{ "schemaVersion": "1.0", "item": { "slug": "index1", "name": "index1", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/gladego/index1", "canonicalUrl": "https://clawhub.ai/gladego/index1", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/index1", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=index1", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "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/index1" }, "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/index1", "agentPageUrl": "https://openagent3.xyz/skills/index1/agent", "manifestUrl": "https://openagent3.xyz/skills/index1/agent.json", "briefUrl": "https://openagent3.xyz/skills/index1/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": "index1", "body": "AI memory system for coding agents with BM25 + vector hybrid search. Provides 6 MCP tools for intelligent code/doc search and cognitive fact recording." }, { "title": "What it does", "body": "Dual memory: corpus (code index) + cognition (episodic facts)\nHybrid search: BM25 full-text + vector semantic search with RRF fusion\nStructure-aware chunking: Markdown, Python, Rust, JavaScript, plain text\nMCP Server: 6 tools (recall, learn, read, status, reindex, config)\nCJK optimized: Chinese/Japanese/Korean query detection with dynamic weight tuning\nBuilt-in ONNX embedding: Vector search works out of the box, no Ollama required\nGraceful degradation: Works without any embedding service (BM25-only mode)" }, { "title": "Install", "body": "# Recommended\npipx install index1\n\n# Or via pip\npip install index1\n\n# Or via npm (auto-installs Python package)\nnpx index1@latest\n\nOne-click plugin setup:\n\nindex1 setup # Auto-configure hooks + MCP for Claude Code\n\nVerify:\n\nindex1 --version\nindex1 doctor # Check environment" }, { "title": "Setup MCP", "body": "Create .mcp.json in your project root:\n\n{\n \"mcpServers\": {\n \"index1\": {\n \"type\": \"stdio\",\n \"command\": \"index1\",\n \"args\": [\"serve\"]\n }\n }\n}\n\nIf index1 is not in PATH, use the full path from which index1." }, { "title": "Add Search Rules", "body": "Add to your project's .claude/CLAUDE.md:\n\n## Search Strategy\n\nThis project has index1 MCP Server configured (recall + 5 other tools). When searching code:\n\n1. Known identifiers (function/class/file names) -> Grep/Glob directly (4ms)\n2. Exploratory questions (\"how does XX work\") -> recall first, then Grep for details\n3. CJK query for English code -> must use recall (Grep can't cross languages)\n4. High-frequency keywords (50+ expected matches) -> prefer recall (saves 90%+ context)\n\nImpact:\n\nWithout rules: Grep \"search\" -> 881 lines -> 35,895 tokens\nWith rules: recall -> 5 summaries -> 460 tokens (97% savings)" }, { "title": "Index Your Project", "body": "index1 index ./src ./docs # Index source and docs\nindex1 status # Check index stats\nindex1 search \"your query\" # Test search" }, { "title": "Optional: Multilingual Enhancement", "body": "index1 v2 has built-in ONNX embedding (bge-small-en-v1.5). For better multilingual support:\n\ncurl -fsSL https://ollama.com/install.sh | sh\nollama pull nomic-embed-text # Standard, 270MB\n# or\nollama pull bge-m3 # Best for CJK, 1.2GB\n\nindex1 config embed_backend ollama\nindex1 doctor # Verify setup\n\nWithout Ollama, ONNX embedding provides vector search out of the box." }, { "title": "Web UI", "body": "index1 web # Start Web UI on port 6888\nindex1 web --port 8080 # Custom port" }, { "title": "MCP Tools Reference", "body": "ToolDescriptionrecallUnified search β€” code + cognitive facts, BM25 + vector hybridlearnRecord insights, decisions, lessons learned (auto-classify + dedup)readRead file content + index metadatastatusIndex and cognition statisticsreindexRebuild index for a path or collectionconfigView or modify configuration" }, { "title": "Troubleshooting", "body": "IssueFixTools not showingCheck .mcp.json format and index1 pathAI doesn't use recallAdd search rules to CLAUDE.mdcommand not foundUse full path from which index1Chinese search returns 0Install Ollama + bge-m3 modelNo vector searchBuilt-in ONNX should work; run index1 doctor" } ], "body": "index1\n\nAI memory system for coding agents with BM25 + vector hybrid search. Provides 6 MCP tools for intelligent code/doc search and cognitive fact recording.\n\nWhat it does\nDual memory: corpus (code index) + cognition (episodic facts)\nHybrid search: BM25 full-text + vector semantic search with RRF fusion\nStructure-aware chunking: Markdown, Python, Rust, JavaScript, plain text\nMCP Server: 6 tools (recall, learn, read, status, reindex, config)\nCJK optimized: Chinese/Japanese/Korean query detection with dynamic weight tuning\nBuilt-in ONNX embedding: Vector search works out of the box, no Ollama required\nGraceful degradation: Works without any embedding service (BM25-only mode)\nInstall\n# Recommended\npipx install index1\n\n# Or via pip\npip install index1\n\n# Or via npm (auto-installs Python package)\nnpx index1@latest\n\n\nOne-click plugin setup:\n\nindex1 setup # Auto-configure hooks + MCP for Claude Code\n\n\nVerify:\n\nindex1 --version\nindex1 doctor # Check environment\n\nSetup MCP\n\nCreate .mcp.json in your project root:\n\n{\n \"mcpServers\": {\n \"index1\": {\n \"type\": \"stdio\",\n \"command\": \"index1\",\n \"args\": [\"serve\"]\n }\n }\n}\n\n\nIf index1 is not in PATH, use the full path from which index1.\n\nAdd Search Rules\n\nAdd to your project's .claude/CLAUDE.md:\n\n## Search Strategy\n\nThis project has index1 MCP Server configured (recall + 5 other tools). When searching code:\n\n1. Known identifiers (function/class/file names) -> Grep/Glob directly (4ms)\n2. Exploratory questions (\"how does XX work\") -> recall first, then Grep for details\n3. CJK query for English code -> must use recall (Grep can't cross languages)\n4. High-frequency keywords (50+ expected matches) -> prefer recall (saves 90%+ context)\n\n\nImpact:\n\nWithout rules: Grep \"search\" -> 881 lines -> 35,895 tokens\nWith rules: recall -> 5 summaries -> 460 tokens (97% savings)\n\nIndex Your Project\nindex1 index ./src ./docs # Index source and docs\nindex1 status # Check index stats\nindex1 search \"your query\" # Test search\n\nOptional: Multilingual Enhancement\n\nindex1 v2 has built-in ONNX embedding (bge-small-en-v1.5). For better multilingual support:\n\ncurl -fsSL https://ollama.com/install.sh | sh\nollama pull nomic-embed-text # Standard, 270MB\n# or\nollama pull bge-m3 # Best for CJK, 1.2GB\n\nindex1 config embed_backend ollama\nindex1 doctor # Verify setup\n\n\nWithout Ollama, ONNX embedding provides vector search out of the box.\n\nWeb UI\nindex1 web # Start Web UI on port 6888\nindex1 web --port 8080 # Custom port\n\nMCP Tools Reference\nTool\tDescription\nrecall\tUnified search β€” code + cognitive facts, BM25 + vector hybrid\nlearn\tRecord insights, decisions, lessons learned (auto-classify + dedup)\nread\tRead file content + index metadata\nstatus\tIndex and cognition statistics\nreindex\tRebuild index for a path or collection\nconfig\tView or modify configuration\nTroubleshooting\nIssue\tFix\nTools not showing\tCheck .mcp.json format and index1 path\nAI doesn't use recall\tAdd search rules to CLAUDE.md\ncommand not found\tUse full path from which index1\nChinese search returns 0\tInstall Ollama + bge-m3 model\nNo vector search\tBuilt-in ONNX should work; run index1 doctor" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/gladego/index1", "publisherUrl": "https://clawhub.ai/gladego/index1", "owner": "gladego", "version": "2.0.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/index1", "downloadUrl": "https://openagent3.xyz/downloads/index1", "agentUrl": "https://openagent3.xyz/skills/index1/agent", "manifestUrl": "https://openagent3.xyz/skills/index1/agent.json", "briefUrl": "https://openagent3.xyz/skills/index1/agent.md" } }