{
  "schemaVersion": "1.0",
  "item": {
    "slug": "neural-memory",
    "name": "Neural Memory",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/nhadaututtheky/neural-memory",
    "canonicalUrl": "https://clawhub.ai/nhadaututtheky/neural-memory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/neural-memory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=neural-memory",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "hooks/hooks.json",
      "marketplace.json",
      "plugin.json",
      "SKILL.md",
      "skills/memory-audit/SKILL.md",
      "skills/memory-evolution/SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/neural-memory"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/neural-memory",
    "agentPageUrl": "https://openagent3.xyz/skills/neural-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/neural-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/neural-memory/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Neural Memory",
        "body": "Reflex-based memory system for AI agents — stores experiences as interconnected neurons and recalls them through spreading activation, mimicking how the human brain works."
      },
      {
        "title": "What It Does",
        "body": "Neural Memory gives AI agents persistent, associative memory across sessions. Instead of keyword search, it uses spreading activation through a neural graph — memories that fire together, wire together."
      },
      {
        "title": "Key Features",
        "body": "45 MCP tools for persistent memory + cognitive reasoning\nSpreading activation recall — not keyword search, memories activate related memories\nCognitive reasoning — hypotheses, evidence, predictions, schema evolution\nKnowledge base training from PDF, DOCX, PPTX, HTML, JSON, XLSX, CSV\nMulti-device sync with neural-aware conflict resolution\n4 embedding providers — Sentence Transformers, Gemini, Ollama, OpenAI\nRetrieval pipeline — RRF score fusion, graph expansion, Personalized PageRank\nSession intelligence — topic EMA tracking, LRU eviction, auto-expiry\nReact dashboard — 7 pages: health, evolution, graph, timeline, settings\nVS Code extension — status bar, graph explorer, CodeLens, memory tree\nFernet encryption for sensitive content\nBrain versioning — snapshots, rollback, export/import\nTelegram backup — send brain .db to chat/group/channel"
      },
      {
        "title": "Installation",
        "body": "pip install neural-memory\n\nOr with embeddings:\n\npip install neural-memory[embeddings]"
      },
      {
        "title": "MCP Configuration",
        "body": "{\r\n  \"mcpServers\": {\r\n    \"neural-memory\": {\r\n      \"command\": \"uvx\",\r\n      \"args\": [\"--from\", \"neural-memory\", \"nmem-mcp\"]\r\n    }\r\n  }\r\n}"
      },
      {
        "title": "Usage",
        "body": "Neural Memory works automatically once configured.\n\nRECALL — before responding to tasks that reference past work:\n\nNew session → nmem_recall(\"current project context\")\nPast decision/event → nmem_recall(\"<project> <topic>\")\nSkip for purely new, self-contained questions\n\nSAVE — after completing each task, if you made a decision, fixed a bug, learned a preference, or discovered a pattern:\n\nnmem_remember(content=\"Chose X over Y because Z\", type=\"decision\", priority=7, tags=[\"project\", \"topic\"])\nUse causal language (not flat facts). Max 1-3 sentences.\nDo NOT save ephemeral file reads, things in git history, or duplicates.\n\nFLUSH — at session end:\n\nnmem_auto(action=\"process\", text=\"brief summary\")"
      },
      {
        "title": "Memory Types",
        "body": "TypeUse ForfactStable knowledgedecision\"Chose X over Y because Z\"insightPatterns discoverederrorBugs and root causesworkflowProcess stepspreferenceUser preferencesinstructionRules to follow"
      },
      {
        "title": "Links",
        "body": "GitHub\nDocumentation\nVS Code Extension"
      }
    ],
    "body": "Neural Memory\n\nReflex-based memory system for AI agents — stores experiences as interconnected neurons and recalls them through spreading activation, mimicking how the human brain works.\n\nWhat It Does\n\nNeural Memory gives AI agents persistent, associative memory across sessions. Instead of keyword search, it uses spreading activation through a neural graph — memories that fire together, wire together.\n\nKey Features\n45 MCP tools for persistent memory + cognitive reasoning\nSpreading activation recall — not keyword search, memories activate related memories\nCognitive reasoning — hypotheses, evidence, predictions, schema evolution\nKnowledge base training from PDF, DOCX, PPTX, HTML, JSON, XLSX, CSV\nMulti-device sync with neural-aware conflict resolution\n4 embedding providers — Sentence Transformers, Gemini, Ollama, OpenAI\nRetrieval pipeline — RRF score fusion, graph expansion, Personalized PageRank\nSession intelligence — topic EMA tracking, LRU eviction, auto-expiry\nReact dashboard — 7 pages: health, evolution, graph, timeline, settings\nVS Code extension — status bar, graph explorer, CodeLens, memory tree\nFernet encryption for sensitive content\nBrain versioning — snapshots, rollback, export/import\nTelegram backup — send brain .db to chat/group/channel\nInstallation\npip install neural-memory\n\n\nOr with embeddings:\n\npip install neural-memory[embeddings]\n\nMCP Configuration\n{\r\n  \"mcpServers\": {\r\n    \"neural-memory\": {\r\n      \"command\": \"uvx\",\r\n      \"args\": [\"--from\", \"neural-memory\", \"nmem-mcp\"]\r\n    }\r\n  }\r\n}\n\nUsage\n\nNeural Memory works automatically once configured.\n\nRECALL — before responding to tasks that reference past work:\n\nNew session → nmem_recall(\"current project context\")\nPast decision/event → nmem_recall(\"<project> <topic>\")\nSkip for purely new, self-contained questions\n\nSAVE — after completing each task, if you made a decision, fixed a bug, learned a preference, or discovered a pattern:\n\nnmem_remember(content=\"Chose X over Y because Z\", type=\"decision\", priority=7, tags=[\"project\", \"topic\"])\nUse causal language (not flat facts). Max 1-3 sentences.\nDo NOT save ephemeral file reads, things in git history, or duplicates.\n\nFLUSH — at session end:\n\nnmem_auto(action=\"process\", text=\"brief summary\")\nMemory Types\nType\tUse For\nfact\tStable knowledge\ndecision\t\"Chose X over Y because Z\"\ninsight\tPatterns discovered\nerror\tBugs and root causes\nworkflow\tProcess steps\npreference\tUser preferences\ninstruction\tRules to follow\nLinks\nGitHub\nDocumentation\nVS Code Extension"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/nhadaututtheky/neural-memory",
    "publisherUrl": "https://clawhub.ai/nhadaututtheky/neural-memory",
    "owner": "nhadaututtheky",
    "version": "4.11.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/neural-memory",
    "downloadUrl": "https://openagent3.xyz/downloads/neural-memory",
    "agentUrl": "https://openagent3.xyz/skills/neural-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/neural-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/neural-memory/agent.md"
  }
}