{"data":{"node":{"slug":"hidai25-eval-view","name":"eval-view","tagline":"Regression testing for AI agents, snapshots behavior, diffs tool calls, catches regressions in CI","github_url":"https://github.com/hidai25/eval-view","owner":"hidai25","repo":"eval-view","owner_avatar_url":"https://avatars.githubusercontent.com/u/31502796?v=4","primary_language":"Python","stars":134,"forks":24,"topics":["agent-benchmark","agent-evaluation","agentic-ai","ai-agents","anthropic","autogen","cli","crewai","evaluation","langchain-agent","langgraph","llm","mcp","openai-assistants","pytest","python","regression-testing","testing"],"archived":false,"github_pushed_at":"2026-09-05T03:28:43+00:00","maintenance_label":"Active","stars_delta_30d":8,"url":"https://www.graphcanon.com/tools/hidai25-eval-view","markdown_url":"https://www.graphcanon.com/tools/hidai25-eval-view.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hidai25-eval-view","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hidai25-eval-view"},"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":"agent-benchmark","name":"agent-benchmark"},{"slug":"agent-evaluation","name":"agent-evaluation"},{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"anthropic","name":"anthropic"},{"slug":"autogen","name":"autogen"},{"slug":"cli","name":"cli"},{"slug":"crewai","name":"crewai"}],"edges":[],"neighbours":[{"slug":"mintplex-labs-anything-llm","name":"anything-llm","tagline":"Self-hosted AI agent experience","github_url":"https://github.com/Mintplex-Labs/anything-llm","owner":"Mintplex-Labs","repo":"anything-llm","owner_avatar_url":"https://avatars.githubusercontent.com/u/134426827?v=4","primary_language":"JavaScript","stars":66167,"forks":7349,"topics":["agent-computer","agent-harness","agent-orchestration","agentic-ai","agentic-workflow","ai-agents","computer-use","hermes-agent","llm","local-ai","localai","multimodal","rag","self-hosted-ai","vector-database"],"archived":false,"github_pushed_at":"2026-09-17T23:23:19+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/mintplex-labs-anything-llm","markdown_url":"https://www.graphcanon.com/tools/mintplex-labs-anything-llm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mintplex-labs-anything-llm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mintplex-labs-anything-llm","shared_categories":["ai-agents"]},{"slug":"patchy631-ai-engineering-hub","name":"ai-engineering-hub","tagline":"Tutorials on LLMs, RAGs, and real-world AI agent applications","github_url":"https://github.com/patchy631/ai-engineering-hub","owner":"patchy631","repo":"ai-engineering-hub","owner_avatar_url":"https://avatars.githubusercontent.com/u/38653995?v=4","primary_language":"Jupyter Notebook","stars":37020,"forks":6107,"topics":["agents","ai","llms","machine-learning","mcp","rag"],"archived":false,"github_pushed_at":"2026-07-27T18:43:06+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/patchy631-ai-engineering-hub","markdown_url":"https://www.graphcanon.com/tools/patchy631-ai-engineering-hub.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/patchy631-ai-engineering-hub","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=patchy631-ai-engineering-hub","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":"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":"promptfoo-promptfoo","name":"promptfoo","tagline":"Test prompts, agents, and RAGs. Compare performance of various LLMs.","github_url":"https://github.com/promptfoo/promptfoo","owner":"promptfoo","repo":"promptfoo","owner_avatar_url":"https://avatars.githubusercontent.com/u/137907881?v=4","primary_language":"TypeScript","stars":25251,"forks":2334,"topics":["ci","ci-cd","cicd","evaluation","evaluation-framework","llm","llm-eval","llm-evaluation","llm-evaluation-framework","llmops","pentesting","prompt-engineering","prompt-testing","prompts","rag","red-teaming","testing","vulnerability-scanners"],"archived":false,"github_pushed_at":"2026-09-18T07:59:45+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/promptfoo-promptfoo","markdown_url":"https://www.graphcanon.com/tools/promptfoo-promptfoo.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/promptfoo-promptfoo","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=promptfoo-promptfoo","shared_categories":["evaluation-observability"]},{"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":"microsoft-agent-framework","name":"agent-framework","tagline":"Framework for building and deploying AI agents and multi-agent workflows","github_url":"https://github.com/microsoft/agent-framework","owner":"microsoft","repo":"agent-framework","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"Python","stars":13573,"forks":2335,"topics":["agent-framework","agentic-ai","agents","ai","dotnet","multi-agent","orchestration","python","sdk","workflows"],"archived":false,"github_pushed_at":"2026-09-18T02:54:16+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/microsoft-agent-framework","markdown_url":"https://www.graphcanon.com/tools/microsoft-agent-framework.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-agent-framework","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-agent-framework","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":"Slowing","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":"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":"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":"Slowing","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":"pguso-agents-from-scratch","name":"agents-from-scratch","tagline":"Build AI agents locally without relying on frameworks or cloud APIs.","github_url":"https://github.com/pguso/agents-from-scratch","owner":"pguso","repo":"agents-from-scratch","owner_avatar_url":"https://avatars.githubusercontent.com/u/4007140?v=4","primary_language":"Python","stars":1017,"forks":251,"topics":["agent-architecture","ai-agents","ai-education","ai-from-scratch","artificial-intelligence","llama","llm","local-llm","machine-learning","no-framework","open-source-education","prompt-engineering","python"],"archived":false,"github_pushed_at":"2026-07-25T15:42:36+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/pguso-agents-from-scratch","markdown_url":"https://www.graphcanon.com/tools/pguso-agents-from-scratch.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pguso-agents-from-scratch","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pguso-agents-from-scratch","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":"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":"declare-lab-instruct-eval","name":"instruct-eval","tagline":"Quantitative evaluation for instruction-tuned language models","github_url":"https://github.com/declare-lab/instruct-eval","owner":"declare-lab","repo":"instruct-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/59164695?v=4","primary_language":"Python","stars":553,"forks":45,"topics":["instruct-tuning","llm"],"archived":false,"github_pushed_at":"2024-03-10T05:00:00+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/declare-lab-instruct-eval","markdown_url":"https://www.graphcanon.com/tools/declare-lab-instruct-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/declare-lab-instruct-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=declare-lab-instruct-eval","shared_categories":["evaluation-observability"]}]}}