{"id":24538779,"url":"https://github.com/spences10/mcp-memory-libsql","last_synced_at":"2025-04-08T03:19:59.686Z","repository":{"id":272510122,"uuid":"916815330","full_name":"spences10/mcp-memory-libsql","owner":"spences10","description":"🧠 High-performance persistent memory system for Model Context Protocol (MCP) powered by libSQL. Features vector search, semantic knowledge storage, and efficient relationship management - perfect for AI agents and knowledge graph applications.","archived":false,"fork":false,"pushed_at":"2025-03-31T20:25:46.000Z","size":155,"stargazers_count":37,"open_issues_count":4,"forks_count":7,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-31T20:37:40.814Z","etag":null,"topics":["ai-tools","embeddings","knowledge-graph","libsql","mcp","model-context-protocol","persistent-storage","semantic-search","vector-search"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/spences10.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-01-14T20:09:43.000Z","updated_at":"2025-03-31T20:25:08.000Z","dependencies_parsed_at":"2025-01-14T22:26:30.339Z","dependency_job_id":"f1a9e688-f794-4509-8474-d514e97da3fe","html_url":"https://github.com/spences10/mcp-memory-libsql","commit_stats":null,"previous_names":["spences10/mcp-memory-libsql"],"tags_count":10,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spences10%2Fmcp-memory-libsql","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spences10%2Fmcp-memory-libsql/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spences10%2Fmcp-memory-libsql/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spences10%2Fmcp-memory-libsql/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/spences10","download_url":"https://codeload.github.com/spences10/mcp-memory-libsql/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247767239,"owners_count":20992548,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-tools","embeddings","knowledge-graph","libsql","mcp","model-context-protocol","persistent-storage","semantic-search","vector-search"],"created_at":"2025-01-22T15:15:21.356Z","updated_at":"2025-04-08T03:19:59.680Z","avatar_url":"https://github.com/spences10.png","language":"TypeScript","funding_links":[],"categories":["Knowledge \u0026 Memory","📚 Projects (1974 total)","Databases","🌐 Web Development","Knowledge Management \u0026 Memory","TypeScript"],"sub_categories":["How to Submit","MCP Servers"],"readme":"# mcp-memory-libsql\n\nA high-performance, persistent memory system for the Model Context\nProtocol (MCP) powered by libSQL. This server provides vector search\ncapabilities and efficient knowledge storage using libSQL as the\nbacking store.\n\n\u003ca href=\"https://glama.ai/mcp/servers/22lg4lq768\"\u003e\n  \u003cimg width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/22lg4lq768/badge\" alt=\"Glama badge\" /\u003e\n\u003c/a\u003e\n\n## Features\n\n- 🚀 High-performance vector search using libSQL\n- 💾 Persistent storage of entities and relations\n- 🔍 Semantic search capabilities\n- 🔄 Knowledge graph management\n- 🌐 Compatible with local and remote libSQL databases\n- 🔒 Secure token-based authentication for remote databases\n\n## Configuration\n\nThis server is designed to be used as part of an MCP configuration.\nHere are examples for different environments:\n\n### Cline Configuration\n\nAdd this to your Cline MCP settings:\n\n```json\n{\n\t\"mcpServers\": {\n\t\t\"mcp-memory-libsql\": {\n\t\t\t\"command\": \"npx\",\n\t\t\t\"args\": [\"-y\", \"mcp-memory-libsql\"],\n\t\t\t\"env\": {\n\t\t\t\t\"LIBSQL_URL\": \"file:/path/to/your/database.db\"\n\t\t\t}\n\t\t}\n\t}\n}\n```\n\n### Claude Desktop with WSL Configuration\n\nFor a detailed guide on setting up this server with Claude Desktop in\nWSL, see\n[Getting MCP Server Working with Claude Desktop in WSL](https://scottspence.com/posts/getting-mcp-server-working-with-claude-desktop-in-wsl).\n\nAdd this to your Claude Desktop configuration for WSL environments:\n\n```json\n{\n\t\"mcpServers\": {\n\t\t\"mcp-memory-libsql\": {\n\t\t\t\"command\": \"wsl.exe\",\n\t\t\t\"args\": [\n\t\t\t\t\"bash\",\n\t\t\t\t\"-c\",\n\t\t\t\t\"source ~/.nvm/nvm.sh \u0026\u0026 LIBSQL_URL=file:/path/to/database.db /home/username/.nvm/versions/node/v20.12.1/bin/npx mcp-memory-libsql\"\n\t\t\t]\n\t\t}\n\t}\n}\n```\n\n### Database Configuration\n\nThe server supports both local SQLite and remote libSQL databases\nthrough the LIBSQL_URL environment variable:\n\nFor local SQLite databases:\n\n```json\n{\n\t\"env\": {\n\t\t\"LIBSQL_URL\": \"file:/path/to/database.db\"\n\t}\n}\n```\n\nFor remote libSQL databases (e.g., Turso):\n\n```json\n{\n\t\"env\": {\n\t\t\"LIBSQL_URL\": \"libsql://your-database.turso.io\",\n\t\t\"LIBSQL_AUTH_TOKEN\": \"your-auth-token\"\n\t}\n}\n```\n\nNote: When using WSL, ensure the database path uses the Linux\nfilesystem format (e.g., `/home/username/...`) rather than Windows\nformat.\n\nBy default, if no URL is provided, it will use `file:/memory-tool.db`\nin the current directory.\n\n## API\n\nThe server implements the standard MCP memory interface with\nadditional vector search capabilities:\n\n- Entity Management\n  - Create/Update entities with embeddings\n  - Delete entities\n  - Search entities by similarity\n- Relation Management\n  - Create relations between entities\n  - Delete relations\n  - Query related entities\n\n## Architecture\n\nThe server uses a libSQL database with the following schema:\n\n- Entities table: Stores entity information and embeddings\n- Relations table: Stores relationships between entities\n- Vector search capabilities implemented using libSQL's built-in\n  vector operations\n\n## Development\n\n### Publishing\n\nDue to npm 2FA requirements, publishing needs to be done manually:\n\n1. Create a changeset (documents your changes):\n\n```bash\npnpm changeset\n```\n\n2. Version the package (updates version and CHANGELOG):\n\n```bash\npnpm changeset version\n```\n\n3. Publish to npm (will prompt for 2FA code):\n\n```bash\npnpm release\n```\n\n## Contributing\n\nContributions are welcome! Please read our contributing guidelines\nbefore submitting pull requests.\n\n## License\n\nMIT License - see the [LICENSE](LICENSE) file for details.\n\n## Acknowledgments\n\n- Built on the\n  [Model Context Protocol](https://github.com/modelcontextprotocol)\n- Powered by [libSQL](https://github.com/tursodatabase/libsql)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fspences10%2Fmcp-memory-libsql","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fspences10%2Fmcp-memory-libsql","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fspences10%2Fmcp-memory-libsql/lists"}