{"data":{"slug":"ryandonofrio3-osgrep","name":"osgrep","tagline":"Open Source Semantic Search for your AI Agent","github_url":"https://github.com/Ryandonofrio3/osgrep","owner":"Ryandonofrio3","repo":"osgrep","owner_avatar_url":"https://avatars.githubusercontent.com/u/97113725?v=4","primary_language":"TypeScript","stars":1145,"forks":67,"topics":["colbert","embeddings","grep","grep-search"],"archived":false,"github_pushed_at":"2026-01-17T19:45:10+00:00","maintenance_label":"Slowing","stars_delta_30d":5,"url":"https://www.graphcanon.com/tools/ryandonofrio3-osgrep","markdown_url":"https://www.graphcanon.com/tools/ryandonofrio3-osgrep.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ryandonofrio3-osgrep","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ryandonofrio3-osgrep","description":"Open Source Semantic Search for your AI Agent","homepage_url":null,"license":"Apache-2.0","open_issues":21,"watchers":2,"ai_summary":"Provides open-source capabilities for semantic search tailored for integrating with AI agents.","readme_excerpt":"## Quick Start\n\n1. **Install**\n   ```bash\n   npm install -g osgrep\n   ```\n\n2.  **Setup (Recommended)**\n\n    ```bash\n    osgrep setup\n    ```\n\n    Downloads embedding models (~150MB) upfront. If you skip this, models download automatically on first use.\n\n3.  **Search**\n\n    ```bash\n    cd my-repo\n    osgrep \"where do we handle authentication?\"\n    ```\n\n    **Your first search will automatically index the repository.** Each repository is automatically isolated with its own index. Switching between repos \"just works\" — no manual configuration needed. If the background server is running (`osgrep serve`), search goes through the hot daemon; otherwise it falls back to on-demand indexing.\n\n4.  **Trace** (Call Graph)\n\n    ```bash\n    osgrep trace \"function_name\"\n    ```\nSee who calls a function (upstream dependencies) and what it calls (downstream dependencies). Perfect for impact analysis and understanding code flow.\n\nTo find the symbols in your code base:\n    ```bash\n    osgrep symbols\n    ```\n\nIn our public benchmarks, `osgrep` can save about 20% of your LLM tokens and deliver a 30% speedup.\n\n<div align=\"center\">\n  <img src=\"public/bench.png\" alt=\"osgrep benchmark\" width=\"100%\" style=\"border-radius: 8px; margin: 20px 0;\" />\n</div>\n\n---\n\n## License\n\nLicensed under the Apache License, Version 2.0.\nSee [LICENSE](LICENSE) and [Apache-2.0](https://opensource.org/licenses/Apache-2.0) for details.","github_created_at":"2025-11-21T06:14:31+00:00","created_at":"2026-07-11T11:31:28.435841+00:00","updated_at":"2026-09-20T06:16:23.574773+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"}],"tags":[{"slug":"colbert","name":"colbert"},{"slug":"embeddings","name":"embeddings"},{"slug":"grep-search","name":"grep-search"}],"trust":{"provenance":{"is_fork":false,"github_id":1101059247,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:16:21.235Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":245,"last_release_at":"2025-12-09T03:12:24Z","stars_delta_30d":5,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:31:29.642Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"package.json:@modelcontextprotocol/*","observed_at":"2026-09-20T06:16:22.337Z","server_manifest":true},"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:16:22.337Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-09-20T06:16:22.337Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T06:16:22.337Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T06:16:22.337Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["- You need advanced semantic search functionality tailored to work seamlessly with your AI agent.","- Your project uses or plans to use TypeScript, allowing osgrep's TypeScript-based solution to integrate more smoothly.","- You rely on open-source technologies, valuing the Apache-2.0 license for flexibility and transparency."],"when_not_to_use":["- If your search requirements can be met with simple keyword matching rather than semantic analysis, as osgrep specializes in more complex semantic searches.","- Your AI project is not using TypeScript or where seamless integration with TypeScript-specific features of osgrep would offer no advantage.","- You require additional proprietary functionalities that go beyond what the open-source license and community provide."],"source":"enrich:decision_facts","observed_at":"2026-07-12T10:49:39.638Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Adopt for","value":"osgrep is an open-source tool focused on semantic search capabilities specifically designed for integration with AI agents using TypeScript."},{"label":"License detail","value":"osgrep is available under the Apache-2.0 license, offering permissive use for both commercial and non-commercial projects without requiring derivative works to be open-sourced."}]}}