{"data":{"slug":"christopherkarani-wax","name":"Wax","tagline":"Single-file memory layer for AI agents with sub-millisecond RAG on Apple Silicon using Metal optimization","github_url":"https://github.com/christopherkarani/Wax","owner":"christopherkarani","repo":"Wax","owner_avatar_url":"https://avatars.githubusercontent.com/u/13857475?v=4","primary_language":"Swift","stars":786,"forks":49,"topics":["ai-agents","cli","coreml","coreml-framework","data-science","machine-learning","mcp","mcp-server","memory","memory-cache","memory-hacking","metal","on-device-ai","rag","rag-pipeline","swift","vector-database","vector-embeddings","vector-search","vectordb"],"archived":false,"github_pushed_at":"2026-08-21T22:25:37+00:00","maintenance_label":"Very active","stars_delta_30d":13,"url":"https://www.graphcanon.com/tools/christopherkarani-wax","markdown_url":"https://www.graphcanon.com/tools/christopherkarani-wax.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/christopherkarani-wax","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=christopherkarani-wax","description":"Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift","homepage_url":"https://christopherkarani.github.io/Wax/","license":"Apache-2.0","open_issues":4,"watchers":6,"ai_summary":"Wax provides an on-device vector database and memory layer written in Swift, optimized for performance on Apple Silicon through Metal. It supports AI agent applications that require fast data retrieval without reliance on external servers or APIs.","readme_excerpt":"## Agent Quick Start\n\nGive your AI coding assistant (Claude Code, Cursor, Codex, Hermes, OpenClaw, Windsurf) a persistent memory that survives across sessions.\n\nInstalling the server is not enough. Hosts ignore MCP tool descriptions unless an always-on file says **when** to write. Paste a block below after you wire the host.\n\n---\n\n## License\n\nWax is released under the Apache License 2.0. See [LICENSE](LICENSE) for details.\n\n<div align=\"center\">\n<sub>Built for developers who believe user data belongs on the user's device</sub>\n</div>","github_created_at":"2026-01-20T06:00:56+00:00","created_at":"2026-07-11T11:27:23.724919+00:00","updated_at":"2026-08-22T00:00:45.905722+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"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":"cli","name":"cli"},{"slug":"coreml","name":"coreml"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"metal","name":"metal"},{"slug":"on-device-ai","name":"on-device-ai"},{"slug":"rag","name":"rag"},{"slug":"vector-search","name":"vector-search"},{"slug":"vectordb","name":"vectordb"}],"trust":{"provenance":{"is_fork":false,"github_id":1138007869,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-22T00:00:44.935Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":7,"days_since_push":0,"last_release_at":"2026-08-21T11:40:05Z","stars_delta_30d":13,"open_issues_delta_30d":3},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:27:24.861Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-22T00:00:45.572Z"},"languages":{"value":["swift"],"source":"github.language","observed_at":"2026-08-22T00:00:45.572Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-22T00:00:45.572Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When developing AI applications that require extremely fast data retrieval with minimal latency on Apple devices.","For projects that prefer in-house data management to avoid external API usage and server dependencies."],"when_not_to_use":["If your application targets non-Apple hardware, as Wax's performance optimization via Metal is specific to Apple Silicon.","In scenarios where integration of Wax with existing complex backend services is necessary, since it does not rely on external APIs or servers for its operation."],"source":"enrich:decision_facts","observed_at":"2026-07-14T19:24:55.586Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Wax, a Swift-based memory layer for AI agents optimized on Apple Silicon via Metal, provides sub-millisecond RAG processing and operates entirely on-device without the need for external servers or APIs."}]}}