{ "schemaVersion": "1.0", "item": { "slug": "muninn", "name": "muninn", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/endgegnerbert-tech/muninn", "canonicalUrl": "https://clawhub.ai/endgegnerbert-tech/muninn", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/muninn", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=muninn", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "CLAUDE.md", "SKILL.md", "dist/brain_lock.js", "dist/constants.js", "dist/cxp.js", "dist/index.js" ], "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", "slug": "muninn", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-05T01:39:45.333Z", "expiresAt": "2026-05-12T01:39:45.333Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=muninn", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=muninn", "contentDisposition": "attachment; filename=\"muninn-2.3.7.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "muninn" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/muninn" }, "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/muninn", "agentPageUrl": "https://openagent3.xyz/skills/muninn/agent", "manifestUrl": "https://openagent3.xyz/skills/muninn/agent.json", "briefUrl": "https://openagent3.xyz/skills/muninn/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": "Muninn - The Universal Memory Layer", "body": "Muninn is an advanced per-project memory system designed for AI agents. It uses the Context Exchange Protocol (CXP) to provide high-performance, token-efficient context management." }, { "title": "πŸ›‘οΈ Security & Privacy (Local-First)", "body": "Muninn is designed with a Privacy-First philosophy.\n\nLocal Storage: All project indexes and memories are stored exclusively on the host machine within the .muninn/ folder (per project) or ~/.muninn/ (for global settings).\nNo Data Exfiltration: Muninn does not transmit any code, context, or memories to third-party servers or remote APIs. All processing (semantic search, indexing, and context injection) happens locally using the high-performance Rust-based CXP engine.\nTransparent Control: Memories are stored as standard Markdown files. You can inspect, edit, or delete them at any time." }, { "title": "βš™οΈ Integration", "body": "Muninn operates as an MCP (Model Context Protocol) server." }, { "title": "πŸš€ The Muninn Protocol (ENFORCED)", "body": "As an agent, you MUST follow the \"Brain-First\" workflow to remain efficient and accurate. The MCP server ensures project safety by validating context before allowing sensitive tool operations.\n\nOrient Yourself (brain_check): Call this at the start of every session or when switching projects. It loads the local project index and identifies key files and patterns.\nSearch Before You Code (search_context): Never assume you know the codebase. Use local semantic search to find existing patterns or prior decisions.\nLearn as You Go (add_memory): Every significant fix, architectural decision, or user preference should be saved locally as a memory." }, { "title": "πŸ›  Tool Reference (MCP)", "body": "init_project: Initialize a local Muninn Brain in a project directory.\nbrain_check: MANDATORY orientation step. Loads local context and patterns.\nadd_memory: Persist facts and decisions to the local .muninn/memories folder.\nsearch_context: Query the local project index semantically.\nreindex_context: Rebuild the local semantic index.\nhealth_check: Verify the status of the local Muninn system." }, { "title": "🦞 Pro-Tip for Agents", "body": "Muninn surgically retrieves only what's needed. Instead of reading large files, use search_context to find the exact lines that matter. This significantly reduces context window overhead and token costs while keeping your work strictly local and secure." } ], "body": "Muninn - The Universal Memory Layer\n\nMuninn is an advanced per-project memory system designed for AI agents. It uses the Context Exchange Protocol (CXP) to provide high-performance, token-efficient context management.\n\nπŸ›‘οΈ Security & Privacy (Local-First)\n\nMuninn is designed with a Privacy-First philosophy.\n\nLocal Storage: All project indexes and memories are stored exclusively on the host machine within the .muninn/ folder (per project) or ~/.muninn/ (for global settings).\nNo Data Exfiltration: Muninn does not transmit any code, context, or memories to third-party servers or remote APIs. All processing (semantic search, indexing, and context injection) happens locally using the high-performance Rust-based CXP engine.\nTransparent Control: Memories are stored as standard Markdown files. You can inspect, edit, or delete them at any time.\nβš™οΈ Integration\n\nMuninn operates as an MCP (Model Context Protocol) server.\n\nπŸš€ The Muninn Protocol (ENFORCED)\n\nAs an agent, you MUST follow the \"Brain-First\" workflow to remain efficient and accurate. The MCP server ensures project safety by validating context before allowing sensitive tool operations.\n\nOrient Yourself (brain_check): Call this at the start of every session or when switching projects. It loads the local project index and identifies key files and patterns.\nSearch Before You Code (search_context): Never assume you know the codebase. Use local semantic search to find existing patterns or prior decisions.\nLearn as You Go (add_memory): Every significant fix, architectural decision, or user preference should be saved locally as a memory.\nπŸ›  Tool Reference (MCP)\ninit_project: Initialize a local Muninn Brain in a project directory.\nbrain_check: MANDATORY orientation step. Loads local context and patterns.\nadd_memory: Persist facts and decisions to the local .muninn/memories folder.\nsearch_context: Query the local project index semantically.\nreindex_context: Rebuild the local semantic index.\nhealth_check: Verify the status of the local Muninn system.\n🦞 Pro-Tip for Agents\n\nMuninn surgically retrieves only what's needed. Instead of reading large files, use search_context to find the exact lines that matter. This significantly reduces context window overhead and token costs while keeping your work strictly local and secure." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/endgegnerbert-tech/muninn", "publisherUrl": "https://clawhub.ai/endgegnerbert-tech/muninn", "owner": "endgegnerbert-tech", "version": "2.3.7", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/muninn", "downloadUrl": "https://openagent3.xyz/downloads/muninn", "agentUrl": "https://openagent3.xyz/skills/muninn/agent", "manifestUrl": "https://openagent3.xyz/skills/muninn/agent.json", "briefUrl": "https://openagent3.xyz/skills/muninn/agent.md" } }