{"data":{"node":{"slug":"philolabs-agentic-vbench","name":"agentic-vbench","tagline":"A benchmark for evaluating AI agents in performing real-world post-production tasks like audio and video editing.","github_url":"https://github.com/PhiloLabs/agentic-vbench","owner":"PhiloLabs","repo":"agentic-vbench","owner_avatar_url":"https://avatars.githubusercontent.com/u/260782224?v=4","primary_language":"Python","stars":96,"forks":27,"topics":["ai-agents","benchmark","harbor","llm-evaluation","video-editing"],"archived":false,"github_pushed_at":"2026-09-02T18:05:36+00:00","maintenance_label":"Very active","stars_delta_30d":14,"url":"https://www.graphcanon.com/tools/philolabs-agentic-vbench","markdown_url":"https://www.graphcanon.com/tools/philolabs-agentic-vbench.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/philolabs-agentic-vbench","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=philolabs-agentic-vbench"},"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":"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":"ai-agents","name":"ai-agents"},{"slug":"benchmark","name":"benchmark"},{"slug":"harbor","name":"harbor"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"video-editing","name":"video-editing"}],"edges":[],"neighbours":[{"slug":"calesthio-openmontage","name":"OpenMontage","tagline":"World's first open-source, agentic video production system.","github_url":"https://github.com/calesthio/OpenMontage","owner":"calesthio","repo":"OpenMontage","owner_avatar_url":"https://avatars.githubusercontent.com/u/213189893?v=4","primary_language":"Python","stars":48781,"forks":6108,"topics":["agent","agentic-ai","ai","claude","copilot","cursor","elevenlabs","ffmpeg","flux","image-generation","open-source","openai","python","remotion","stable-diffusion","text-to-speech","text-to-video","video-generation","video-production"],"archived":false,"github_pushed_at":"2026-08-18T15:50:54+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/calesthio-openmontage","markdown_url":"https://www.graphcanon.com/tools/calesthio-openmontage.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/calesthio-openmontage","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=calesthio-openmontage","shared_categories":["ai-agents"]},{"slug":"agentscope-ai-agentscope","name":"agentscope","tagline":"Build and run agents you can see, understand and trust.","github_url":"https://github.com/agentscope-ai/agentscope","owner":"agentscope-ai","repo":"agentscope","owner_avatar_url":"https://avatars.githubusercontent.com/u/211762292?v=4","primary_language":"Python","stars":31912,"forks":3517,"topics":["agent","chatbot","large-language-models","llm","llm-agent","mcp","multi-agent","multi-modal","react-agent","realtime-agent","voice-agent","voice-assistant"],"archived":false,"github_pushed_at":"2026-09-18T07:47:31+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/agentscope-ai-agentscope","markdown_url":"https://www.graphcanon.com/tools/agentscope-ai-agentscope.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/agentscope-ai-agentscope","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=agentscope-ai-agentscope","shared_categories":["ai-agents"]},{"slug":"nirdiamant-agents-towards-production","name":"agents-towards-production","tagline":"End-to-end, code-first tutorials for building production-grade GenAI agents","github_url":"https://github.com/NirDiamant/agents-towards-production","owner":"NirDiamant","repo":"agents-towards-production","owner_avatar_url":"https://avatars.githubusercontent.com/u/28316913?v=4","primary_language":"Jupyter Notebook","stars":21298,"forks":2824,"topics":["agent","agent-framework","agentic-ai","agents","ai-agents","deployment","genai","generative-ai","langgraph","llm","llms","mcp","mlops","multi-agent-systems","observability","production","python","rag","tutorials"],"archived":false,"github_pushed_at":"2026-08-15T00:52:10+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/nirdiamant-agents-towards-production","markdown_url":"https://www.graphcanon.com/tools/nirdiamant-agents-towards-production.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nirdiamant-agents-towards-production","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nirdiamant-agents-towards-production","shared_categories":["ai-agents"]},{"slug":"raga-ai-hub-ragaai-catalyst","name":"RagaAI-Catalyst","tagline":"Python SDK for AI agent observability and evaluation","github_url":"https://github.com/raga-ai-hub/RagaAI-Catalyst","owner":"raga-ai-hub","repo":"RagaAI-Catalyst","owner_avatar_url":"https://avatars.githubusercontent.com/u/161833182?v=4","primary_language":"Python","stars":16162,"forks":3567,"topics":["agentic-ai","agentic-ai-development","agentneo","agents","ai-agent-monitoring","ai-application-debugging","ai-evaluation-tools","ai-performance-optimization","ai-tool-interaction-monitoring","llm-testing","llm-tracing","llmops"],"archived":false,"github_pushed_at":"2026-02-11T14:43:33+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/raga-ai-hub-ragaai-catalyst","markdown_url":"https://www.graphcanon.com/tools/raga-ai-hub-ragaai-catalyst.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/raga-ai-hub-ragaai-catalyst","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=raga-ai-hub-ragaai-catalyst","shared_categories":["evaluation-observability","ai-agents"]},{"slug":"alvinunreal-oh-my-opencode-slim","name":"oh-my-opencode-slim","tagline":"Lean agentic AI suite for model orchestration and task delegation","github_url":"https://github.com/alvinunreal/oh-my-opencode-slim","owner":"alvinunreal","repo":"oh-my-opencode-slim","owner_avatar_url":"https://avatars.githubusercontent.com/u/204474669?v=4","primary_language":"TypeScript","stars":8939,"forks":531,"topics":["agentic-ai","oh-my-opencode","opencode","orchestration"],"archived":false,"github_pushed_at":"2026-09-18T04:49:45+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/alvinunreal-oh-my-opencode-slim","markdown_url":"https://www.graphcanon.com/tools/alvinunreal-oh-my-opencode-slim.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alvinunreal-oh-my-opencode-slim","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alvinunreal-oh-my-opencode-slim","shared_categories":["ai-agents"]},{"slug":"agentops-ai-agentops","name":"agentops","tagline":"Python SDK for AI agent monitoring and LLM cost tracking","github_url":"https://github.com/AgentOps-AI/agentops","owner":"AgentOps-AI","repo":"agentops","owner_avatar_url":"https://avatars.githubusercontent.com/u/140554352?v=4","primary_language":"Python","stars":5830,"forks":625,"topics":["agent","agentops","agents-sdk","ai","anthropic","autogen","cost-estimation","crewai","evals","evaluation-metrics","groq","langchain","llm","mistral","ollama","openai","openai-agents"],"archived":false,"github_pushed_at":"2026-06-25T08:25:03+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/agentops-ai-agentops","markdown_url":"https://www.graphcanon.com/tools/agentops-ai-agentops.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/agentops-ai-agentops","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=agentops-ai-agentops","shared_categories":["evaluation-observability","ai-agents"]},{"slug":"evolvinglmms-lab-lmms-eval","name":"lmms-eval","tagline":"One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks","github_url":"https://github.com/EvolvingLMMs-Lab/lmms-eval","owner":"EvolvingLMMs-Lab","repo":"lmms-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/154951679?v=4","primary_language":"Python","stars":4368,"forks":639,"topics":["agi","audio-evaluation","benchmark","evaluation","large-language-models","llm-evaluation","multimodal","multimodal-evaluation","video-understanding","vision-language-model","vlm"],"archived":false,"github_pushed_at":"2026-08-06T02:22:23+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval","markdown_url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/evolvinglmms-lab-lmms-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=evolvinglmms-lab-lmms-eval","shared_categories":["evaluation-observability"]},{"slug":"future-agi-future-agi","name":"future-agi","tagline":"Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications","github_url":"https://github.com/future-agi/future-agi","owner":"future-agi","repo":"future-agi","owner_avatar_url":"https://avatars.githubusercontent.com/u/147392366?v=4","primary_language":"Python","stars":2032,"forks":627,"topics":["ai-agents","ai-evals","ai-gateway","ai-optimization","ai-simulations","evaluation-framework","guardrails","hallucination-detection","llm","llm-evaluation","llm-observability","llmops","model-evaluation","observability","opentelemetry","rag","rag-evaluation","simulation","telemetry","tracing"],"archived":false,"github_pushed_at":"2026-09-18T08:15:25+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/future-agi-future-agi","markdown_url":"https://www.graphcanon.com/tools/future-agi-future-agi.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/future-agi-future-agi","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=future-agi-future-agi","shared_categories":["evaluation-observability","ai-agents"]},{"slug":"e2b-dev-awesome-ai-sdks","name":"awesome-ai-sdks","tagline":"A database of SDKs for AI agents creation and management","github_url":"https://github.com/e2b-dev/awesome-ai-sdks","owner":"e2b-dev","repo":"awesome-ai-sdks","owner_avatar_url":"https://avatars.githubusercontent.com/u/129434473?v=4","primary_language":null,"stars":1223,"forks":399,"topics":["agent","agentops","agents","ai","ai-agents","awesome","awesome-list","chatgpt","e2b","framework","langchain","llama-index","llm","llmops","openai","sdk","tools","vercel"],"archived":false,"github_pushed_at":"2026-07-09T17:29:58+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/e2b-dev-awesome-ai-sdks","markdown_url":"https://www.graphcanon.com/tools/e2b-dev-awesome-ai-sdks.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/e2b-dev-awesome-ai-sdks","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=e2b-dev-awesome-ai-sdks","shared_categories":["ai-agents"]},{"slug":"benchflow-ai-awesome-evals","name":"awesome-evals","tagline":"A curated library of resources for building and evaluating AI agents","github_url":"https://github.com/benchflow-ai/awesome-evals","owner":"benchflow-ai","repo":"awesome-evals","owner_avatar_url":"https://avatars.githubusercontent.com/u/190338344?v=4","primary_language":null,"stars":901,"forks":104,"topics":["agent-evaluation","ai-agents","awesome","awesome-list","benchmarks","evals","llm","llm-evaluation","rl-environments"],"archived":false,"github_pushed_at":"2026-09-15T17:49:19+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/benchflow-ai-awesome-evals","markdown_url":"https://www.graphcanon.com/tools/benchflow-ai-awesome-evals.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/benchflow-ai-awesome-evals","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=benchflow-ai-awesome-evals","shared_categories":["evaluation-observability","ai-agents"]},{"slug":"haohao-end-openagent","name":"openagent","tagline":"Harness architecture for rapidly building vertical AI agents","github_url":"https://github.com/Haohao-end/openagent","owner":"Haohao-end","repo":"openagent","owner_avatar_url":"https://avatars.githubusercontent.com/u/184792454?v=4","primary_language":"Python","stars":811,"forks":82,"topics":["agent","ai","celery","deepagents","deepresearch","deepseek","docker","faiss-vector-database","flask","harness-engineering","langchain","langgraph","llmops","mcp","nginx","postgresql","skills","tailwindcss","vue","weaviate"],"archived":false,"github_pushed_at":"2026-07-17T13:36:09+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/haohao-end-openagent","markdown_url":"https://www.graphcanon.com/tools/haohao-end-openagent.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/haohao-end-openagent","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=haohao-end-openagent","shared_categories":["ai-agents"]},{"slug":"tiger-ai-lab-clawbench","name":"ClawBench","tagline":"Open-source benchmark for browser AI agents on daily tasks","github_url":"https://github.com/TIGER-AI-Lab/ClawBench","owner":"TIGER-AI-Lab","repo":"ClawBench","owner_avatar_url":"https://avatars.githubusercontent.com/u/144196744?v=4","primary_language":"Python","stars":796,"forks":58,"topics":["agent-evaluation","agentic-ai","ai-agent-benchmark","ai-agents","benchmark","browser-agent","browser-automation","browser-use","chrome-agent","chrome-extension","computer-use","dataset","evaluation","everyday-tasks","llm","llm-evaluation","online-tasks","real-world-benchmark","web-agent","web-agents"],"archived":false,"github_pushed_at":"2026-09-20T05:45:35+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/tiger-ai-lab-clawbench","markdown_url":"https://www.graphcanon.com/tools/tiger-ai-lab-clawbench.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tiger-ai-lab-clawbench","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tiger-ai-lab-clawbench","shared_categories":["evaluation-observability","ai-agents"]}]}}