{"id":"d0eef98b-b2f8-4e8d-a511-c8eff84daf9f","entityType":"agent","slug":"clawhub-nhadaututtheky-neural-memory","name":"Neural Memory","canonicalUrl":"https://www.xpersona.co/agent/clawhub-nhadaututtheky-neural-memory","canonicalPath":"/agent/clawhub-nhadaututtheky-neural-memory","generatedAt":"2026-10-09T16:39:33.006Z","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":"Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or context across sessions (2) User asks \"do you remember...\" or references past conversations (3) Starting a new task — inject relevant context from memory (4) After making decisions or encountering errors — store for future reference (5) User asks \"why did X happen?\" — trace causal chains through memory Zero LLM dependency. Neural graph with Hebbian learning, memory decay, contradiction detection, and temporal reasoning. Skill: Neural Memory Owner: nhadaututtheky Summary: Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or context across sessions (2) User asks \"do you remember...\" or references past conversations (3) Starting a new task — inject relevant context from memory (4) After making decisions or encountering errors — store","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 3K downloads reported by the source. Last updated 4/15/2026.","installCommand":"clawhub skill install kn70ngajsmd3pjtems7xrs3kv580v8fj:neural-memory","sourceUrl":"https://clawhub.ai/nhadaututtheky/neural-memory","homepage":"https://clawhub.ai/nhadaututtheky/neural-memory","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/nhadaututtheky/neural-memory","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":63,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or con"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No protocol or capability metadata is available."},"protocols":[],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":0,"capabilityMatrix":{"rows":[],"flattenedTokens":""}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"stars":null,"forks":null,"downloads":3012,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"3K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-02-28T18:04:01.309Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-02-28T18:04:01.309Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-01T18:04:01.309Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-02-09T10:16:58.592Z","changelog":"Initial release: associative memory with spreading activation for OpenClaw","fileCount":2,"zipByteSize":3493}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install kn70ngajsmd3pjtems7xrs3kv580v8fj:neural-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-nhadaututtheky-neural-memory/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nhadaututtheky-neural-memory/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nhadaututtheky-neural-memory/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-nhadaututtheky-neural-memory/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-nhadaututtheky-neural-memory/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-nhadaututtheky-neural-memory/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":[]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T16:39:33.006Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nhadaututtheky-neural-memory/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nhadaututtheky-neural-memory/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nhadaututtheky-neural-memory/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nhadaututtheky-neural-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":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"Skill: Neural Memory\n\nOwner: nhadaututtheky\n\nSummary: Associative memory with spreading activation for persistent, intelligent recall.\nUse PROACTIVELY when:\n(1) You need to remember facts, decisions, errors, or context across sessions\n(2) User asks \"do you remember...\" or references past conversations\n(3) Starting a new task — inject relevant context from memory\n(4) After making decisions or encountering errors — store for future reference\n(5) User asks \"why did X happen?\" — trace causal chains through memory\nZero LLM dependency. Neural graph with Hebbian learning, memory decay, contradiction detection, and temporal reasoning.\n\nTags: latest:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-02-09T10:16:58.592Z | user\n\nInitial release: associative memory with spreading activation for OpenClaw\n\nArchive index:\n\nArchive v1.0.0: 2 files, 3493 bytes\n\nFiles: SKILL.md (7002b), _meta.json (132b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: neural-memory\ndescription: |\n  Associative memory with spreading activation for persistent, intelligent recall.\n  Use PROACTIVELY when:\n  (1) You need to remember facts, decisions, errors, or context across sessions\n  (2) User asks \"do you remember...\" or references past conversations\n  (3) Starting a new task — inject relevant context from memory\n  (4) After making decisions or encountering errors — store for future reference\n  (5) User asks \"why did X happen?\" — trace causal chains through memory\n  Zero LLM dependency. Neural graph with Hebbian learning, memory decay, contradiction detection, and temporal reasoning.\nhomepage: https://github.com/nhadaututtheky/neural-memory\nmetadata: {\"openclaw\":{\"emoji\":\"brain\",\"primaryEnv\":\"NEURALMEMORY_BRAIN\",\"requires\":{\"bins\":[\"python3\"],\"env\":[\"NEURALMEMORY_BRAIN\"]},\"os\":[\"darwin\",\"linux\",\"win32\"],\"install\":[{\"id\":\"pip\",\"kind\":\"node\",\"package\":\"neural-memory\",\"bins\":[\"nmem\"],\"label\":\"pip install neural-memory\"}]}}\n---\n\n# NeuralMemory — Associative Memory for AI Agents\n\nA biologically-inspired memory system that uses spreading activation instead of keyword/vector search. Memories form a neural graph where neurons connect via 20 typed synapses. Frequently co-accessed memories strengthen their connections (Hebbian learning). Stale memories decay naturally. Contradictions are auto-detected.\n\n**Why not just vector search?** Vector search finds documents similar to your query. NeuralMemory finds *conceptually related* memories through graph traversal — even when there's no keyword or embedding overlap. \"What decision did we make about auth?\" activates time + entity + concept neurons simultaneously and finds the intersection.\n\n## Setup\n\n### 1. Install NeuralMemory\n\n```bash\npip install neural-memory\nnmem init\n```\n\nThis creates `~/.neuralmemory/` with a default brain and configures MCP automatically.\n\n### 2. Configure MCP for OpenClaw\n\nAdd to your OpenClaw MCP configuration (`~/.openclaw/mcp.json` or project `openclaw.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"neural-memory\": {\n      \"command\": \"python3\",\n      \"args\": [\"-m\", \"neural_memory.mcp\"],\n      \"env\": {\n        \"NEURALMEMORY_BRAIN\": \"default\"\n      }\n    }\n  }\n}\n```\n\n### 3. Verify\n\n```bash\nnmem stats\n```\n\nYou should see brain statistics (neurons, synapses, fibers).\n\n## Tools Reference\n\n### Core Memory Tools\n\n| Tool | Purpose | When to Use |\n|------|---------|-------------|\n| `nmem_remember` | Store a memory | After decisions, errors, facts, insights, user preferences |\n| `nmem_recall` | Query memories | Before tasks, when user references past context, \"do you remember...\" |\n| `nmem_context` | Get recent memories | At session start, inject fresh context |\n| `nmem_todo` | Quick TODO with 30-day expiry | Task tracking |\n\n### Intelligence Tools\n\n| Tool | Purpose | When to Use |\n|------|---------|-------------|\n| `nmem_auto` | Auto-extract memories from text | After important conversations — captures decisions, errors, TODOs automatically |\n| `nmem_recall` (depth=3) | Deep associative recall | Complex questions requiring cross-domain connections |\n| `nmem_habits` | Workflow pattern suggestions | When user repeats similar action sequences |\n\n### Management Tools\n\n| Tool | Purpose | When to Use |\n|------|---------|-------------|\n| `nmem_health` | Brain health diagnostics | Periodic checkup, before sharing brain |\n| `nmem_stats` | Brain statistics | Quick overview of memory counts |\n| `nmem_version` | Brain snapshots and rollback | Before risky operations, version checkpoints |\n| `nmem_transplant` | Transfer memories between brains | Cross-project knowledge sharing |\n\n## Workflow\n\n### At Session Start\n1. Call `nmem_context` to inject recent memories into your awareness\n2. If user mentions a specific topic, call `nmem_recall` with that topic\n\n### During Conversation\n3. When a decision is made: `nmem_remember` with type=\"decision\"\n4. When an error occurs: `nmem_remember` with type=\"error\"\n5. When user states a preference: `nmem_remember` with type=\"preference\"\n6. When asked about past events: `nmem_recall` with appropriate depth\n\n### At Session End\n7. Call `nmem_auto` with action=\"process\" on important conversation segments\n8. This auto-extracts facts, decisions, errors, and TODOs\n\n## Examples\n\n### Remember a decision\n```\nnmem_remember(\n  content=\"Use PostgreSQL for production, SQLite for development\",\n  type=\"decision\",\n  tags=[\"database\", \"infrastructure\"],\n  priority=8\n)\n```\n\n### Recall with spreading activation\n```\nnmem_recall(\n  query=\"database configuration for production\",\n  depth=1,\n  max_tokens=500\n)\n```\nReturns memories found via graph traversal, not keyword matching. Related memories (e.g., \"deploy uses Docker with pg_dump backups\") surface even without shared keywords.\n\n### Trace causal chains\n```\nnmem_recall(\n  query=\"why did the deployment fail last week?\",\n  depth=2\n)\n```\nFollows CAUSED_BY and LEADS_TO synapses to trace cause-and-effect chains.\n\n### Auto-capture from conversation\n```\nnmem_auto(\n  action=\"process\",\n  text=\"We decided to switch from REST to GraphQL because the frontend needs flexible queries. The migration will take 2 sprints. TODO: update API docs.\"\n)\n```\nAutomatically extracts: 1 decision, 1 fact, 1 TODO.\n\n## Key Features\n\n- **Zero LLM dependency** — Pure algorithmic: regex, graph traversal, Hebbian learning\n- **Spreading activation** — Associative recall through neural graph, not keyword/vector search\n- **20 synapse types** — Temporal (BEFORE/AFTER), causal (CAUSED_BY/LEADS_TO), semantic (IS_A/HAS_PROPERTY), emotional (FELT/EVOKES), conflict (CONTRADICTS)\n- **Memory lifecycle** — Short-term → Working → Episodic → Semantic with Ebbinghaus decay\n- **Contradiction detection** — Auto-detects conflicting memories, deprioritizes outdated ones\n- **Hebbian learning** — \"Neurons that fire together wire together\" — memory improves with use\n- **Temporal reasoning** — Causal chain traversal, event sequences, temporal range queries\n- **Brain versioning** — Snapshot, rollback, diff brain state\n- **Brain transplant** — Transfer filtered knowledge between brains\n- **Vietnamese + English** — Full bilingual support for extraction and sentiment\n\n## Depth Levels\n\n| Depth | Name | Speed | Use Case |\n|-------|------|-------|----------|\n| 0 | Instant | <10ms | Quick facts, recent context |\n| 1 | Context | ~50ms | Standard recall (default) |\n| 2 | Habit | ~200ms | Pattern matching, workflow suggestions |\n| 3 | Deep | ~500ms | Cross-domain associations, causal chains |\n\n## Notes\n\n- Memories are stored locally in SQLite at `~/.neuralmemory/brains/<brain>.db`\n- No data is sent to external services (unless optional embedding provider is configured)\n- Brain isolation: each brain is independent, no cross-contamination\n- `nmem_remember` returns fiber_id for reference tracking\n- Priority scale: 0 (trivial) to 10 (critical), default 5\n- Memory types: fact, decision, preference, todo, insight, context, instruction, error, workflow, reference\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn70ngajsmd3pjtems7xrs3kv580v8fj\",\n  \"slug\": \"neural-memory\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1770632218592\n}","readmeExcerpt":"Skill: Neural Memory Owner: nhadaututtheky Summary: Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or context across sessions (2) User asks \"do you remember...\" or references past conversations (3) Starting a new task — inject relevant context from memory (4) After making decisions or encountering errors — store","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"pip install neural-memory\nnmem init"},{"language":"json","snippet":"{\n  \"mcpServers\": {\n    \"neural-memory\": {\n      \"command\": \"python3\",\n      \"args\": [\"-m\", \"neural_memory.mcp\"],\n      \"env\": {\n        \"NEURALMEMORY_BRAIN\": \"default\"\n      }\n    }\n  }\n}"},{"language":"bash","snippet":"nmem stats"},{"language":"text","snippet":"nmem_remember(\n  content=\"Use PostgreSQL for production, SQLite for development\",\n  type=\"decision\",\n  tags=[\"database\", \"infrastructure\"],\n  priority=8\n)"},{"language":"text","snippet":"nmem_recall(\n  query=\"database configuration for production\",\n  depth=1,\n  max_tokens=500\n)"},{"language":"text","snippet":"nmem_recall(\n  query=\"why did the deployment fail last week?\",\n  depth=2\n)"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: neural-memory\ndescription: |\n  Associative memory with spreading activation for persistent, intelligent recall.\n  Use PROACTIVELY when:\n  (1) You need to remember facts, decisions, errors, or context across sessions\n  (2) User asks \"do you remember...\" or references past conversations\n  (3) Starting a new task — inject relevant context from memory\n  (4) After making decisions or encountering errors — store for future reference\n  (5) User asks \"why did X happen?\" — trace causal chains through memory\n  Zero LLM dependency. Neural graph with Hebbian learning, memory decay, contradiction detection, and temporal reasoning.\nhomepage: https://github.com/nhadaututtheky/neural-memory\nmetadata: {\"openclaw\":{\"emoji\":\"brain\",\"primaryEnv\":\"NEURALMEMORY_BRAIN\",\"requires\":{\"bins\":[\"python3\"],\"env\":[\"NEURALMEMORY_BRAIN\"]},\"os\":[\"darwin\",\"linux\",\"win32\"],\"install\":[{\"id\":\"pip\",\"kind\":\"node\",\"package\":\"neural-memory\",\"bins\":[\"nmem\"],\"label\":\"pip install neural-memory\"}]}}\n---\n\n# NeuralMemory — Associative Memory for AI Agents\n\nA biologically-inspired memory system that uses spreading activation instead of keyword/vector search. Memories form a neural graph where neurons connect via 20 typed synapses. Frequently co-accessed memories strengthen their connections (Hebbian learning). Stale memories decay naturally. Contradictions are auto-detected.\n\n**Why not just vector search?** Vector search finds documents similar to your query. NeuralMemory finds *conceptually related* memories through graph traversal — even when there's no keyword or embedding overlap. \"What decision did we make about auth?\" activates time + entity + concept neurons simultaneously and finds the intersection.\n\n## Setup\n\n### 1. Install NeuralMemory\n\n```bash\npip install neural-memory\nnmem init\n```\n\nThis creates `~/.neuralmemory/` with a default brain and configures MCP automatically.\n\n### 2. Configure MCP for OpenClaw\n\nAdd to your OpenClaw MCP configuration (`~/.openclaw/mcp.json` or project `openclaw.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"neural-memory\": {\n      \"command\": \"python3\",\n      \"args\": [\"-m\", \"neural_memory.mcp\"],\n      \"env\": {\n        \"NEURALMEMORY_BRAIN\": \"default\"\n      }\n    }\n  }\n}\n```\n\n### 3. Verify\n\n```bash\nnmem stats\n```\n\nYou should see brain statistics (neurons, synapses, fibers).\n\n## Tools Reference\n\n### Core Memory Tools\n\n| Tool | Purpose | When to Use |\n|------|---------|-------------|\n| `nmem_remember` | Store a memory | After decisions, errors, facts, insights, user preferences |\n| `nmem_recall` | Query memories | Before tasks, when user references past context, \"do you remember...\" |\n| `nmem_context` | Get recent memories | At session start, inject fresh context |\n| `nmem_todo` | Quick TODO with 30-day expiry | Task tracking |\n\n### Intelligence Tools\n\n| Tool | Purpose | When to Use |\n|------|---------|-------------|\n| `nmem_auto` | Auto-extract memories from text | After important conversations — captures decisions, errors, TODOs automatically |\n| `nmem_rec"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn70ngajsmd3pjtems7xrs3kv580v8fj\",\n  \"slug\": \"neural-memory\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1770632218592\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or context across sessions (2) User asks \"do you remember...\" or references past conversations (3) Starting a new task — inject relevant context from memory (4) After making decisions or encountering errors — store for future reference (5) User asks \"why did X happen?\" — trace causal chains through memory Zero LLM dependency. Neural graph with Hebbian learning, memory decay, contradiction detection, and temporal reasoning. Skill: Neural Memory Owner: nhadaututtheky Summary: Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or context across sessions (2) User asks \"do you remember...\" or references past conversations (3) Starting a new task — inject relevant context from memory (4) After making decisions or encountering errors — store","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":785,"uniquenessScore":53,"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":"agent-directory","verified":false,"confidence":"low","updatedAt":"2026-10-09T16:39:33.006Z","emptyReason":"No close protocol neighbors were found."},"items":[],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[]}}}