{"data":{"slug":"shishirpatil-gorilla","name":"gorilla","tagline":"Training and Evaluating LLMs for Function Calls (Tool Calls)","github_url":"https://github.com/ShishirPatil/gorilla","owner":"ShishirPatil","repo":"gorilla","owner_avatar_url":"https://avatars.githubusercontent.com/u/30296397?v=4","primary_language":"Python","stars":12940,"forks":1387,"topics":["api","api-documentation","chatgpt","claude-api","gpt-4-api","llm","openai-api","openai-functions"],"archived":false,"github_pushed_at":"2026-04-13T03:19:45+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/shishirpatil-gorilla","markdown_url":"https://www.graphcanon.com/tools/shishirpatil-gorilla.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/shishirpatil-gorilla","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=shishirpatil-gorilla","description":"Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)","homepage_url":"https://gorilla.cs.berkeley.edu/","license":"Apache-2.0","open_issues":264,"watchers":94,"ai_summary":"A toolset for training and evaluating large language models with functions calls or tool usages.","readme_excerpt":"### Quick Start\nTry Gorilla in your browser:\n- 🚀 [Gorilla Colab Demo](https://colab.research.google.com/drive/1y78Zj7xHysX0xMpr9S468HYs12Mj6X1F?usp=sharing): Try the base Gorilla model\n- 🌐 [Gorilla Gradio Demo](https://huggingface.co/spaces/gorilla-llm/gorilla-demo/): Interactive web interface\n- 🔥 [OpenFunctions Colab Demo](https://colab.research.google.com/drive/1Td3_R5vPael9PnKYHcl-PxmZkZzA9TCo?usp=sharing): Try the latest OpenFunctions model\n- 🎯 [OpenFunctions Website Demo](https://gorilla.cs.berkeley.edu/leaderboard.html#api-explorer): Experiment with function calling\n- 📊 [Berkeley Function Calling Leaderboard](https://gorilla.cs.berkeley.edu/leaderboard): Compare function calling capabilities\n\n---\n\n### Installation Options\n\n1. **Gorilla CLI** - Fastest way to get started\n```bash\npip install gorilla-cli\ngorilla generate 100 random characters into a file called test.txt\n```\n[Learn more about Gorilla CLI →](https://github.com/gorilla-llm/gorilla-cli)\n\n2. **Run Gorilla Locally**\n```bash\ngit clone https://github.com/ShishirPatil/gorilla.git\ncd gorilla/inference\n```\n[Detailed local setup instructions →](/gorilla/inference/README.md)\n\n3. **Use OpenFunctions**\n```python\nimport openai\n\nopenai.api_key = \"EMPTY\"\nopenai.api_base = \"http://luigi.millennium.berkeley.edu:8000/v1\"\n\n---\n\n## License\n\nGorilla is Apache 2.0 licensed, making it suitable for both academic and commercial use.","github_created_at":"2023-05-19T00:46:45+00:00","created_at":"2026-07-11T10:44:10.87545+00:00","updated_at":"2026-07-11T15:17:33.753859+00:00","categories":[{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"llm","name":"llm"},{"slug":"openai-functions","name":"openai-functions"},{"slug":"gpt-4-api","name":"gpt-4-api"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"api","name":"api"},{"slug":"openai-api","name":"openai-api"},{"slug":"claude-api","name":"claude-api"}],"trust":{"provenance":{"is_fork":false,"github_id":642608852,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T10:44:11.489Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":89,"last_release_at":"2025-07-17T21:10:14Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:44:12.429Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T15:17:04.735Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-11T15:17:04.735Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-11T15:17:04.735Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":""},"requirements":{"notes":["Gorilla works best with Python environments and requires installation through pip or local repository cloning."]},"constraints":{"pricing_model":"freemium"},"when_to_use":["You should consider using Gorilla if you need a comprehensive framework for developing LLMs capable of leveraging external functions effectively.","If your project requires interactive testing through web interfaces like Colab and Gradio, Gorilla provides dedicated demos that can help streamline this process."],"when_not_to_use":["Avoid Gorilla if your primary focus is not on function calling or tool usage capabilities for LLMs; another model-specific framework may better fit your needs.","If the lack of a direct comparison tool to other models' function-calling performance is critical in your decision process, and you find no suitable alternatives listed on their leaderboard."],"source":"enrich:decision_facts","observed_at":"2026-07-11T15:17:33.454Z"},"constraint_facets":{"pricing_model":"freemium"},"decision_summary":[{"label":"Pricing","value":"freemium"},{"label":"Requirements","value":"Gorilla works best with Python environments and requires installation through pip or local repository cloning."},{"label":"Adopt for","value":"Gorilla specializes in training and evaluating large language models (LLMs) to perform function calls or tool usages."},{"label":"License detail","value":"Gorilla can be used freely under the Apache 2.0 license for both academic and commercial purposes."}]}}