{"data":{"slug":"om-ai-lab-omagent","name":"OmAgent","tagline":"Build multimodal language agents for fast prototype and production","github_url":"https://github.com/om-ai-lab/OmAgent","owner":"om-ai-lab","repo":"OmAgent","owner_avatar_url":"https://avatars.githubusercontent.com/u/96569904?v=4","primary_language":"Python","stars":2667,"forks":292,"topics":["agent","chatbot","gemini","gpt","gpt4","gradio","language-agent","large-language-models","llama","llava","llm","multimodal","multimodal-agent","openai","python","rag","smart-hardware","vision-and-language","vlm","workflow"],"archived":false,"github_pushed_at":"2025-03-19T11:36:13+00:00","maintenance_label":"Dormant","stars_delta_30d":2,"url":"https://www.graphcanon.com/tools/om-ai-lab-omagent","markdown_url":"https://www.graphcanon.com/tools/om-ai-lab-omagent.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/om-ai-lab-omagent","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=om-ai-lab-omagent","description":"[EMNLP-2024] Build multimodal language agents for fast prototype and production","homepage_url":"https://om-agent.com","license":"Apache-2.0","open_issues":21,"watchers":131,"ai_summary":"A Python library for developing multimodal language agents including modules to integrate GPT, Gemini, LLaMA, and LLAVA models with support for chatbot and smart hardware workflows.","readme_excerpt":"## 🛠️ How To Install\n- python >= 3.10\n- Install omagent_core  \n  Use pip to install omagent_core latest release.\n  ```bash\n  pip install omagent-core\n  ```\n  Or install the latest version from the source code like below.\n  ```bash\n  pip install -e omagent-core\n  ```","github_created_at":"2024-07-04T17:48:43+00:00","created_at":"2026-07-15T10:48:25.558059+00:00","updated_at":"2026-09-20T04:27:30.316369+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":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"chatbot","name":"chatbot"},{"slug":"gemini","name":"gemini"},{"slug":"gpt","name":"gpt"},{"slug":"llama","name":"llama"},{"slug":"llm","name":"llm"},{"slug":"multimodal-agent","name":"multimodal-agent"},{"slug":"openai","name":"openai"}],"trust":{"provenance":{"is_fork":false,"github_id":824259091,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-16T06:00:39.884Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":545,"last_release_at":"2025-02-24T08:16:48Z","stars_delta_30d":2,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:48:26.946Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-16T06:00:40.343Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-16T06:00:40.343Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-16T06:00:40.343Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires Python >= 3.10"],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["Use OmAgent if you are prototyping scenarios involving smart hardware and multimodal workflows.","For projects leveraging Gradio for user interfaces, OmAgent's integration capabilities can expedite development."],"when_not_to_use":["Avoid using OmAgent if your project does not require support for multimodal models or specific integrations with GPT, Gemini, LLaMA, and LLAVA.","If a lightweight solution is required and advanced multimodal features are unnecessary, another tool might be more suited."],"source":"enrich:decision_facts","observed_at":"2026-07-16T21:09:11.290Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Requires Python >= 3.10"},{"label":"Adopt for","value":"OmAgent is a Python library for developing multimodal language agents that supports GPT, Gemini, LLaMA, and LLAVA models."}]}}