{"data":{"slug":"chroma-core-chroma","name":"chroma","tagline":"Search infrastructure for AI","github_url":"https://github.com/chroma-core/chroma","owner":"chroma-core","repo":"chroma","owner_avatar_url":"https://avatars.githubusercontent.com/u/105881770?v=4","primary_language":"Rust","stars":29320,"forks":2516,"topics":["agents","ai","ai-agents","database","rust","rust-lang"],"archived":false,"github_pushed_at":"2026-09-17T21:48:14+00:00","maintenance_label":"Very active","stars_delta_30d":422,"url":"https://www.graphcanon.com/tools/chroma-core-chroma","markdown_url":"https://www.graphcanon.com/tools/chroma-core-chroma.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/chroma-core-chroma","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=chroma-core-chroma","description":"Search infrastructure for AI","homepage_url":"https://www.trychroma.com/","license":"Apache-2.0","open_issues":864,"watchers":138,"ai_summary":"Chroma is an open-source data infrastructure for AI, providing vector, hybrid, and full-text search capabilities. It supports multiple programming languages and offers a simple API for creating collections, adding documents, and querying data.","readme_excerpt":"<p align=\"center\">\n    <b>Chroma - the open-source data infrastructure for AI</b>. <br />\n</p>\n\n<p align=\"center\">\n  <a href=\"https://discord.gg/MMeYNTmh3x\" target=\"_blank\">\n      <img src=\"https://img.shields.io/discord/1073293645303795742?cacheSeconds=3600\" alt=\"Discord\">\n  </a> |\n  <a href=\"https://github.com/chroma-core/chroma/blob/master/LICENSE\" target=\"_blank\">\n      <img src=\"https://img.shields.io/badge/License-Apache_2.0-blue.svg\" alt=\"License\">\n  </a> |\n  <a href=\"https://docs.trychroma.com/\" target=\"_blank\">\n      Docs\n  </a> |\n  <a href=\"https://www.trychroma.com/\" target=\"_blank\">\n      Homepage\n  </a>\n</p>\n\n```bash\npip install chromadb # python client\n# for javascript, npm install chromadb!\n# for client-server mode, chroma run --path /chroma_db_path\n```\n\n## Chroma Cloud\n\nOur hosted service, Chroma Cloud, powers serverless vector, hybrid, and full-text search. It's extremely fast, cost-effective, scalable and painless. Create a DB and try it out in under 30 seconds with $5 of free credits.\n\n[Get started with Chroma Cloud](https://trychroma.com/signup)\n\n## API\n\nThe core API is only 4 functions (run our [💡 Google Colab](https://colab.research.google.com/drive/1QEzFyqnoFxq7LUGyP1vzR4iLt9PpCDXv?usp=sharing)):\n\n```python\nimport chromadb\n# setup Chroma in-memory, for easy prototyping. Can add persistence easily!\nclient = chromadb.Client()\n\n# Create collection. get_collection, get_or_create_collection, delete_collection also available!\ncollection = client.create_collection(\"all-my-documents\")\n\n# Add docs to the collection. Can also update and delete. Row-based API coming soon!\ncollection.add(\n    documents=[\"This is document1\", \"This is document2\"], # we handle tokenization, embedding, and indexing automatically. You can skip that and add your own embeddings as well\n    metadatas=[{\"source\": \"notion\"}, {\"source\": \"google-docs\"}], # filter on these!\n    ids=[\"doc1\", \"doc2\"], # unique for each doc\n)\n\n# Query/search 2 most similar results. You can also .get by id\nresults = collection.query(\n    query_texts=[\"This is a query document\"],\n    n_results=2,\n    # where={\"metadata_field\": \"is_equal_to_this\"}, # optional filter\n    # where_document={\"$contains\":\"search_string\"}  # optional filter\n)\n```\n\nLearn about all features on our [Docs](https://docs.trychroma.com)\n\n## Get involved\n\nChroma is a rapidly developing project. We welcome PR contributors and ideas for how to improve the project.\n- [Join the conversation on Discord](https://discord.com/invite/chromadb) - `#contributing` channel\n- [Review the 🛣️ Roadmap and contribute your ideas](https://docs.trychroma.com/docs/overview/oss#roadmap)\n- [Grab an issue and open a PR](https://github.com/chroma-core/chroma/issues) - [`Good first issue tag`](https://github.com/chroma-core/chroma/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22)\n- [Read our contributing guide](https://docs.trychroma.com/docs/overview/oss#contributing)\n\n**Release Cadence**\nWe currently release new tagged versions of the `pypi` and `npm` packages on Mondays. Hotfixes go out at any time during the week.\n\n## License\n\n[Apache 2.0](./LICENSE)","github_created_at":"2022-10-05T17:58:44+00:00","created_at":"2026-07-07T15:08:38.505367+00:00","updated_at":"2026-09-20T04:28:23.540656+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":"agents","name":"agents"},{"slug":"ai","name":"ai"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"database","name":"database"},{"slug":"full-text-search","name":"full-text-search"},{"slug":"rust","name":"rust"},{"slug":"rust-lang","name":"rust-lang"},{"slug":"vector-search","name":"vector-search"}],"trust":{"provenance":{"is_fork":false,"github_id":546206616,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:05:48.374Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":0,"last_release_at":"2026-05-05T05:55:40Z","stars_delta_30d":422,"open_issues_delta_30d":118},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":8,"high_count":0,"last_scan_at":"2026-09-18T08:05:50.710Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:05:47.287Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-18T08:05:47.287Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-18T08:05:47.287Z"},"languages":{"value":["rust","python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-18T08:05:47.287Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-18T08:05:47.287Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-18T08:05:47.287Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Chroma is open-source and free to use, but it also offers a hosted service called Chroma Cloud, which is cost-effective and scalable, with $5 of free credits available."},"requirements":{"notes":["Chroma can be installed via pip for Python and npm for JavaScript.","For client-server mode, you can run Chroma with a specified path for the database."],"min_ram_gb":1,"requires_docker":false},"constraints":{"min_ram_gb":1,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When you need a simple and efficient API for creating collections, adding documents, and querying data with vector, hybrid, and full-text search capabilities.","If you are working with Rust and want to leverage its performance benefits in your AI search infrastructure.","When you require a scalable solution that can be easily prototyped in-memory and later made persistent.","If you are looking for a solution that handles tokenization, embedding, and indexing automatically, allowing you to skip these steps and focus on your application logic."],"when_not_to_use":["If you need a solution that is tightly integrated with a specific database system that Chroma does not support or integrate with.","When you require a more complex or specialized search infrastructure that offers features beyond vector, hybrid, and full-text search.","If you are working in an environment where Rust is not a preferred language, and you need a tool that is more aligned with your existing tech stack.","When you need a solution that is not open-source and prefer proprietary software with dedicated support and features."],"source":"enrich:decision_facts","observed_at":"2026-09-18T09:12:44.706Z"},"constraint_facets":{"min_ram_gb":1,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - Chroma is open-source and free to use, but it also offers a hosted service called Chroma Cloud, which is cost-effective and scalable, with $5 of free credits available."},{"label":"Requirements","value":"Min 1 GB RAM; Chroma can be installed via pip for Python and npm for JavaScript.; For client-server mode, you can run Chroma with a specified path for the database."},{"label":"Adopt for","value":"Chroma is an open-source data infrastructure for AI, offering vector, hybrid, and full-text search capabilities. It supports multiple programming languages and provides a simple API for managing collections and querying."},{"label":"License detail","value":"Chroma is licensed under the Apache-2.0 license, which is a permissive free software license."}]}}