n## Field Name Gotchas\n\nCommon mistakes — read references/api.md for full details:\n- `/agent-remember` → `text` not `content`\n- `/agent-recall` → `q` not `query`  \n- `/agent-note` → `text` not `note`\n\n## Full API Reference\n\nSee [references/api.md](references/api.md) for complete field specs, response shapes, and error reference.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7469xncnrgxjxrd794277p3184vd19\",\n  \"slug\": \"bluecolumn-memory\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1776286665277\n}\n\nFile v1.0.0:references/api.md\n\n# BlueColumn API Reference\n\n**Base URL:** `https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1`\n\n**Auth header:** `Authorization: Bearer <bc_live_KEY>`\n\n## POST /agent-remember\n\nIngest text, audio URL, or file URL into vector memory.\n\n**Fields:**\n- `text` (string) — raw text to ingest ← use this for most cases\n- `audio_url` (string) — URL to audio file (Whisper transcription)\n- `file_url` (string) — URL to PDF/document\n- `title` (string, optional) — title hint\n\n**Response:** `{ success, session_id, title, summary, action_items, key_topics, chunk_count, queryable }`\n\n⚠️ Field is `text` not `content` — common mistake.\n\n## POST /agent-recall\n\nQuery memory with natural language, returns AI-generated answer + sources.\n\n**Fields:**\n- `q` (string, required) — natural language query\n\n**Response:** `{ answer, sources: [{ session_id, title, relevance }], tokens_used }`\n\n⚠️ Field is `q` not `query` — common mistake.\n\n## POST /agent-note\n\nStore a lightweight agent observation as a searchable vector.\n\n**Fields:**\n- `text` (string, required, min 5 chars) — observation to store\n- `tags` (array, optional) — string tags for filtering\n\n**Response:** `{ note_id, chunk_count, queryable }`\n\n⚠️ Field is `text` not `note` — common mistake.\n\n## Error Reference\n\n| Error | Fix |\n|---|---|\n| `Provide audio_url, file_url, or text` | Use `text` field in /agent-remember |\n| `text is required (min 5 chars)` | Use `text` field, min 5 chars in /agent-note |\n| `q (query string) is required` | Use `q` field in /agent-recall |\n| `Invalid API key` | Check key starts with `bc_live_` |","readmeExcerpt":"Skill: bluecolumn-memory Owner: bluecolumnconsulting-lgtm Summary: Store and recall persistent memory for AI agents using BlueColumn. Agents can save facts, decisions, preferences, promises, and action items, then query them later with natural language. Installable via npx skills add bluecolumnconsulting-lgtm/bluecolumn-agent-skill or copy into any agent's skill directory. Tags: agents:1.0.0, bluecolumn:1.0.0, latest","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"POST /recall\nContent-Type: application/json\nAuthorization: Bearer <api-key>"},{"language":"json","snippet":"{ \"q\": \"What did the user decide about the billing design?\" }"},{"language":"text","snippet":"POST /remember\nContent-Type: application/json\nAuthorization: Bearer <api-key>"},{"language":"json","snippet":"{\n  \"text\": \"Full raw content to store (transcript, doc, note...)\",\n  \"title\": \"Topic label, e.g. Meeting - Q3 planning - 2026-08-27\"\n}"},{"language":"text","snippet":"POST /note\nAuthorization: Bearer <api-key>"},{"language":"json","snippet":"{\n  \"text\": \"User prefers concise replies with concrete next steps\",\n  \"tags\": [\"preference\"]\n}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: bluecolumn-memory\ndescription: Store and recall persistent memory for AI agents using BlueColumn. Agents can save facts, decisions, preferences, promises, and action items, then query them later with natural language. Installable via `npx skills add bluecolumnconsulting-lgtm/bluecolumn-agent-skill` or copy into any agent's skill directory.\nversion: 1.1.0\n---\n\n# BlueColumn Memory (agent-ready)\n\nBlueColumn gives AI agents **persistent, searchable memory**. Store anything (facts, decisions, preferences, promises, action items, transcripts), then recall it later with natural-language queries — with citations back to the source.\n\nThis is the agent-facing skill. It works with any assistant that can call HTTP APIs (OpenClaw, Claude Code, Cursor, or raw HTTP).\n\n## Setup\n\n1. Get an API key at [bluecolumn.ai/login](https://bluecolumn.ai/login). Create an account; onboarding auto-provisions your first `bc_live_...` key. Copy it from **Dashboard → API Keys**.\n   - Free tier: **100 writes + 100 reads + 30 audio minutes per month** — no credit card required.\n2. Store the key wherever your agent keeps secrets (env var, secret store, or a private local notes file). Never commit it to a public repo. Keys look like `bc_live_...` (32+ chars after the prefix).\n\n## Endpoints\n\nBase URL: `https://api.bluecolumn.ai`\n\n| Action | Endpoint |\n|---|---|\n| Store memory | `POST /remember` |\n| Query memory | `POST /recall` |\n| Quick observation | `POST /note` |\n\n(Equivalent aliases also work: `/agent-remember`, `/agent-recall`, `/agent-note`.)\n\n### 1. RECALL — query memory\n\n```\nPOST /recall\nContent-Type: application/json\nAuthorization: Bearer <api-key>\n```\n\nBody:\n```json\n{ \"q\": \"What did the user decide about the billing design?\" }\n```\n\nReturns: AI-synthesized `answer` with source citations (session ids, timestamps, relevance scores).\n\n### 2. REMEMBER — store memory\n\n```\nPOST /remember\nContent-Type: application/json\nAuthorization: Bearer <api-key>\n```\n\nBody:\n```json\n{\n  \"text\": \"Full raw content to store (transcript, doc, note...)\",\n  \"title\": \"Topic label, e.g. Meeting - Q3 planning - 2026-08-27\"\n}\n```\n\nReturns: `session_id`, chunk count, auto-extracted `summary`, `action_items`, `key_topics`.\n\n### 3. NOTE — quick observation (lightweight)\n\n```\nPOST /note\nAuthorization: Bearer <api-key>\n```\n\nBody:\n```json\n{\n  \"text\": \"User prefers concise replies with concrete next steps\",\n  \"tags\": [\"preference\"]\n}\n```\n\nShort vector note for preferences and quick observations (min 5 chars). Optional tags.\n\n## Field-name gotchas\n\n- `/remember` takes `text`, not `content`\n- `/recall` takes `q`, not `query`\n- `/note` takes `text`, not `note`\n\n## Billing & limits — what to do when a call fails\n\nAll calls are metered against the account's plan. Handle these status codes:\n\n| Status | Meaning | Agent action |\n|---|---|---|\n| `401` | Invalid or missing key | Re-check the key is set and active. |\n| `402` | Free tier exhausted / insufficient credit | Stop making billable calls and tell the us"},{"path":"README.md","content":"# bluecolumn-agent-skill\n\nAgent-ready skill for [BlueColumn](https://bluecolumn.ai) — persistent, searchable memory for AI agents.\n\n## Install\n\n### OpenClaw / skills CLI\n```bash\nnpx skills add bluecolumnconsulting-lgtm/bluecolumn-agent-skill\n```\n\n### Manual\nCopy [`SKILL.md`](SKILL.md) into your agent's skill directory (e.g. `~/.openclaw/workspace/skills/bluecolumn-memory/`).\n\n## What it does\n\nGives your agent three REST calls:\n\n| Endpoint | Purpose |\n|---|---|\n| `POST /remember` | Store text, docs, or audio URLs — auto-extracts summary + action items |\n| `POST /recall` | Natural-language query → synthesized answer with source citations |\n| `POST /note` | Lightweight observation writes (preferences, decisions) |\n\nBase URL: `https://api.bluecolumn.ai` (aliases `/agent-remember`, `/agent-recall`, `/agent-note` also work).\n\nFree tier: 100 writes + 100 reads + 30 audio minutes/month, no credit card.\n\n## Get a key\n\n1. Go to [bluecolumn.ai/login](https://bluecolumn.ai/login)\n2. Create an account — onboarding auto-provisions your first `bc_live_...` key\n3. Copy it from **Dashboard → API Keys**\n\n## MCP alternative\n\nIf your agent speaks MCP (Claude Desktop, Claude Code, Cursor):\n\n```bash\nnpx bluecolumn-mcp --api-key=bc_live_xxxxxxxxxxxx\n```\n\n## Example\n\n```bash\n# Store\ncurl -X POST https://api.bluecolumn.ai/remember \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer bc_live_YOUR_KEY\" \\\n  -d '{\"text\": \"User is building a CRM agent; prefers TypeScript\", \"title\": \"User profile\"}'\n\n# Recall\ncurl -X POST https://api.bluecolumn.ai/recall \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer bc_live_YOUR_KEY\" \\\n  -d '{\"q\": \"What is the user building?\"}'\n```\n\n## Billing & limits\n\nCalls are metered per account. On `402` (free tier exhausted) or `429` (plan quota), surface the upgrade URL to the user — see SKILL.md for the full error table.\n\n## License\n\nMIT"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7469xncnrgxjxrd794277p3184vd19\",\n  \"slug\": \"bluecolumn-memory\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1790729377339\n}"},{"path":"skill-card.md","content":"## Description:\n\nHelps agents store notes and documents in BlueColumn and retrieve persistent memory with source citations.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[bluecolumnconsulting-lgtm](https://clawhub.ai/user/bluecolumnconsulting-lgtm)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent users can save decisions, preferences, and other authorized context in BlueColumn, then ask natural-language questions across sessions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Persistent storage of raw transcripts, documents, or sensitive personal content on an external service.\n\nMitigation: Save only authorized, necessary content; exclude secrets, credentials, regulated data, and confidential material unless retention and deletion controls are understood.\n\nRisk: Running unreviewed packages from installation or MCP examples.\n\nMitigation: Prefer reviewed source or pinned package versions before installation.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/bluecolumnconsulting-lgtm/skills/bluecolumn-memory)\n- [BlueColumn documentation](https://bluecolumn.ai/docs)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Configuration guidance]\n\n**Output Format:** [Markdown guidance with optional API examples and cited recall answers]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Recall answers may cite stored sources; writes may return summaries and action items.]\n\n## Skill Version(s):\n\n1.1.0 (source: skill frontmatter and server release)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Store and recall persistent memory for AI agents using BlueColumn. Agents can save facts, decisions, preferences, promises, and action items, then query them later with natural language. Installable via `npx skills add bluecolumnconsulting-lgtm/bluecolumn-agent-skill` or copy into any agent's skill directory. Skill: bluecolumn-memory Owner: bluecolumnconsulting-lgtm Summary: Store and recall persistent memory for AI agents using BlueColumn. Agents can save facts, decisions, preferences, promises, and action items, then query them later with natural language. Installable via npx skills add bluecolumnconsulting-lgtm/bluecolumn-agent-skill or copy into any agent's skill directory. Tags: agents:1.0.0, bluecolumn:1.0.0, latest","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1331,"uniquenessScore":48,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T09:32:17.111Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T09:32:17.111Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T11:24:28.564Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}