{"id":"eca2b1eb-3537-4932-9285-c600927247ab","entityType":"agent","slug":"clawhub-fozikio-cortex-engine","name":"cortex-memory","canonicalUrl":"https://www.xpersona.co/agent/clawhub-fozikio-cortex-engine","canonicalPath":"/agent/clawhub-fozikio-cortex-engine","generatedAt":"2026-10-10T15:50:48.643Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T13:12:23.935Z","emptyReason":null},"description":"Persistent memory for AI agents. Knowledge survives across sessions: recall past decisions, track evolving beliefs, detect contradictions via NLI, and build a knowledge graph over time. 60 tools over MCP, with FSRS spaced-repetition scheduling and spreading-activation retrieval. Runs locally on SQLite and Ollama, so no cloud account is needed. Skill: cortex-memory Owner: fozikio Summary: Persistent memory for AI agents. Knowledge survives across sessions: recall past decisions, track evolving beliefs, detect contradictions via NLI, and build a knowledge graph over time. 60 tools over MCP, with FSRS spaced-repetition scheduling and spreading-activation retrieval. Runs locally on SQLite and Ollama, so no cloud account is needed. Tags: agents:1.0.1, code-revi","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s174thqtasmtez8pcz57f07ha18bj3g8:cortex-engine","sourceUrl":"https://clawhub.ai/fozikio/cortex-engine","homepage":"https://clawhub.ai/fozikio/skills/cortex-engine","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/fozikio/cortex-engine","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/fozikio/skills/cortex-engine","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":63,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Persistent memory for AI agents. Knowledge survives across sessions: recall past decisions, track evolving beliefs, detect contradictions via NLI, and build a k"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T13:12:23.935Z","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":"2026-10-10T13:12:23.935Z","emptyReason":null},"stars":null,"forks":null,"downloads":1419,"packageName":null,"latestVersion":"1.0.3","tractionLabel":"1.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T13:12:23.934Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T13:12:23.935Z","lastCrawledAt":"2026-10-10T13:12:23.934Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T13:12:23.934Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.3","createdAt":"2026-07-31T07:13:12.564Z","changelog":"Fixes an install path that silently installed a very old engine. - Install is now `npm install -g @fozikio/cortex-engine`, unpinned. The previous instructions pinned `cortex-engine@0.5.1` - the unscoped package, which is deprecated but whose old versions still resolve. The documented path therefore installed an engine two major versions behind, which worked just well enough to hide the problem. The integrity hash was removed rather than updated: it verified correctly, because it was genuinely the hash of that old package. - `npx cortex-engine@0.5.1 fozikio init` was malformed regardless of version, since `fozikio` is a declared bin. Now `fozikio init my-agent`. - Documents the 1.4.0 service CLI, previously absent entirely: `up`, `status`, `doctor`, `dashboard`, `down`. `status` and `up` probe over HTTP rather than checking for a process, and adopt rather than kill - which matters when something else already owns port 11434. - Tool table corrected from 25 to the actual 60, across 13 categories. Threads, identity/evolution, content, social, graph and signals were missing. - skill-card.md: replaced the deprecated unscoped npm link, and removed the advice to \"verify the provided integrity checksum\" - it pointed at the same outdated artifact.","fileCount":3,"zipByteSize":4569},{"version":"1.1.0","createdAt":"2026-07-31T06:51:20.104Z","changelog":"Fix install path that silently installed a deprecated ancient engine; document the 1.4.0 service CLI; correct tool count 25 -> 60","fileCount":3,"zipByteSize":4597},{"version":"1.0.2","createdAt":"2026-07-31T06:49:05.642Z","changelog":"Fix install path: was pinned to a deprecated ancient version that still resolves. Document the 1.4.0 service CLI (up/status/doctor). Correct tool count 25 -> 60.","fileCount":3,"zipByteSize":4602},{"version":"1.0.1","createdAt":"2026-03-16T07:43:21.422Z","changelog":"Added npm integrity checksum (sha512). Reframed setup as prerequisites section to clarify the skill itself is instruction-only.","fileCount":3,"zipByteSize":3479},{"version":"1.0.0","createdAt":"2026-03-16T07:41:25.180Z","changelog":"Consolidated from cortex-query + cortex-review. Fixed security: pinned npm versions, added source repo links for verification.","fileCount":2,"zipByteSize":2000}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s174thqtasmtez8pcz57f07ha18bj3g8:cortex-engine","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-fozikio-cortex-engine/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fozikio-cortex-engine/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fozikio-cortex-engine/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fozikio-cortex-engine/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fozikio-cortex-engine/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fozikio-cortex-engine/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T15:50:48.642Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fozikio-cortex-engine/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fozikio-cortex-engine/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fozikio-cortex-engine/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fozikio-cortex-engine/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":"2026-10-10T13:12:23.935Z","emptyReason":null},"readme":"Skill: cortex-memory\n\nOwner: fozikio\n\nSummary: Persistent memory for AI agents. Knowledge survives across sessions: recall past decisions, track evolving beliefs, detect contradictions via NLI, and build a knowledge graph over time. 60 tools over MCP, with FSRS spaced-repetition scheduling and spreading-activation retrieval. Runs locally on SQLite and Ollama, so no cloud account is needed.\n\nTags: agents:1.0.1, code-review:1.0.1, cognition:1.0.1, knowledge-graph:1.0.1, latest:1.1.0, mcp:1.0.1, memory:1.0.1, spaced-repetition:1.0.1\n\nVersion history:\n\nv1.0.3 | 2026-07-31T07:13:12.564Z | user\n\nFixes an install path that silently installed a very old engine.\n\n- Install is now `npm install -g @fozikio/cortex-engine`, unpinned. The previous instructions pinned `cortex-engine@0.5.1` - the unscoped package, which is deprecated but whose old versions still resolve. The documented path therefore installed an engine two major versions behind, which worked just well enough to hide the problem. The integrity hash was removed rather than updated: it verified correctly, because it was genuinely the hash of that old package.\n- `npx cortex-engine@0.5.1 fozikio init` was malformed regardless of version, since `fozikio` is a declared bin. Now `fozikio init my-agent`.\n- Documents the 1.4.0 service CLI, previously absent entirely: `up`, `status`, `doctor`, `dashboard`, `down`. `status` and `up` probe over HTTP rather than checking for a process, and adopt rather than kill - which matters when something else already owns port 11434.\n- Tool table corrected from 25 to the actual 60, across 13 categories. Threads, identity/evolution, content, social, graph and signals were missing.\n- skill-card.md: replaced the deprecated unscoped npm link, and removed the advice to \"verify the provided integrity checksum\" - it pointed at the same outdated artifact.\n\nv1.1.0 | 2026-07-31T06:51:20.104Z | user\n\nFix install path that silently installed a deprecated ancient engine; document the 1.4.0 service CLI; correct tool count 25 -> 60\n\nv1.0.2 | 2026-07-31T06:49:05.642Z | user\n\nFix install path: was pinned to a deprecated ancient version that still resolves. Document the 1.4.0 service CLI (up/status/doctor). Correct tool count 25 -> 60.\n\nv1.0.1 | 2026-03-16T07:43:21.422Z | user\n\nAdded npm integrity checksum (sha512). Reframed setup as prerequisites section to clarify the skill itself is instruction-only.\n\nv1.0.0 | 2026-03-16T07:41:25.180Z | user\n\nConsolidated from cortex-query + cortex-review. Fixed security: pinned npm versions, added source repo links for verification.\n\nArchive index:\n\nArchive v1.0.3: 3 files, 4569 bytes\n\nFiles: skill-card.md (2201b), SKILL.md (6407b), _meta.json (132b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: cortex-memory\nversion: 1.1.0\ndescription: Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.\nauthor: idapixl\ntags: [memory, cognition, mcp, agents, knowledge-graph, spaced-repetition, code-review, fsrs]\n---\n\n# Cortex Memory\n\nPersistent memory engine for AI agents. Knowledge survives across sessions — recall what you learned last week, track evolving beliefs, detect contradictions, and build a knowledge graph over time.\n\n**Source:** [github.com/Fozikio/cortex-engine](https://github.com/Fozikio/cortex-engine) (MIT) | [npm](https://www.npmjs.com/package/@fozikio/cortex-engine)\n\n## Prerequisites\n\nThis skill requires [cortex-engine](https://github.com/Fozikio/cortex-engine) running as an MCP server. Install it separately before using this skill:\n\n```bash\nnpm install -g @fozikio/cortex-engine\n```\n\n> **Install the scoped package, unpinned.** The unscoped `cortex-engine` on npm is the old name and is deprecated — but old versions of it still resolve, so pinning one installs an ancient engine that works just well enough to hide the problem. Always use `@fozikio/cortex-engine`, and let it take the latest.\n\nThen initialize and start:\n\n```bash\nfozikio init my-agent    # scaffold a workspace\nfozikio up               # start ollama + nli, wait until they answer\nfozikio serve            # start the MCP server (stdio)\n```\n\nIf anything goes wrong, `fozikio doctor` diagnoses the install and tells you how to fix it.\n\nRuns locally with SQLite + Ollama. No cloud accounts needed. The skill instructions below are read-only — they teach your agent how to use cortex tools, they don't execute anything.\n\n## Managing the services\n\n`cortex-engine` 1.4.0+ ships a service supervisor, so you do not have to babysit Ollama:\n\n| Command | What it does |\n|---|---|\n| `fozikio up` | start every service and wait until it actually answers |\n| `fozikio status` | service health (HTTP probe, not PID liveness); exits 1 if unhealthy |\n| `fozikio doctor` | diagnose the install and say how to fix what is broken |\n| `fozikio dashboard` | live service and memory view |\n| `fozikio down` | stop services it started |\n\n`status` and `up` use an HTTP probe rather than checking whether a process exists, because a wedged process still holds the port. They also **adopt rather than kill**: if fozikio did not start a process, it will not stop it — which matters when the Ollama desktop app or another agent already owns `:11434`.\n\n## Core Loop\n\n**Read before you write.** Always check what you already know before adding more.\n\n### Search\n\n```\nquery(\"authentication architecture decisions\")\n```\n\nBe specific. `query(\"JWT token expiry policy\")` beats `query(\"auth\")`. Results include relevance scores and connected concepts.\n\nExplore around a result:\n```\nneighbors(memory_id)\n```\n\n### Record\n\n**Facts** — things you confirmed:\n```\nobserve(\"The API rate limits at 1000 req/min per API key, not per user\")\n```\n\n**Questions** — unresolved:\n```\nwonder(\"Why does the sync daemon stall after 300k seconds?\")\n```\n\n**Hypotheses** — unconfirmed ideas:\n```\nspeculate(\"Connection pooling might fix the timeout issues\")\n```\n\n### Update beliefs\n\n```\nbelieve(concept_id, \"Revised understanding based on new evidence\", \"reason\")\n```\n\n### Track work across sessions\n\n```\nops_append(\"Finished auth refactor, tests passing\", project=\"api-v2\")\nops_query(project=\"api-v2\")  # pick up where you left off\n```\n\n## Memory-Grounded Reviews\n\nReview code or designs by comparing against accumulated knowledge:\n\n1. **Ground:** `query(\"the domain being reviewed\")` — load past decisions and patterns\n2. **Compare:** Does the work align with or diverge from established patterns?\n3. **Record:** `observe()` new patterns, `wonder()` about unclear choices, `believe()` updated understanding\n4. **Output:**\n\n```markdown\n## Review — Grounded in Memory\n\n### Aligned with known patterns\n- [matches cortex context]\n\n### Divergences\n- [what differs, intentional or accidental]\n\n### New patterns to capture\n- [novel approaches worth observing]\n```\n\n## Session Pattern\n\n1. **Start:** `query()` the topic you're working on\n2. **During:** `observe()` facts, `wonder()` questions as they come up\n3. **End:** `ops_append()` what you did and what's unfinished\n4. **Periodically:** `dream()` to consolidate memories (compress, abstract, prune)\n\n## Available Tools\n\n**60 tools** across 13 categories. Run `fozikio tools` for the full list with descriptions.\n\n| Category | Count | Tools |\n|---|---|---|\n| **memory** | 11 | context, federated_query, feedback, neighbors, observe, query, query_cross, recall, retrieve, speculate, wonder |\n| **consolidation** | 5 | abstract, digest, dream, ruminate, wander |\n| **beliefs** | 4 | belief, believe, contradict, validate |\n| **ops** | 3 | ops_append, ops_query, ops_update |\n| **threads** | 4 | thread_create, thread_resolve, thread_update, threads_list |\n| **journal** | 5 | evolution_list, evolution_resolve, evolve, journal_read, journal_write |\n| **social** | 4 | social_draft, social_read, social_score, social_update |\n| **content** | 3 | content_create, content_list, content_update |\n| **graph** | 4 | link, resolve, suggest_links, suggest_tags |\n| **vitals** | 2 | vitals_get, vitals_set |\n| **agents** | 2 | agent_invoke, intention |\n| **maintenance** | 5 | find_duplicates, forget, goal_set, notice, surface |\n| **meta** | 8 | consolidation_status, graph_report, predict, query_explain, retrieval_audit, sleep_pressure, stats, suggest |\n\n### Beyond the basics\n\n- **threads** — multi-session explorations. A thread is something you want to keep thinking about, distinct from an ops log entry recording what happened.\n- **journal / evolution** — identity change over time. `evolve()` proposes a shift; `evolution_resolve()` applies, rejects, or reverts it, so the ledger reflects what was actually adopted rather than only what was suggested.\n- **beliefs** — `contradict()` adjudicates whether an observation genuinely conflicts with an existing memory (via NLI, falling back to the LLM) and records a CONTRADICTION or TENSION signal rather than silently overwriting.\n- **meta** — `sleep_pressure()` and `consolidation_status()` tell you whether `dream()` is overdue; `retrieval_audit()` and `query_explain()` show why a query returned what it did.\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn72z63n9q59956xsvygf25e5d82xx7m\",\n  \"slug\": \"cortex-engine\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1785481992564\n}\n\nFile v1.0.3:skill-card.md\n\n## Description: <br>\nPersistent cognitive memory for AI agents: query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[idapixl](https://clawhub.ai/user/idapixl) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent builders use this skill to give agents persistent local memory for recalling prior decisions, tracking evolving beliefs, detecting contradictions, and continuing work across sessions. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill enables long-lived local memory that can retain project and personal context across sessions. <br>\nMitigation: Avoid storing secrets or sensitive business details unless local retention is acceptable for the deployment. <br>\nRisk: The skill depends on a globally installed external npm package and local services. <br>\nMitigation: Review the npm package and service behavior before installation, and use the documented scoped package @fozikio/cortex-engine. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/idapixl/skills/cortex-engine) <br>\n- [cortex-engine GitHub repository](https://github.com/Fozikio/cortex-engine) <br>\n- [@fozikio/cortex-engine npm package](https://www.npmjs.com/package/@fozikio/cortex-engine) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown with inline shell commands and tool-call examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Guides an agent through local MCP memory workflows for querying, recording, reviewing, and consolidating knowledge.] <br>\n\n## Skill Version(s): <br>\n1.0.3 (source: ClawHub release evidence) <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 v1.1.0: 3 files, 4597 bytes\n\nFiles: skill-card.md (2208b), SKILL.md (6407b), _meta.json (132b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: cortex-memory\nversion: 1.1.0\ndescription: Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.\nauthor: idapixl\ntags: [memory, cognition, mcp, agents, knowledge-graph, spaced-repetition, code-review, fsrs]\n---\n\n# Cortex Memory\n\nPersistent memory engine for AI agents. Knowledge survives across sessions — recall what you learned last week, track evolving beliefs, detect contradictions, and build a knowledge graph over time.\n\n**Source:** [github.com/Fozikio/cortex-engine](https://github.com/Fozikio/cortex-engine) (MIT) | [npm](https://www.npmjs.com/package/@fozikio/cortex-engine)\n\n## Prerequisites\n\nThis skill requires [cortex-engine](https://github.com/Fozikio/cortex-engine) running as an MCP server. Install it separately before using this skill:\n\n```bash\nnpm install -g @fozikio/cortex-engine\n```\n\n> **Install the scoped package, unpinned.** The unscoped `cortex-engine` on npm is the old name and is deprecated — but old versions of it still resolve, so pinning one installs an ancient engine that works just well enough to hide the problem. Always use `@fozikio/cortex-engine`, and let it take the latest.\n\nThen initialize and start:\n\n```bash\nfozikio init my-agent    # scaffold a workspace\nfozikio up               # start ollama + nli, wait until they answer\nfozikio serve            # start the MCP server (stdio)\n```\n\nIf anything goes wrong, `fozikio doctor` diagnoses the install and tells you how to fix it.\n\nRuns locally with SQLite + Ollama. No cloud accounts needed. The skill instructions below are read-only — they teach your agent how to use cortex tools, they don't execute anything.\n\n## Managing the services\n\n`cortex-engine` 1.4.0+ ships a service supervisor, so you do not have to babysit Ollama:\n\n| Command | What it does |\n|---|---|\n| `fozikio up` | start every service and wait until it actually answers |\n| `fozikio status` | service health (HTTP probe, not PID liveness); exits 1 if unhealthy |\n| `fozikio doctor` | diagnose the install and say how to fix what is broken |\n| `fozikio dashboard` | live service and memory view |\n| `fozikio down` | stop services it started |\n\n`status` and `up` use an HTTP probe rather than checking whether a process exists, because a wedged process still holds the port. They also **adopt rather than kill**: if fozikio did not start a process, it will not stop it — which matters when the Ollama desktop app or another agent already owns `:11434`.\n\n## Core Loop\n\n**Read before you write.** Always check what you already know before adding more.\n\n### Search\n\n```\nquery(\"authentication architecture decisions\")\n```\n\nBe specific. `query(\"JWT token expiry policy\")` beats `query(\"auth\")`. Results include relevance scores and connected concepts.\n\nExplore around a result:\n```\nneighbors(memory_id)\n```\n\n### Record\n\n**Facts** — things you confirmed:\n```\nobserve(\"The API rate limits at 1000 req/min per API key, not per user\")\n```\n\n**Questions** — unresolved:\n```\nwonder(\"Why does the sync daemon stall after 300k seconds?\")\n```\n\n**Hypotheses** — unconfirmed ideas:\n```\nspeculate(\"Connection pooling might fix the timeout issues\")\n```\n\n### Update beliefs\n\n```\nbelieve(concept_id, \"Revised understanding based on new evidence\", \"reason\")\n```\n\n### Track work across sessions\n\n```\nops_append(\"Finished auth refactor, tests passing\", project=\"api-v2\")\nops_query(project=\"api-v2\")  # pick up where you left off\n```\n\n## Memory-Grounded Reviews\n\nReview code or designs by comparing against accumulated knowledge:\n\n1. **Ground:** `query(\"the domain being reviewed\")` — load past decisions and patterns\n2. **Compare:** Does the work align with or diverge from established patterns?\n3. **Record:** `observe()` new patterns, `wonder()` about unclear choices, `believe()` updated understanding\n4. **Output:**\n\n```markdown\n## Review — Grounded in Memory\n\n### Aligned with known patterns\n- [matches cortex context]\n\n### Divergences\n- [what differs, intentional or accidental]\n\n### New patterns to capture\n- [novel approaches worth observing]\n```\n\n## Session Pattern\n\n1. **Start:** `query()` the topic you're working on\n2. **During:** `observe()` facts, `wonder()` questions as they come up\n3. **End:** `ops_append()` what you did and what's unfinished\n4. **Periodically:** `dream()` to consolidate memories (compress, abstract, prune)\n\n## Available Tools\n\n**60 tools** across 13 categories. Run `fozikio tools` for the full list with descriptions.\n\n| Category | Count | Tools |\n|---|---|---|\n| **memory** | 11 | context, federated_query, feedback, neighbors, observe, query, query_cross, recall, retrieve, speculate, wonder |\n| **consolidation** | 5 | abstract, digest, dream, ruminate, wander |\n| **beliefs** | 4 | belief, believe, contradict, validate |\n| **ops** | 3 | ops_append, ops_query, ops_update |\n| **threads** | 4 | thread_create, thread_resolve, thread_update, threads_list |\n| **journal** | 5 | evolution_list, evolution_resolve, evolve, journal_read, journal_write |\n| **social** | 4 | social_draft, social_read, social_score, social_update |\n| **content** | 3 | content_create, content_list, content_update |\n| **graph** | 4 | link, resolve, suggest_links, suggest_tags |\n| **vitals** | 2 | vitals_get, vitals_set |\n| **agents** | 2 | agent_invoke, intention |\n| **maintenance** | 5 | find_duplicates, forget, goal_set, notice, surface |\n| **meta** | 8 | consolidation_status, graph_report, predict, query_explain, retrieval_audit, sleep_pressure, stats, suggest |\n\n### Beyond the basics\n\n- **threads** — multi-session explorations. A thread is something you want to keep thinking about, distinct from an ops log entry recording what happened.\n- **journal / evolution** — identity change over time. `evolve()` proposes a shift; `evolution_resolve()` applies, rejects, or reverts it, so the ledger reflects what was actually adopted rather than only what was suggested.\n- **beliefs** — `contradict()` adjudicates whether an observation genuinely conflicts with an existing memory (via NLI, falling back to the LLM) and records a CONTRADICTION or TENSION signal rather than silently overwriting.\n- **meta** — `sleep_pressure()` and `consolidation_status()` tell you whether `dream()` is overdue; `retrieval_audit()` and `query_explain()` show why a query returned what it did.\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn72z63n9q59956xsvygf25e5d82xx7m\",\n  \"slug\": \"cortex-engine\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1785480680104\n}\n\nFile v1.1.0:skill-card.md\n\n## Description:\n\nPersistent cognitive memory for AI agents -- query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[fozikio](https://clawhub.ai/user/fozikio)\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 a local persistent-memory MCP service for querying prior knowledge, recording facts and questions, tracking work across sessions, and producing memory-grounded reviews.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill installs and relies on a changing third-party local service package.\n\nMitigation: Review the @fozikio/cortex-engine package before installation and prefer a reviewed pinned version or local locked install when possible.\n\nRisk: Observations, beliefs, operational notes, and consolidations persist across agent sessions.\n\nMitigation: Avoid storing secrets unless intentional, and periodically review or prune persisted memory contents.\n\nRisk: The local memory service may access local resources while running.\n\nMitigation: Run the service with the least local access practical.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/fozikio/skills/cortex-engine)\n- [@fozikio/cortex-engine npm package](https://www.npmjs.com/package/@fozikio/cortex-engine)\n- [Cortex Engine project](https://github.com/Fozikio/cortex-engine)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown, Shell commands]\n\n**Output Format:** [Markdown with inline tool examples and shell commands]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Guides use of a local MCP memory service and may produce structured review notes grounded in stored memory.]\n\n## Skill Version(s):\n\n1.1.0 (source: server release evidence and skill frontmatter)\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: 3 files, 4602 bytes\n\nFiles: skill-card.md (2235b), SKILL.md (6407b), _meta.json (132b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: cortex-memory\nversion: 1.1.0\ndescription: Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.\nauthor: idapixl\ntags: [memory, cognition, mcp, agents, knowledge-graph, spaced-repetition, code-review, fsrs]\n---\n\n# Cortex Memory\n\nPersistent memory engine for AI agents. Knowledge survives across sessions — recall what you learned last week, track evolving beliefs, detect contradictions, and build a knowledge graph over time.\n\n**Source:** [github.com/Fozikio/cortex-engine](https://github.com/Fozikio/cortex-engine) (MIT) | [npm](https://www.npmjs.com/package/@fozikio/cortex-engine)\n\n## Prerequisites\n\nThis skill requires [cortex-engine](https://github.com/Fozikio/cortex-engine) running as an MCP server. Install it separately before using this skill:\n\n```bash\nnpm install -g @fozikio/cortex-engine\n```\n\n> **Install the scoped package, unpinned.** The unscoped `cortex-engine` on npm is the old name and is deprecated — but old versions of it still resolve, so pinning one installs an ancient engine that works just well enough to hide the problem. Always use `@fozikio/cortex-engine`, and let it take the latest.\n\nThen initialize and start:\n\n```bash\nfozikio init my-agent    # scaffold a workspace\nfozikio up               # start ollama + nli, wait until they answer\nfozikio serve            # start the MCP server (stdio)\n```\n\nIf anything goes wrong, `fozikio doctor` diagnoses the install and tells you how to fix it.\n\nRuns locally with SQLite + Ollama. No cloud accounts needed. The skill instructions below are read-only — they teach your agent how to use cortex tools, they don't execute anything.\n\n## Managing the services\n\n`cortex-engine` 1.4.0+ ships a service supervisor, so you do not have to babysit Ollama:\n\n| Command | What it does |\n|---|---|\n| `fozikio up` | start every service and wait until it actually answers |\n| `fozikio status` | service health (HTTP probe, not PID liveness); exits 1 if unhealthy |\n| `fozikio doctor` | diagnose the install and say how to fix what is broken |\n| `fozikio dashboard` | live service and memory view |\n| `fozikio down` | stop services it started |\n\n`status` and `up` use an HTTP probe rather than checking whether a process exists, because a wedged process still holds the port. They also **adopt rather than kill**: if fozikio did not start a process, it will not stop it — which matters when the Ollama desktop app or another agent already owns `:11434`.\n\n## Core Loop\n\n**Read before you write.** Always check what you already know before adding more.\n\n### Search\n\n```\nquery(\"authentication architecture decisions\")\n```\n\nBe specific. `query(\"JWT token expiry policy\")` beats `query(\"auth\")`. Results include relevance scores and connected concepts.\n\nExplore around a result:\n```\nneighbors(memory_id)\n```\n\n### Record\n\n**Facts** — things you confirmed:\n```\nobserve(\"The API rate limits at 1000 req/min per API key, not per user\")\n```\n\n**Questions** — unresolved:\n```\nwonder(\"Why does the sync daemon stall after 300k seconds?\")\n```\n\n**Hypotheses** — unconfirmed ideas:\n```\nspeculate(\"Connection pooling might fix the timeout issues\")\n```\n\n### Update beliefs\n\n```\nbelieve(concept_id, \"Revised understanding based on new evidence\", \"reason\")\n```\n\n### Track work across sessions\n\n```\nops_append(\"Finished auth refactor, tests passing\", project=\"api-v2\")\nops_query(project=\"api-v2\")  # pick up where you left off\n```\n\n## Memory-Grounded Reviews\n\nReview code or designs by comparing against accumulated knowledge:\n\n1. **Ground:** `query(\"the domain being reviewed\")` — load past decisions and patterns\n2. **Compare:** Does the work align with or diverge from established patterns?\n3. **Record:** `observe()` new patterns, `wonder()` about unclear choices, `believe()` updated understanding\n4. **Output:**\n\n```markdown\n## Review — Grounded in Memory\n\n### Aligned with known patterns\n- [matches cortex context]\n\n### Divergences\n- [what differs, intentional or accidental]\n\n### New patterns to capture\n- [novel approaches worth observing]\n```\n\n## Session Pattern\n\n1. **Start:** `query()` the topic you're working on\n2. **During:** `observe()` facts, `wonder()` questions as they come up\n3. **End:** `ops_append()` what you did and what's unfinished\n4. **Periodically:** `dream()` to consolidate memories (compress, abstract, prune)\n\n## Available Tools\n\n**60 tools** across 13 categories. Run `fozikio tools` for the full list with descriptions.\n\n| Category | Count | Tools |\n|---|---|---|\n| **memory** | 11 | context, federated_query, feedback, neighbors, observe, query, query_cross, recall, retrieve, speculate, wonder |\n| **consolidation** | 5 | abstract, digest, dream, ruminate, wander |\n| **beliefs** | 4 | belief, believe, contradict, validate |\n| **ops** | 3 | ops_append, ops_query, ops_update |\n| **threads** | 4 | thread_create, thread_resolve, thread_update, threads_list |\n| **journal** | 5 | evolution_list, evolution_resolve, evolve, journal_read, journal_write |\n| **social** | 4 | social_draft, social_read, social_score, social_update |\n| **content** | 3 | content_create, content_list, content_update |\n| **graph** | 4 | link, resolve, suggest_links, suggest_tags |\n| **vitals** | 2 | vitals_get, vitals_set |\n| **agents** | 2 | agent_invoke, intention |\n| **maintenance** | 5 | find_duplicates, forget, goal_set, notice, surface |\n| **meta** | 8 | consolidation_status, graph_report, predict, query_explain, retrieval_audit, sleep_pressure, stats, suggest |\n\n### Beyond the basics\n\n- **threads** — multi-session explorations. A thread is something you want to keep thinking about, distinct from an ops log entry recording what happened.\n- **journal / evolution** — identity change over time. `evolve()` proposes a shift; `evolution_resolve()` applies, rejects, or reverts it, so the ledger reflects what was actually adopted rather than only what was suggested.\n- **beliefs** — `contradict()` adjudicates whether an observation genuinely conflicts with an existing memory (via NLI, falling back to the LLM) and records a CONTRADICTION or TENSION signal rather than silently overwriting.\n- **meta** — `sleep_pressure()` and `consolidation_status()` tell you whether `dream()` is overdue; `retrieval_audit()` and `query_explain()` show why a query returned what it did.\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn72z63n9q59956xsvygf25e5d82xx7m\",\n  \"slug\": \"cortex-engine\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1785480545642\n}\n\nFile v1.0.2:skill-card.md\n\n## Description: <br>\nPersistent cognitive memory for AI agents that can query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[idapixl](https://clawhub.ai/user/idapixl) <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 give an AI agent durable local memory for recalling prior decisions, tracking beliefs, recording unresolved questions, and carrying work context across sessions. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Durable local memory can preserve sensitive, stale, or incorrect information across sessions. <br>\nMitigation: Be deliberate about what the agent records or updates, and periodically review stored memories, beliefs, journals, and logs. <br>\nRisk: The skill depends on the separately installed @fozikio/cortex-engine package and local services. <br>\nMitigation: Review that package before global installation and use the documented service health and diagnostic commands before relying on the memory server. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/idapixl/skills/cortex-engine) <br>\n- [cortex-engine GitHub repository](https://github.com/Fozikio/cortex-engine) <br>\n- [@fozikio/cortex-engine npm package](https://www.npmjs.com/package/@fozikio/cortex-engine) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, markdown, shell commands, configuration] <br>\n**Output Format:** [Markdown with inline shell commands and tool-call examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Guides use of a local MCP memory service backed by SQLite and Ollama.] <br>\n\n## Skill Version(s): <br>\n1.0.2 (source: server release metadata; artifact frontmatter lists 1.1.0) <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 v1.0.1: 3 files, 3479 bytes\n\nFiles: skill-card.md (2515b), SKILL.md (3515b), _meta.json (132b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: cortex-memory\nversion: 1.0.0\ndescription: Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.\nauthor: idapixl\ntags: [memory, cognition, mcp, agents, knowledge-graph, spaced-repetition, code-review, fsrs]\n---\n\n# Cortex Memory\n\nPersistent memory engine for AI agents. Knowledge survives across sessions — recall what you learned last week, track evolving beliefs, detect contradictions, and build a knowledge graph over time.\n\n**Source:** [github.com/Fozikio/cortex-engine](https://github.com/Fozikio/cortex-engine) (MIT) | [npm](https://www.npmjs.com/package/cortex-engine)\n\n## Prerequisites\n\nThis skill requires [cortex-engine](https://github.com/Fozikio/cortex-engine) running as an MCP server. Install it separately before using this skill:\n\n```bash\nnpm install cortex-engine@0.5.1\n# Integrity: sha512-8oIL8KenrdTdACAMSM/iqyrxx04yFE/3IfHx1dTF2439ljXhSCvULcNF5V10tH8UK7P/zuwmx3RuNynvjGi4kg==\n```\n\nThen initialize and start:\n```bash\nnpx cortex-engine@0.5.1 fozikio init my-agent\nnpx cortex-engine@0.5.1  # starts MCP server\n```\n\nRuns locally with SQLite + Ollama. No cloud accounts needed. The skill instructions below are read-only — they teach your agent how to use cortex tools, they don't execute anything.\n\n## Core Loop\n\n**Read before you write.** Always check what you already know before adding more.\n\n### Search\n\n```\nquery(\"authentication architecture decisions\")\n```\n\nBe specific. `query(\"JWT token expiry policy\")` beats `query(\"auth\")`. Results include relevance scores and connected concepts.\n\nExplore around a result:\n```\nneighbors(memory_id)\n```\n\n### Record\n\n**Facts** — things you confirmed:\n```\nobserve(\"The API rate limits at 1000 req/min per API key, not per user\")\n```\n\n**Questions** — unresolved:\n```\nwonder(\"Why does the sync daemon stall after 300k seconds?\")\n```\n\n**Hypotheses** — unconfirmed ideas:\n```\nspeculate(\"Connection pooling might fix the timeout issues\")\n```\n\n### Update beliefs\n\n```\nbelieve(concept_id, \"Revised understanding based on new evidence\", \"reason\")\n```\n\n### Track work across sessions\n\n```\nops_append(\"Finished auth refactor, tests passing\", project=\"api-v2\")\nops_query(project=\"api-v2\")  # pick up where you left off\n```\n\n## Memory-Grounded Reviews\n\nReview code or designs by comparing against accumulated knowledge:\n\n1. **Ground:** `query(\"the domain being reviewed\")` — load past decisions and patterns\n2. **Compare:** Does the work align with or diverge from established patterns?\n3. **Record:** `observe()` new patterns, `wonder()` about unclear choices, `believe()` updated understanding\n4. **Output:**\n\n```markdown\n## Review — Grounded in Memory\n\n### Aligned with known patterns\n- [matches cortex context]\n\n### Divergences\n- [what differs, intentional or accidental]\n\n### New patterns to capture\n- [novel approaches worth observing]\n```\n\n## Session Pattern\n\n1. **Start:** `query()` the topic you're working on\n2. **During:** `observe()` facts, `wonder()` questions as they come up\n3. **End:** `ops_append()` what you did and what's unfinished\n4. **Periodically:** `dream()` to consolidate memories (compress, abstract, prune)\n\n## Available Tools\n\n| Category | Tools |\n|----------|-------|\n| **Read** | query, recall, predict, validate, neighbors, wander |\n| **Write** | observe, wonder, speculate, believe, reflect, digest |\n| **Ops** | ops_append, ops_query, ops_update |\n| **System** | stats, dream |\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn72z63n9q59956xsvygf25e5d82xx7m\",\n  \"slug\": \"cortex-engine\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1773647001422\n}\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nPersistent cognitive memory for AI agents that helps query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and contradiction detection. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[idapixl](https://clawhub.ai/user/idapixl) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent operators use Cortex Engine to give agents local long-term memory across sessions, including querying prior knowledge, recording facts and questions, updating beliefs, tracking work, and producing memory-grounded reviews. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Persistent local memory may retain sensitive information if an agent records secrets, private customer data, or other restricted material. <br>\nMitigation: Avoid recording passwords, tokens, private customer data, or other sensitive material unless appropriate local data controls are in place. <br>\nRisk: The skill depends on a separately installed cortex-engine npm package and local MCP server. <br>\nMitigation: Review the separate cortex-engine package before installation and run it only in intended local environments. <br>\nRisk: Memory-grounded outputs can reflect outdated or incorrect stored beliefs. <br>\nMitigation: Query existing memory before writing, update beliefs when evidence changes, and review generated findings before relying on them. <br>\n\n\n## Reference(s): <br>\n- [Cortex Engine ClawHub Skill Page](https://clawhub.ai/idapixl/skills/cortex-engine) <br>\n- [Cortex Engine npm Package](https://www.npmjs.com/package/cortex-engine) <br>\n- [Cortex Engine GitHub Repository](https://github.com/Fozikio/cortex-engine) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance] <br>\n**Output Format:** [Markdown guidance with inline shell commands and MCP tool-call examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Instruction-only skill; requires a separately installed local cortex-engine MCP server.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: ClawHub 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: 2 files, 2000 bytes\n\nFiles: SKILL.md (3204b), _meta.json (132b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: cortex-memory\nversion: 1.0.0\ndescription: Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.\nauthor: idapixl\ntags: [memory, cognition, mcp, agents, knowledge-graph, spaced-repetition, code-review, fsrs]\n---\n\n# Cortex Memory\n\nPersistent memory engine for AI agents. Knowledge survives across sessions — recall what you learned last week, track evolving beliefs, detect contradictions, and build a knowledge graph over time.\n\n**Source:** [github.com/Fozikio/cortex-engine](https://github.com/Fozikio/cortex-engine) (MIT) | [npm](https://www.npmjs.com/package/cortex-engine)\n\n## Setup\n\n```bash\n# Install with pinned version — verify source at the links above before running\nnpm install cortex-engine@0.5.1\n\n# Initialize a new agent workspace\nnpx cortex-engine@0.5.1 fozikio init my-agent\n\n# Start the MCP server\nnpx cortex-engine@0.5.1\n```\n\nRuns locally with SQLite + Ollama. No cloud accounts needed.\n\n## Core Loop\n\n**Read before you write.** Always check what you already know before adding more.\n\n### Search\n\n```\nquery(\"authentication architecture decisions\")\n```\n\nBe specific. `query(\"JWT token expiry policy\")` beats `query(\"auth\")`. Results include relevance scores and connected concepts.\n\nExplore around a result:\n```\nneighbors(memory_id)\n```\n\n### Record\n\n**Facts** — things you confirmed:\n```\nobserve(\"The API rate limits at 1000 req/min per API key, not per user\")\n```\n\n**Questions** — unresolved:\n```\nwonder(\"Why does the sync daemon stall after 300k seconds?\")\n```\n\n**Hypotheses** — unconfirmed ideas:\n```\nspeculate(\"Connection pooling might fix the timeout issues\")\n```\n\n### Update beliefs\n\n```\nbelieve(concept_id, \"Revised understanding based on new evidence\", \"reason\")\n```\n\n### Track work across sessions\n\n```\nops_append(\"Finished auth refactor, tests passing\", project=\"api-v2\")\nops_query(project=\"api-v2\")  # pick up where you left off\n```\n\n## Memory-Grounded Reviews\n\nReview code or designs by comparing against accumulated knowledge:\n\n1. **Ground:** `query(\"the domain being reviewed\")` — load past decisions and patterns\n2. **Compare:** Does the work align with or diverge from established patterns?\n3. **Record:** `observe()` new patterns, `wonder()` about unclear choices, `believe()` updated understanding\n4. **Output:**\n\n```markdown\n## Review — Grounded in Memory\n\n### Aligned with known patterns\n- [matches cortex context]\n\n### Divergences\n- [what differs, intentional or accidental]\n\n### New patterns to capture\n- [novel approaches worth observing]\n```\n\n## Session Pattern\n\n1. **Start:** `query()` the topic you're working on\n2. **During:** `observe()` facts, `wonder()` questions as they come up\n3. **End:** `ops_append()` what you did and what's unfinished\n4. **Periodically:** `dream()` to consolidate memories (compress, abstract, prune)\n\n## Available Tools\n\n| Category | Tools |\n|----------|-------|\n| **Read** | query, recall, predict, validate, neighbors, wander |\n| **Write** | observe, wonder, speculate, believe, reflect, digest |\n| **Ops** | ops_append, ops_query, ops_update |\n| **System** | stats, dream |\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn72z63n9q59956xsvygf25e5d82xx7m\",\n  \"slug\": \"cortex-engine\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1773646885180\n}","readmeExcerpt":"Skill: cortex-memory Owner: fozikio Summary: Persistent memory for AI agents. Knowledge survives across sessions: recall past decisions, track evolving beliefs, detect contradictions via NLI, and build a knowledge graph over time. 60 tools over MCP, with FSRS spaced-repetition scheduling and spreading-activation retrieval. Runs locally on SQLite and Ollama, so no cloud account is needed. Tags: agents:1.0.1, code-revi","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"npm install -g @fozikio/cortex-engine"},{"language":"bash","snippet":"fozikio init my-agent    # scaffold a workspace\nfozikio up               # start ollama + nli, wait until they answer\nfozikio serve            # start the MCP server (stdio)"},{"language":"text","snippet":"query(\"authentication architecture decisions\")"},{"language":"text","snippet":"neighbors(memory_id)"},{"language":"text","snippet":"observe(\"The API rate limits at 1000 req/min per API key, not per user\")"},{"language":"text","snippet":"wonder(\"Why does the sync daemon stall after 300k seconds?\")"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: cortex-memory\nversion: 1.1.0\ndescription: Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.\nauthor: idapixl\ntags: [memory, cognition, mcp, agents, knowledge-graph, spaced-repetition, code-review, fsrs]\n---\n\n# Cortex Memory\n\nPersistent memory engine for AI agents. Knowledge survives across sessions — recall what you learned last week, track evolving beliefs, detect contradictions, and build a knowledge graph over time.\n\n**Source:** [github.com/Fozikio/cortex-engine](https://github.com/Fozikio/cortex-engine) (MIT) | [npm](https://www.npmjs.com/package/@fozikio/cortex-engine)\n\n## Prerequisites\n\nThis skill requires [cortex-engine](https://github.com/Fozikio/cortex-engine) running as an MCP server. Install it separately before using this skill:\n\n```bash\nnpm install -g @fozikio/cortex-engine\n```\n\n> **Install the scoped package, unpinned.** The unscoped `cortex-engine` on npm is the old name and is deprecated — but old versions of it still resolve, so pinning one installs an ancient engine that works just well enough to hide the problem. Always use `@fozikio/cortex-engine`, and let it take the latest.\n\nThen initialize and start:\n\n```bash\nfozikio init my-agent    # scaffold a workspace\nfozikio up               # start ollama + nli, wait until they answer\nfozikio serve            # start the MCP server (stdio)\n```\n\nIf anything goes wrong, `fozikio doctor` diagnoses the install and tells you how to fix it.\n\nRuns locally with SQLite + Ollama. No cloud accounts needed. The skill instructions below are read-only — they teach your agent how to use cortex tools, they don't execute anything.\n\n## Managing the services\n\n`cortex-engine` 1.4.0+ ships a service supervisor, so you do not have to babysit Ollama:\n\n| Command | What it does |\n|---|---|\n| `fozikio up` | start every service and wait until it actually answers |\n| `fozikio status` | service health (HTTP probe, not PID liveness); exits 1 if unhealthy |\n| `fozikio doctor` | diagnose the install and say how to fix what is broken |\n| `fozikio dashboard` | live service and memory view |\n| `fozikio down` | stop services it started |\n\n`status` and `up` use an HTTP probe rather than checking whether a process exists, because a wedged process still holds the port. They also **adopt rather than kill**: if fozikio did not start a process, it will not stop it — which matters when the Ollama desktop app or another agent already owns `:11434`.\n\n## Core Loop\n\n**Read before you write.** Always check what you already know before adding more.\n\n### Search\n\n```\nquery(\"authentication architecture decisions\")\n```\n\nBe specific. `query(\"JWT token expiry policy\")` beats `query(\"auth\")`. Results include relevance scores and connected concepts.\n\nExplore around a result:\n```\nneighbors(memory_id)\n```\n\n### Record\n\n**Facts** — things you confirmed:\n```\nobserve(\"The API rate limits at 1000 req/min"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn72z63n9q59956xsvygf25e5d82xx7m\",\n  \"slug\": \"cortex-engine\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1785481992564\n}"},{"path":"skill-card.md","content":"## Description: <br>\nPersistent cognitive memory for AI agents: query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[idapixl](https://clawhub.ai/user/idapixl) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent builders use this skill to give agents persistent local memory for recalling prior decisions, tracking evolving beliefs, detecting contradictions, and continuing work across sessions. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill enables long-lived local memory that can retain project and personal context across sessions. <br>\nMitigation: Avoid storing secrets or sensitive business details unless local retention is acceptable for the deployment. <br>\nRisk: The skill depends on a globally installed external npm package and local services. <br>\nMitigation: Review the npm package and service behavior before installation, and use the documented scoped package @fozikio/cortex-engine. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/idapixl/skills/cortex-engine) <br>\n- [cortex-engine GitHub repository](https://github.com/Fozikio/cortex-engine) <br>\n- [@fozikio/cortex-engine npm package](https://www.npmjs.com/package/@fozikio/cortex-engine) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown with inline shell commands and tool-call examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Guides an agent through local MCP memory workflows for querying, recording, reviewing, and consolidating knowledge.] <br>\n\n## Skill Version(s): <br>\n1.0.3 (source: ClawHub release evidence) <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>"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Persistent memory for AI agents. Knowledge survives across sessions: recall past decisions, track evolving beliefs, detect contradictions via NLI, and build a knowledge graph over time. 60 tools over MCP, with FSRS spaced-repetition scheduling and spreading-activation retrieval. Runs locally on SQLite and Ollama, so no cloud account is needed. Skill: cortex-memory Owner: fozikio Summary: Persistent memory for AI agents. Knowledge survives across sessions: recall past decisions, track evolving beliefs, detect contradictions via NLI, and build a knowledge graph over time. 60 tools over MCP, with FSRS spaced-repetition scheduling and spreading-activation retrieval. Runs locally on SQLite and Ollama, so no cloud account is needed. Tags: agents:1.0.1, code-revi","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1318,"uniquenessScore":50,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T13:12:23.935Z","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":"2026-10-10T13:12:23.935Z","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":"2026-10-10T15:50:48.643Z","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"}]}}}