{"data":{"slug":"caviraoss-openmemory","name":"OpenMemory","tagline":"Local persistent memory store for LLM applications","github_url":"https://github.com/CaviraOSS/OpenMemory","owner":"CaviraOSS","repo":"OpenMemory","owner_avatar_url":"https://avatars.githubusercontent.com/u/214697751?v=4","primary_language":"TypeScript","stars":4510,"forks":504,"topics":["ai","ai-agents","ai-infrastructure","ai-memory","artificial-intelligence","cognitive-architecture","embeddings","gemini","llm","long-term-memory","memory","memory-engine","memory-retrieval","ollama","one-line","openai","openmemory","rag","supermemory","vector-database"],"archived":false,"github_pushed_at":"2026-09-14T12:02:21+00:00","maintenance_label":"Very active","stars_delta_30d":153,"url":"https://www.graphcanon.com/tools/caviraoss-openmemory","markdown_url":"https://www.graphcanon.com/tools/caviraoss-openmemory.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/caviraoss-openmemory","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=caviraoss-openmemory","description":"Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.","homepage_url":"https://openmemory.cavira.app","license":"Apache-2.0","open_issues":19,"watchers":33,"ai_summary":"Provides local storage and retrieval capabilities for various AI agents including claude desktop, GitHub Copilot, Codex, and more. Built with TypeScript.","readme_excerpt":"### Install as a library\n\n```bash\nnpm install longmemory\n```\n\n```ts\nimport { createMemory } from 'longmemory';\n\nconst memory = await createMemory();\nawait memory.ingest({\n    user_id: 'alice',\n    text: 'I prefer TypeScript for backend services',\n});\n\nconst result = await memory.recall({\n    text: 'What language does Alice prefer?',\n    mode: 'strict',\n});\n\nconsole.log(result);\nawait memory.close();\n```\n\nNo service or external database is required for in-memory use.\n\nFor optional evidence-grounded answers with your own model, use the exported\n`answer_from_evidence` adapter. It accepts authorized evidence, validates cited\nexcerpts, and makes at most one model call; ordinary recall is unchanged.\nSee [docs/answering.md](docs/answering.md) for policies, limits, and integration.\n\n---\n\n### Install the CLI\n\n```bash\nnpm install --global longmemory\nlongmemory init\nlongmemory recall \"current project priorities\" --mode associative\n```\n\n---\n\n### Docker\n\n```bash\ndocker run --rm \\\n  -p 7331:7331 \\\n  -v longmemory-data:/data \\\n  -e LONGMEMORY_API_KEY=change-me \\\n  ghcr.io/caviraoss/longmemory:latest\n```\n\n---\n\n### Docker Compose\n\n```bash\ncp .env.example .env\ndocker compose up --build -d longmemory\n```\n\nInclude the dashboard:\n\n```bash\ndocker compose --profile ui up --build -d\n```\n\n- API and MCP: `http://127.0.0.1:7331`\n- Dashboard: `http://127.0.0.1:3000`\n- Health: `http://127.0.0.1:7331/health`\n\n---\n\n---\n\n## 11. Deployment Options\n\n| Platform       | Configuration          | What it deploys                           |\n| -------------- | ---------------------- | ----------------------------------------- |\n| Docker         | `Dockerfile`           | API and Streamable HTTP MCP               |\n| Docker Compose | `docker-compose.yml`   | API/MCP plus optional dashboard           |\n| Heroku         | `app.json`             | Containerized API/MCP                     |\n| Railway        | `railway.json`         | Containerized API/MCP                     |\n| Render         | `render.yaml`          | API/MCP with persistent disk              |\n| DigitalOcean   | `.do/spec.yaml`        | App Platform API/MCP service              |\n| Vercel         | `vercel.json`          | Dashboard; configure `LONGMEMORY_API_URL` |\n| Windows        | `start-longmemory.ps1` | Background local API/MCP process          |\n\nFor hosted API deployments, set `LONGMEMORY_API_KEY`, mount persistent storage at `/data`, and terminate TLS at the platform edge. Vercel hosts only the stateless dashboard and requires a separately deployed LongMemory API.\n\n---\n\n---\n\n## 17. License\n\nLongMemory is licensed under the [Apache License 2.0](LICENSE). The separately\npublished n8n community node uses MIT as required by n8n's strict package\nvalidator.","github_created_at":"2025-10-19T16:12:49+00:00","created_at":"2026-07-07T17:43:57.97511+00:00","updated_at":"2026-09-20T06:01:07.861841+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"ai-agents","name":"ai-agents"},{"slug":"embeddings","name":"embeddings"},{"slug":"long-term-memory","name":"long-term-memory"},{"slug":"memory-engine","name":"memory-engine"},{"slug":"vector-database","name":"vector-database"}],"trust":{"provenance":{"is_fork":false,"github_id":1079345325,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:01:05.506Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":5,"last_release_at":"2025-12-20T16:45:32Z","stars_delta_30d":153,"open_issues_delta_30d":6},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:24:44.485Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"package.json:@modelcontextprotocol/*","observed_at":"2026-09-20T06:01:06.736Z","server_manifest":true},"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:01:06.736Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-20T06:01:06.736Z","managed_saas":false},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-09-20T06:01:06.736Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T06:01:06.736Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-20T06:01:06.736Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T06:01:06.736Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Need to integrate persistent memory support for specific LLMs like Claude.","Looking for a TypeScript-based solution.","Developing applications that require direct compatibility with GitHub Copilot."],"when_not_to_use":["Require cloud-based memory storage services.","Your project must use languages other than TypeScript.","Seek a generic vector database without specific LLM integrations."],"source":"enrich:decision_facts","observed_at":"2026-07-12T11:24:38.664Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"OpenMemory offers local storage tailored for AI agents like Claude Desktop and GitHub Copilot."}]}}