[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76X50FGZT0K2104MEXMJY50":3,"skill-same:01M76X50FGZT0K2104MEXMJY50":46},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M76X50FGZT0K2104MEXMJY50","muninn-memory",null,"javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fphillipneho\u002Fmuninn-memory\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: muninn-memory\nversion: \"1.0.5\"\ndescription: Memory system for AI agents. Store, recall, and manage memories with semantic search, entity extraction, and salience scoring. Works locally with SQLite and Ollama. Free tier: full features, no restrictions.\ninstall: \"clawhub install muninn-memory\"\ntype: skill\nrepository: https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fmuninn-memory\nauthor: KakāpōHiko (KH)\n---\n\n# Muninn Memory\n\nA local-first memory system for AI agents. Store episodic, semantic, and procedural memories with intelligent retrieval.\n\n## Installation\n\n```bash\nclawhub install muninn-memory\n```\n\nOr install from source:\n```bash\ncd ~\u002F.openclaw\u002Fworkspace\u002Fskills\ngit clone https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fmuninn-memory.git\ncd muninn-memory\nnpm install && npm run build\n```\n\n## Requirements\n\n- **Node.js** 18+\n- **Ollama** running locally (for embeddings)\n- **SQLite** (included)\n\n## Quick Start\n\n```typescript\nimport { MemoryStore } from 'muninn-memory';\n\n\u002F\u002F Initialize (creates SQLite DB)\nconst memory = new MemoryStore('.\u002Fmemories.db');\n\n\u002F\u002F Store a memory\nconst mem = await memory.remember(\n  'Phillip lives in Brisbane, Australia',\n  'semantic',\n  { entities: ['Phillip', 'Brisbane', 'Australia'], salience: 0.8 }\n);\nconsole.log('Stored:', mem.id);\n\n\u002F\u002F Recall memories\nconst results = await memory.recall('Where does Phillip live?');\nconsole.log(results[0].content);\n\u002F\u002F \"Phillip lives in Brisbane, Australia\"\n\n\u002F\u002F Get stats\nconsole.log(memory.getStats());\n\u002F\u002F { total: 1, byType: { episodic: 0, semantic: 1, procedural: 0 }, entities: 3, edges: 0, procedures: 0 }\n\nmemory.close();\n```\n\n## Memory Types\n\n| Type | Use Case |\n|------|----------|\n| `episodic` | Events, conversations, experiences |\n| `semantic` | Facts, knowledge, relationships |\n| `procedural` | Skills, workflows, step-by-step processes |\n\n## API\n\n### `remember(content, type, options?)`\n\nStore a new memory.\n\n```typescript\nawait memory.remember(\n  'Meeting with Sarah about Q3 roadmap',\n  'episodic',\n  { \n    entities: ['Sarah', 'Q3 roadmap'],\n    salience: 0.7,\n    title: 'Q3 Planning Meeting'\n  }\n);\n```\n\n**Options:**\n- `title?: string` - Short title\n- `summary?: string` - Brief summary\n- `entities?: string[]` - Extracted entities\n- `topics?: string[]` - Topics\u002Ftags\n- `salience?: number` - Importance 0-1 (default: 0.5)\n\n**Returns:** `Memory` object with id, content, type, entities, etc.\n\n### `recall(query, options?)`\n\nSearch memories using hybrid search.\n\n```typescript\nconst results = await memory.recall('Sarah Q3', {\n  limit: 5,\n  types: ['episodic', 'semantic'],\n  entities: ['Sarah'],\n  topics: ['planning']\n});\n```\n\n**Options:**\n- `types?: MemoryType[]` - Filter by type\n- `entities?: string[]` - Filter by entity\n- `topics?: string[]` - Filter by topic\n- `limit?: number` - Max results (default: 10)\n\n**Returns:** Array of `Memory` objects sorted by relevance.\n\n### `forget(id, hard?)`\n\nDelete a memory.\n\n```typescript\n\u002F\u002F Soft delete (can be recovered)\nmemory.forget('m_abc123');\n\n\u002F\u002F Hard delete (permanent)\nmemory.forget('m_abc123', true);\n```\n\n### `getEntities()`\n\nList all extracted entities.\n\n```typescript\nconst entities = memory.getEntities();\n\u002F\u002F [{ name: 'Phillip', memory_count: 5, last_seen: '2026-02-24...' }, ...]\n```\n\n### `getStats()`\n\nGet vault statistics.\n\n```typescript\nconst stats = memory.getStats();\n\u002F\u002F { total: 42, byType: {...}, entities: 15, edges: 8, procedures: 3 }\n```\n\n## CLI Usage\n\n```bash\n# Run tests\nnode dist\u002Findex.js test\n\n# Start MCP server (for agent integration)\nnpm run mcp\n```\n\n## MCP Server\n\nStart the MCP server for agent integration:\n\n```bash\nnpm run mcp\n```\n\n**Security Verification:**\n\n| Claim | Evidence |\n|-------|----------|\n| **stdio-only transport** | `src\u002Fmcp\u002Fserver.ts:5` imports `StdioServerTransport` from `@modelcontextprotocol\u002Fsdk\u002Fserver\u002Fstdio.js` — no HTTP\u002FTCP listeners |\n| **Local-only network** | Only `fetch('http:\u002F\u002Flocalhost:11434\u002F...')` for Ollama embeddings — no external servers |\n| **No postinstall scripts** | `package.json` has no `postinstall`, `preinstall`, or `postbuild` scripts |\n| **Dependencies** | Only `better-sqlite3` (local DB), `ollama` (local embeddings), `uuid` — all from npm |\n| **Credentials** | No environment variables, no secrets in code |\n\n**Database:** Default location is `.\u002Fopenclaw-memory.db` (SQLite, local file).\n\n**Known Limitations:**\n- Memory content is passed to LLM prompts — users could inject instructions via stored memories\n- Calls local Ollama at `localhost:11434` for embeddings — requires Ollama running\n\n## Security Notes\n\n1. ✅ **No external network** — MCP server uses stdio, not HTTP\u002FTCP. Only calls `localhost:11434` for local Ollama embeddings.\n2. ✅ **No authentication required** — Only accessible to the parent process\n3. ✅ **Local-only database** — SQLite file, no remote connections\n4. ✅ **No credentials needed** — Only requires local Ollama for embeddings\n5. ✅ **No postinstall scripts** — Clean npm install\n6. ⚠️ **Prompt injection risk** — Memory content is passed to LLM prompts. If users store malicious content, it could affect LLM behavior. This is inherent to all memory systems.\n\n## Database Location\n\nDefault: `.\u002Fopenclaw-memory.db`\n\nCustom path:\n```typescript\nconst memory = new MemoryStore('\u002Fpath\u002Fto\u002Fcustom.db');\n```\n\n## Features\n\n- **Hybrid Search** — BM25 + semantic (embedding) with reciprocal rank fusion\n- **Entity Extraction** — Auto-extract people, orgs, projects, technologies\n- **Spelling Variants** — UK↔US English expansion (colour\u002Fcolor, etc.)\n- **Question-Type Aware** — Factual questions prioritize semantic memories\n- **Entity Boost** — Memories with matching entities rank higher\n\n## Benchmark\n\n| System | LOCOMO Score |\n|--------|--------------|\n| **Muninn** | **93%** |\n| Engram | 79.6% |\n| Mem0 | 66.9% |\n\nMuninn Phase 1.5 includes knowledge graph integration for temporal reasoning and contradiction detection.\n\n## License\n\nMIT — Free, open source, no restrictions.\n\n---\n\n🦜 *Built by KakāpōHiko (KH)*\n","# Muninn Memory\n\nA local-first memory system for AI agents. Store episodic, semantic, and procedural memories with intelligent retrieval.\n\n## Installation\n\n```bash\nclawhub install muninn-memory\n```\n\nOr install from source:\n```bash\ncd ~\u002F.openclaw\u002Fworkspace\u002Fskills\ngit clone https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fmuninn-memory.git\ncd muninn-memory\nnpm install && npm run build\n```\n\n## Requirements\n\n- **Node.js** 18+\n- **Ollama** running locally (for embeddings)\n- **SQLite** (included)\n\n## Quick Start\n\n```typescript\nimport { MemoryStore } from 'muninn-memory';\n\n\u002F\u002F Initialize (creates SQLite DB)\nconst memory = new MemoryStore('.\u002Fmemories.db');\n\n\u002F\u002F Store a memory\nconst mem = await memory.remember(\n  'Phillip lives in Brisbane, Australia',\n  'semantic',\n  { entities: ['Phillip', 'Brisbane', 'Australia'], salience: 0.8 }\n);\nconsole.log('Stored:', mem.id);\n\n\u002F\u002F Recall memories\nconst results = await memory.recall('Where does Phillip live?');\nconsole.log(results[0].content);\n\u002F\u002F \"Phillip lives in Brisbane, Australia\"\n\n\u002F\u002F Get stats\nconsole.log(memory.getStats());\n\u002F\u002F { total: 1, byType: { episodic: 0, semantic: 1, procedural: 0 }, entities: 3, edges: 0, procedures: 0 }\n\nmemory.close();\n```\n\n## Memory Types\n\n| Type | Use Case |\n|------|----------|\n| `episodic` | Events, conversations, experiences |\n| `semantic` | Facts, knowledge, relationships |\n| `procedural` | Skills, workflows, step-by-step processes |\n\n## API\n\n### `remember(content, type, options?)`\n\nStore a new memory.\n\n```typescript\nawait memory.remember(\n  'Meeting with Sarah about Q3 roadmap',\n  'episodic',\n  { \n    entities: ['Sarah', 'Q3 roadmap'],\n    salience: 0.7,\n    title: 'Q3 Planning Meeting'\n  }\n);\n```\n\n**Options:**\n- `title?: string` - Short title\n- `summary?: string` - Brief summary\n- `entities?: string[]` - Extracted entities\n- `topics?: string[]` - Topics\u002Ftags\n- `salience?: number` - Importance 0-1 (default: 0.5)\n\n**Returns:** `Memory` object with id, content, type, entities, etc.\n\n### `recall(query, options?)`\n\nSearch memories using hybrid search.\n\n```typescript\nconst results = await memory.recall('Sarah Q3', {\n  limit: 5,\n  types: ['episodic', 'semantic'],\n  entities: ['Sarah'],\n  topics: ['planning']\n});\n```\n\n**Options:**\n- `types?: MemoryType[]` - Filter by type\n- `entities?: string[]` - Filter by entity\n- `topics?: string[]` - Filter by topic\n- `limit?: number` - Max results (default: 10)\n\n**Returns:** Array of `Memory` objects sorted by relevance.\n\n### `forget(id, hard?)`\n\nDelete a memory.\n\n```typescript\n\u002F\u002F Soft delete (can be recovered)\nmemory.forget('m_abc123');\n\n\u002F\u002F Hard delete (permanent)\nmemory.forget('m_abc123', true);\n```\n\n### `getEntities()`\n\nList all extracted entities.\n\n```typescript\nconst entities = memory.getEntities();\n\u002F\u002F [{ name: 'Phillip', memory_count: 5, last_seen: '2026-02-24...' }, ...]\n```\n\n### `getStats()`\n\nGet vault statistics.\n\n```typescript\nconst stats = memory.getStats();\n\u002F\u002F { total: 42, byType: {...}, entities: 15, edges: 8, procedures: 3 }\n```\n\n## CLI Usage\n\n```bash\n# Run tests\nnode dist\u002Findex.js test\n\n# Start MCP server (for agent integration)\nnpm run mcp\n```\n\n## MCP Server\n\nStart the MCP server for agent integration:\n\n```bash\nnpm run mcp\n```\n\n**Security Verification:**\n\n| Claim | Evidence |\n|-------|----------|\n| **stdio-only transport** | `src\u002Fmcp\u002Fserver.ts:5` imports `StdioServerTransport` from `@modelcontextprotocol\u002Fsdk\u002Fserver\u002Fstdio.js` — no HTTP\u002FTCP listeners |\n| **Local-only network** | Only `fetch('http:\u002F\u002Flocalhost:11434\u002F...')` for Ollama embeddings — no external servers |\n| **No postinstall scripts** | `package.json` has no `postinstall`, `preinstall`, or `postbuild` scripts |\n| **Dependencies** | Only `better-sqlite3` (local DB), `ollama` (local embeddings), `uuid` — all from npm |\n| **Credentials** | No environment variables, no secrets in code |\n\n**Database:** Default location is `.\u002Fopenclaw-memory.db` (SQLite, local file).\n\n**Known Limitations:**\n- Memory content is passed to LLM prompts — users could inject instructions via stored memories\n- Calls local Ollama at `localhost:11434` for embeddings — requires Ollama running\n\n## Security Notes\n\n1. ✅ **No external network** — MCP server uses stdio, not HTTP\u002FTCP. Only calls `localhost:11434` for local Ollama embeddings.\n2. ✅ **No authentication required** — Only accessible to the parent process\n3. ✅ **Local-only database** — SQLite file, no remote connections\n4. ✅ **No credentials needed** — Only requires local Ollama for embeddings\n5. ✅ **No postinstall scripts** — Clean npm install\n6. ⚠️ **Prompt injection risk** — Memory content is passed to LLM prompts. If users store malicious content, it could affect LLM behavior. This is inherent to all memory systems.\n\n## Database Location\n\nDefault: `.\u002Fopenclaw-memory.db`\n\nCustom path:\n```typescript\nconst memory = new MemoryStore('\u002Fpath\u002Fto\u002Fcustom.db');\n```\n\n## Features\n\n- **Hybrid Search** — BM25 + semantic (embedding) with reciprocal rank fusion\n- **Entity Extraction** — Auto-extract people, orgs, projects, technologies\n- **Spelling Variants** — UK↔US English expansion (colour\u002Fcolor, etc.)\n- **Question-Type Aware** — Factual questions prioritize semantic memories\n- **Entity Boost** — Memories with matching entities rank higher\n\n## Benchmark\n\n| System | LOCOMO Score |\n|--------|--------------|\n| **Muninn** | **93%** |\n| Engram | 79.6% |\n| Mem0 | 66.9% |\n\nMuninn Phase 1.5 includes knowledge graph integration for temporal reasoning and contradiction detection.\n\n## License\n\nMIT — Free, open source, no restrictions.\n\n---\n\n🦜 *Built by KakāpōHiko (KH)*\n",{},"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fphillipneho\u002Fmuninn-memory",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":7,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill muninn-memory",{"tool":38,"command":39},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill muninn-memory",{"tool":41,"command":42},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill muninn-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fphillipneho\u002Fmuninn-memory\u002FSKILL.md",true,[],[47,55,62,69,76,83],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":54},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":54},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":54},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":54},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":54},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":54},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]