{"id":"26b5344a-fcaa-48f7-aeb0-f8b086a049e6","entityType":"agent","slug":"clawhub-skills-alibaizhanov-mengram-openclaw-skill","name":"mengram-memory","canonicalUrl":"https://www.xpersona.co/agent/clawhub-skills-alibaizhanov-mengram-openclaw-skill","canonicalPath":"/agent/clawhub-skills-alibaizhanov-mengram-openclaw-skill","generatedAt":"2026-10-10T03:14:23.029Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"Long-term memory with 3 types (facts, events, workflows). Self-improving procedures that evolve from failures. Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, tracking workflows, or reporting procedure outcomes. --- name: mengram-memory description: Long-term memory with 3 types (facts, events, workflows). Self-improving procedures that evolve from failures. Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, tracking workflows, or reporting procedure outcomes. homepage: https://github.com/AiBaizhanov","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.","installCommand":"clawhub skill install skills:alibaizhanov:mengram-openclaw-skill","sourceUrl":"https://github.com/openclaw/skills/tree/main/skills/alibaizhanov/mengram-openclaw-skill","homepage":"https://github.com/AiBaizhanov/mengram","primaryLinks":[{"label":"View on ClawHub","url":"https://github.com/openclaw/skills/tree/main/skills/alibaizhanov/mengram-openclaw-skill","kind":"source"},{"label":"Homepage","url":"https://github.com/AiBaizhanov/mengram","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":50,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Long-term memory with 3 types (facts, events, workflows). Self-improving procedures that evolve from failures. Remember user preferences, past conversations, an"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"extract","status":"self-declared"},{"label":"pass","status":"self-declared"},{"label":"use","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":4,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"extract","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"pass","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"use","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:extract|supported|profile capability:pass|supported|profile capability:use|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No source adoption metrics were available."},"stars":null,"forks":null,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-02-25T05:59:09.387Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-02-25T05:59:09.387Z","lastIndexedAt":null,"nextCrawlAt":"2026-02-26T05:59:09.387Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install skills:alibaizhanov:mengram-openclaw-skill","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-skills-alibaizhanov-mengram-openclaw-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alibaizhanov-mengram-openclaw-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alibaizhanov-mengram-openclaw-skill/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-alibaizhanov-mengram-openclaw-skill/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-alibaizhanov-mengram-openclaw-skill/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-alibaizhanov-mengram-openclaw-skill/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T03:14:23.029Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alibaizhanov-mengram-openclaw-skill/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alibaizhanov-mengram-openclaw-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alibaizhanov-mengram-openclaw-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alibaizhanov-mengram-openclaw-skill/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":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"---\nname: mengram-memory\ndescription: Long-term memory with 3 types (facts, events, workflows). Self-improving procedures that evolve from failures. Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, tracking workflows, or reporting procedure outcomes.\nhomepage: https://github.com/AiBaizhanov/mengram\nmetadata: {\"openclaw\":{\"emoji\":\"🧠\",\"requires\":{\"env\":[\"MENGRAM_API_KEY\"],\"bins\":[\"curl\",\"python3\"]},\"primaryEnv\":\"MENGRAM_API_KEY\",\"files\":[\"scripts/*\"]}}\n---\n\n# Mengram Memory\n\nHuman-like long-term memory for your OpenClaw agent. Remembers facts, events, and workflows across all sessions and channels.\n\n## What This Skill Does\n\nMengram gives you 3 types of memory that work together:\n\n- **Semantic Memory** — facts about the user (preferences, relationships, work, habits)\n- **Episodic Memory** — events with timestamps and outcomes (meetings, trips, decisions)\n- **Procedural Memory** — learned workflows with success/failure tracking (how-to steps)\n- **Experience-Driven Procedures** — workflows that self-improve: failures trigger automatic evolution, repeated successes auto-create new procedures\n\nAll memory persists across sessions and channels. What you learn on WhatsApp is available on Discord.\n\n## Tools\n\nThis skill uses `Bash` to run scripts in `{baseDir}/scripts/`.\n\n## When To Use\n\n**ALWAYS search memory before answering questions** about the user, their preferences, their history, or anything personal. This is critical — check memory first, then respond.\n\n**Save to memory after:**\n- The user shares personal information (name, preferences, habits, relationships)\n- A task or event is completed (booking, deployment, purchase)\n- A multi-step workflow is finished successfully or fails\n- The user corrects you or provides new context\n\n**Record procedure feedback after:**\n- A known workflow succeeds — run `mengram-feedback.sh` with `true`\n- A known workflow fails — run `mengram-feedback.sh` with `false` and describe what went wrong. This triggers automatic procedure evolution — the procedure improves itself.\n\n**Get profile when:**\n- Starting a new session or conversation\n- The user asks \"what do you know about me\"\n- You need comprehensive context about the user\n\n## Scripts\n\n### 1. Search Memory\n\nSearch all 3 memory types for relevant context. **Do this before answering personal questions.**\n\n```bash\nbash {baseDir}/scripts/mengram-search.sh \"search query here\"\n```\n\nReturns facts, past events, and known workflows matching the query. Use specific queries — \"coffee preferences\" not \"stuff about user\".\n\n### 2. Save to Memory\n\nSave conversation messages so Mengram can extract facts, events, and procedures automatically.\n\n```bash\nbash {baseDir}/scripts/mengram-add.sh \"user said: I'm allergic to peanuts and my meeting with Sarah went well yesterday\"\n```\n\nYou can pass multiple messages. Mengram's AI automatically extracts:\n- Facts → semantic memory (\"user is allergic to peanuts\")\n- Events → episodic memory (\"meeting with Sarah, yesterday, went well\")\n- Procedures → procedural memory (if workflow steps are described)\n\n### 3. Get Cognitive Profile\n\nGet a comprehensive portrait of the user — who they are, what they know, recent events, known workflows.\n\n```bash\nbash {baseDir}/scripts/mengram-profile.sh\n```\n\nReturns a full context block you can use to personalize responses.\n\n### 4. Save Workflow\n\nAfter completing a multi-step task, save it as a reusable procedure with success/failure tracking.\n\n```bash\nbash {baseDir}/scripts/mengram-workflow.sh \"Resolved billing issue: 1) Checked subscription status 2) Found expired card 3) Sent renewal link 4) User confirmed payment\"\n```\n\nNext time a similar task comes up, `mengram-search.sh` will return this workflow with its success rate.\n\n### 5. Procedure Feedback (Experience-Driven)\n\nRecord success or failure for a procedure. **On failure with context, the procedure automatically evolves** — AI analyzes what went wrong and creates an improved version.\n\n```bash\n# Success\nbash {baseDir}/scripts/mengram-feedback.sh \"procedure-id\" true\n\n# Failure — triggers evolution\nbash {baseDir}/scripts/mengram-feedback.sh \"procedure-id\" false \"OOM error on step 3, forgot to increase memory limit\" 3\n```\n\nArguments: `<procedure-id> <true|false> [failure context] [failed_at_step]`\n\nThe procedure ID is returned in search results. When evolution triggers, the procedure gets a new version with improved steps — automatically.\n\n### 6. List Procedures\n\nView all learned procedures, or drill into a specific one to see version history and evolution log.\n\n```bash\n# List all\nbash {baseDir}/scripts/mengram-procedures.sh\n\n# Specific procedure with version history\nbash {baseDir}/scripts/mengram-procedures.sh \"procedure-id\"\n```\n\nShows procedure name, steps, success/failure counts, version number, and full evolution history.\n\n### 7. Setup Check\n\nVerify the Mengram connection is working:\n\n```bash\nbash {baseDir}/scripts/mengram-setup.sh\n```\n\n## Recommended Behavior\n\n1. **Start of session:** Run `mengram-profile.sh` to load user context\n2. **User asks something personal:** Run `mengram-search.sh \"topic\"` before answering\n3. **User shares new info:** Run `mengram-add.sh` with the relevant messages\n4. **After completing a task:** Run `mengram-workflow.sh` with the steps taken\n5. **Task succeeded using a known procedure:** Run `mengram-feedback.sh <id> true`\n6. **Task failed using a known procedure:** Run `mengram-feedback.sh <id> false \"what went wrong\" <step>` — this evolves the procedure\n7. **Check learned procedures:** Run `mengram-procedures.sh` to see all workflows with versions\n8. **Periodically:** Run `mengram-add.sh` with recent conversation highlights to keep memory updated\n\n## Examples\n\n- \"What's my favorite restaurant?\" → `mengram-search.sh \"favorite restaurant\"`\n- \"Book the usual\" → `mengram-search.sh \"booking usual preferences\"` to find what \"the usual\" means\n- \"I just switched to a new phone, Galaxy S26\" → `mengram-add.sh \"user switched to Samsung Galaxy S26\"`\n- \"Remember that I'm vegetarian\" → `mengram-add.sh \"user is vegetarian\"`\n- User asks \"what do you know about me?\" → `mengram-profile.sh`\n- Deploy succeeded → `mengram-feedback.sh \"proc-id\" true`\n- Deploy failed at step 3 → `mengram-feedback.sh \"proc-id\" false \"forgot migrations\" 3` → procedure auto-evolves\n- \"Show me my workflows\" → `mengram-procedures.sh`\n\n## Configuration\n\nSet in `~/.openclaw/openclaw.json`:\n\n```json\n{\n  \"skills\": {\n    \"entries\": {\n      \"mengram-memory\": {\n        \"enabled\": true,\n        \"env\": {\n          \"MENGRAM_API_KEY\": \"om-your-api-key-here\"\n        }\n      }\n    }\n  }\n}\n```\n\nGet your free API key at https://mengram.io\n\n## Security & Privacy\n\n- **External endpoint:** `https://mengram.io/v1/*` (only)\n- **Data sent:** conversation text for memory extraction, search queries, procedure feedback\n- **Data stored:** extracted facts, events, procedures (with version history) on Mengram servers (PostgreSQL + pgvector)\n- **Environment variables accessed:** `MENGRAM_API_KEY` (only)\n- **Local files read/written:** none\n\n**Trust Statement:** By using this skill, conversation data is sent to mengram.io for memory extraction and storage. Only install if you trust Mengram with your conversation data. Mengram is open-source: https://github.com/AiBaizhanov/mengram\n","readmeExcerpt":"--- name: mengram-memory description: Long-term memory with 3 types (facts, events, workflows). Self-improving procedures that evolve from failures. Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, tracking workflows, or reporting procedure outcomes. homepage: https://github.com/AiBaizhanov","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"bash {baseDir}/scripts/mengram-search.sh \"search query here\""},{"language":"bash","snippet":"bash {baseDir}/scripts/mengram-add.sh \"user said: I'm allergic to peanuts and my meeting with Sarah went well yesterday\""},{"language":"bash","snippet":"bash {baseDir}/scripts/mengram-profile.sh"},{"language":"bash","snippet":"bash {baseDir}/scripts/mengram-workflow.sh \"Resolved billing issue: 1) Checked subscription status 2) Found expired card 3) Sent renewal link 4) User confirmed payment\""},{"language":"bash","snippet":"# Success\nbash {baseDir}/scripts/mengram-feedback.sh \"procedure-id\" true\n\n# Failure — triggers evolution\nbash {baseDir}/scripts/mengram-feedback.sh \"procedure-id\" false \"OOM error on step 3, forgot to increase memory limit\" 3"},{"language":"bash","snippet":"# List all\nbash {baseDir}/scripts/mengram-procedures.sh\n\n# Specific procedure with version history\nbash {baseDir}/scripts/mengram-procedures.sh \"procedure-id\""}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"CLAWHUB","editorialOverview":"Long-term memory with 3 types (facts, events, workflows). Self-improving procedures that evolve from failures. Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, tracking workflows, or reporting procedure outcomes. --- name: mengram-memory description: Long-term memory with 3 types (facts, events, workflows). Self-improving procedures that evolve from failures. Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, tracking workflows, or reporting procedure outcomes. homepage: https://github.com/AiBaizhanov","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":402,"uniquenessScore":62,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","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":"2026-04-15T00:45:39.800Z","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":"2026-10-10T03:14:23.029Z","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"}]}}}