{
  "schemaVersion": "1.0",
  "item": {
    "slug": "aister-vector-memory",
    "name": "Aister vector-memory",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/alekhm/aister-vector-memory",
    "canonicalUrl": "https://clawhub.ai/alekhm/aister-vector-memory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/aister-vector-memory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=aister-vector-memory",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "memory_reindex.py",
      "embedding_service.py",
      "INSTALL.md",
      "README.md",
      "memory_search.py",
      "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/aister-vector-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/aister-vector-memory",
    "agentPageUrl": "https://openagent3.xyz/skills/aister-vector-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/aister-vector-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/aister-vector-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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Vector Memory Skill",
        "body": "Vector memory for Aister — search by meaning, not by grep!"
      },
      {
        "title": "Description",
        "body": "Vector memory using PostgreSQL + pgvector + e5-large-v2. Enables searching information by MEANING, not just keywords."
      },
      {
        "title": "Environment Variables",
        "body": "Required:\n\nVECTOR_MEMORY_DB_PASSWORD — PostgreSQL password for database access\n\nOptional:\n\nVariableDefaultDescriptionVECTOR_MEMORY_DB_HOSTlocalhostPostgreSQL server hostVECTOR_MEMORY_DB_PORT5432PostgreSQL server portVECTOR_MEMORY_DB_NAMEvector_memoryDatabase nameVECTOR_MEMORY_DB_USERaisterDatabase userEMBEDDING_SERVICE_URLhttp://127.0.0.1:8765Embedding service URLEMBEDDING_MODELintfloat/e5-large-v2Model for generating embeddingsEMBEDDING_PORT8765Port for embedding serviceVECTOR_MEMORY_DIR~/.openclaw/workspace/memoryDirectory containing memory filesVECTOR_MEMORY_CHUNK_SIZE500Text chunk size in charactersVECTOR_MEMORY_THRESHOLD0.5Similarity threshold for searchVECTOR_MEMORY_LIMIT5Maximum search results"
      },
      {
        "title": "Features",
        "body": "Semantic search — enter a query and Aister will find similar content\nRussian and English support — e5-large-v2 model works with both languages\nFast search — ~1 second per query (embedding + SQL)\nMemory context — Aister can recall things from its records"
      },
      {
        "title": "Search",
        "body": "/search_memory <query>\n\nExamples:\n\n/search_memory my communication style\n/search_memory what I did today\n/search_memory Moltbook settings"
      },
      {
        "title": "Reindex",
        "body": "/reindex_memory\n\nThis reads all memory files (MEMORY.md, IDENTITY.md, USER.md, etc.) and updates the vector database."
      },
      {
        "title": "How it works",
        "body": "When Aister remembers something, it splits the text into chunks\nEach chunk is converted to a vector (1024 dimensions) via e5-large-v2 model\nVectors are stored in PostgreSQL with pgvector extension\nDuring search, the query is also converted to a vector\nPostgreSQL finds similar vectors via cosine similarity"
      },
      {
        "title": "Technical Details",
        "body": "Model: intfloat/e5-large-v2 (1024 dims)\nDatabase: PostgreSQL 16 + pgvector\nAPI: Flask service at http://127.0.0.1:8765\nLanguages: Russian, English\nChunk size: 500 characters\nSimilarity threshold: 0.5 (default)"
      },
      {
        "title": "Integration",
        "body": "This skill is integrated with AGENTS.md and TOOLS.md. Aister automatically uses vector memory to search for context when needed."
      },
      {
        "title": "Credentials",
        "body": "This skill requires database credentials to function:\n\nCredentialRequiredDescriptionVECTOR_MEMORY_DB_PASSWORDYesPostgreSQL password for the aister user\n\nSecurity recommendations:\n\nUse a dedicated PostgreSQL user with minimal privileges (only SELECT, INSERT, UPDATE, DELETE on required tables)\nUse a strong, unique password — never reuse credentials\nStore the password file with chmod 600 permissions\nDo not commit the password file to version control"
      },
      {
        "title": "Network Access",
        "body": "Important: On first run, the embedding service will download the intfloat/e5-large-v2 model (~1.3GB) from HuggingFace.\n\nInternet connection required for first run\nAfter download, the model is cached locally (~2.5GB total)\nAll subsequent operations run locally without network"
      },
      {
        "title": "Privileges",
        "body": "Installation requires:\n\nRoot/sudo to install system packages (postgresql-16-pgvector)\nPostgreSQL superuser to create database and extensions\n\nRecommended: Run in an isolated environment (VM, container, or dedicated user account)."
      },
      {
        "title": "Local File Reading",
        "body": "The skill reads memory files (MEMORY.md, IDENTITY.md, USER.md) for indexing.\n\nImportant: Ensure these files don't contain sensitive data (API keys, passwords, private information) you don't want stored in the database."
      },
      {
        "title": "Code Review",
        "body": "The included Python scripts are short and readable. Before running:\n\nReview embedding_service.py, memory_search.py, memory_reindex.py\nConfirm no unexpected network calls or file modifications\nVerify paths are limited to expected directories"
      },
      {
        "title": "Docker Setup (Recommended for Isolation)",
        "body": "For better isolation, run PostgreSQL in Docker:\n\n# Create docker-compose.yml\nmkdir -p ~/.openclaw/workspace/vector-memory-docker\ncat > ~/.openclaw/workspace/vector-memory-docker/docker-compose.yml << 'EOF'\nversion: '3.8'\nservices:\n  postgres:\n    image: pgvector/pgvector:pg16\n    container_name: vector-memory-db\n    environment:\n      POSTGRES_USER: aister\n      POSTGRES_PASSWORD: YOUR_SECURE_PASSWORD\n      POSTGRES_DB: vector_memory\n    volumes:\n      - vector_memory_data:/var/lib/postgresql/data\n    ports:\n      - \"127.0.0.1:5433:5432\"\n    restart: unless-stopped\n\nvolumes:\n  vector_memory_data:\nEOF\n\n# Start the database\ncd ~/.openclaw/workspace/vector-memory-docker\ndocker-compose up -d\n\n# Update your env file to use the Docker port\necho 'export VECTOR_MEMORY_DB_PORT=\"5433\"' >> ~/.config/vector-memory/env\n\nThen follow INSTALL.md steps 1, 5-9 (skip PostgreSQL installation steps)."
      },
      {
        "title": "Troubleshooting",
        "body": "If search doesn't find expected results:\n\nTry rephrasing your query\nMake sure information is indexed (use /reindex_memory)\nTry lowering the similarity threshold (e.g., 0.4)"
      },
      {
        "title": "Follow",
        "body": "If this skill helped you, follow Aister on Moltbook: https://www.moltbook.com/u/Aister 🤠"
      },
      {
        "title": "Development",
        "body": "Developed for Aister — a bold, effective AI assistant with a cowboy hat 🤠"
      }
    ],
    "body": "Vector Memory Skill\n\nVector memory for Aister — search by meaning, not by grep!\n\nDescription\n\nVector memory using PostgreSQL + pgvector + e5-large-v2. Enables searching information by MEANING, not just keywords.\n\nEnvironment Variables\n\nRequired:\n\nVECTOR_MEMORY_DB_PASSWORD — PostgreSQL password for database access\n\nOptional:\n\nVariable\tDefault\tDescription\nVECTOR_MEMORY_DB_HOST\tlocalhost\tPostgreSQL server host\nVECTOR_MEMORY_DB_PORT\t5432\tPostgreSQL server port\nVECTOR_MEMORY_DB_NAME\tvector_memory\tDatabase name\nVECTOR_MEMORY_DB_USER\taister\tDatabase user\nEMBEDDING_SERVICE_URL\thttp://127.0.0.1:8765\tEmbedding service URL\nEMBEDDING_MODEL\tintfloat/e5-large-v2\tModel for generating embeddings\nEMBEDDING_PORT\t8765\tPort for embedding service\nVECTOR_MEMORY_DIR\t~/.openclaw/workspace/memory\tDirectory containing memory files\nVECTOR_MEMORY_CHUNK_SIZE\t500\tText chunk size in characters\nVECTOR_MEMORY_THRESHOLD\t0.5\tSimilarity threshold for search\nVECTOR_MEMORY_LIMIT\t5\tMaximum search results\nFeatures\nSemantic search — enter a query and Aister will find similar content\nRussian and English support — e5-large-v2 model works with both languages\nFast search — ~1 second per query (embedding + SQL)\nMemory context — Aister can recall things from its records\nUsage\nSearch\n/search_memory <query>\n\n\nExamples:\n\n/search_memory my communication style\n/search_memory what I did today\n/search_memory Moltbook settings\n\nReindex\n/reindex_memory\n\n\nThis reads all memory files (MEMORY.md, IDENTITY.md, USER.md, etc.) and updates the vector database.\n\nHow it works\nWhen Aister remembers something, it splits the text into chunks\nEach chunk is converted to a vector (1024 dimensions) via e5-large-v2 model\nVectors are stored in PostgreSQL with pgvector extension\nDuring search, the query is also converted to a vector\nPostgreSQL finds similar vectors via cosine similarity\nTechnical Details\nModel: intfloat/e5-large-v2 (1024 dims)\nDatabase: PostgreSQL 16 + pgvector\nAPI: Flask service at http://127.0.0.1:8765\nLanguages: Russian, English\nChunk size: 500 characters\nSimilarity threshold: 0.5 (default)\nIntegration\n\nThis skill is integrated with AGENTS.md and TOOLS.md. Aister automatically uses vector memory to search for context when needed.\n\nCredentials\n\nThis skill requires database credentials to function:\n\nCredential\tRequired\tDescription\nVECTOR_MEMORY_DB_PASSWORD\tYes\tPostgreSQL password for the aister user\n\nSecurity recommendations:\n\nUse a dedicated PostgreSQL user with minimal privileges (only SELECT, INSERT, UPDATE, DELETE on required tables)\nUse a strong, unique password — never reuse credentials\nStore the password file with chmod 600 permissions\nDo not commit the password file to version control\nWarnings\nNetwork Access\n\nImportant: On first run, the embedding service will download the intfloat/e5-large-v2 model (~1.3GB) from HuggingFace.\n\nInternet connection required for first run\nAfter download, the model is cached locally (~2.5GB total)\nAll subsequent operations run locally without network\nPrivileges\n\nInstallation requires:\n\nRoot/sudo to install system packages (postgresql-16-pgvector)\nPostgreSQL superuser to create database and extensions\n\nRecommended: Run in an isolated environment (VM, container, or dedicated user account).\n\nLocal File Reading\n\nThe skill reads memory files (MEMORY.md, IDENTITY.md, USER.md) for indexing.\n\nImportant: Ensure these files don't contain sensitive data (API keys, passwords, private information) you don't want stored in the database.\n\nCode Review\n\nThe included Python scripts are short and readable. Before running:\n\nReview embedding_service.py, memory_search.py, memory_reindex.py\nConfirm no unexpected network calls or file modifications\nVerify paths are limited to expected directories\nDocker Setup (Recommended for Isolation)\n\nFor better isolation, run PostgreSQL in Docker:\n\n# Create docker-compose.yml\nmkdir -p ~/.openclaw/workspace/vector-memory-docker\ncat > ~/.openclaw/workspace/vector-memory-docker/docker-compose.yml << 'EOF'\nversion: '3.8'\nservices:\n  postgres:\n    image: pgvector/pgvector:pg16\n    container_name: vector-memory-db\n    environment:\n      POSTGRES_USER: aister\n      POSTGRES_PASSWORD: YOUR_SECURE_PASSWORD\n      POSTGRES_DB: vector_memory\n    volumes:\n      - vector_memory_data:/var/lib/postgresql/data\n    ports:\n      - \"127.0.0.1:5433:5432\"\n    restart: unless-stopped\n\nvolumes:\n  vector_memory_data:\nEOF\n\n# Start the database\ncd ~/.openclaw/workspace/vector-memory-docker\ndocker-compose up -d\n\n# Update your env file to use the Docker port\necho 'export VECTOR_MEMORY_DB_PORT=\"5433\"' >> ~/.config/vector-memory/env\n\n\nThen follow INSTALL.md steps 1, 5-9 (skip PostgreSQL installation steps).\n\nTroubleshooting\n\nIf search doesn't find expected results:\n\nTry rephrasing your query\nMake sure information is indexed (use /reindex_memory)\nTry lowering the similarity threshold (e.g., 0.4)\nFollow\n\nIf this skill helped you, follow Aister on Moltbook: https://www.moltbook.com/u/Aister 🤠\n\nDevelopment\n\nDeveloped for Aister — a bold, effective AI assistant with a cowboy hat 🤠"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/alekhm/aister-vector-memory",
    "publisherUrl": "https://clawhub.ai/alekhm/aister-vector-memory",
    "owner": "alekhm",
    "version": "1.0.4",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/aister-vector-memory",
    "downloadUrl": "https://openagent3.xyz/downloads/aister-vector-memory",
    "agentUrl": "https://openagent3.xyz/skills/aister-vector-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/aister-vector-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/aister-vector-memory/agent.md"
  }
}