{"data":{"node":{"slug":"judgmentlabs-judgeval","name":"judgeval","tagline":"The Continuous-Improvement Stack for Agents","github_url":"https://github.com/JudgmentLabs/judgeval","owner":"JudgmentLabs","repo":"judgeval","owner_avatar_url":"https://avatars.githubusercontent.com/u/186249420?v=4","primary_language":"Python","stars":1047,"forks":95,"topics":["agent","agentic-ai","agents","grpo","langchain","langgraph","llama-index","llm","llm-evaluation","llm-observability","open-source","openai","prompt-engineering","reinforcement-learning","rl"],"archived":false,"github_pushed_at":"2026-07-27T00:46:56+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/judgmentlabs-judgeval","markdown_url":"https://www.graphcanon.com/tools/judgmentlabs-judgeval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/judgmentlabs-judgeval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=judgmentlabs-judgeval"},"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","name":"agent"},{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"agents","name":"agents"},{"slug":"grpo","name":"grpo"},{"slug":"langchain","name":"langchain"},{"slug":"llamaindex","name":"llamaindex"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"open-source","name":"open-source"}],"edges":[],"neighbours":[{"slug":"openai-evals","name":"evals","tagline":"Framework for evaluating LLMs and LLM systems with an open-source registry of benchmarks.","github_url":"https://github.com/openai/evals","owner":"openai","repo":"evals","owner_avatar_url":"https://avatars.githubusercontent.com/u/14957082?v=4","primary_language":"Python","stars":19127,"forks":3050,"topics":[],"archived":false,"github_pushed_at":"2026-04-14T15:29:57+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/openai-evals","markdown_url":"https://www.graphcanon.com/tools/openai-evals.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openai-evals","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openai-evals","shared_categories":["evaluation-observability"]},{"slug":"ethz-spylab-agentdojo","name":"agentdojo","tagline":"A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","github_url":"https://github.com/ethz-spylab/agentdojo","owner":"ethz-spylab","repo":"agentdojo","owner_avatar_url":"https://avatars.githubusercontent.com/u/106388551?v=4","primary_language":"Python","stars":716,"forks":188,"topics":["benchmark","large-language-models","prompt-injection","security"],"archived":false,"github_pushed_at":"2026-06-02T10:01:31+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/ethz-spylab-agentdojo","markdown_url":"https://www.graphcanon.com/tools/ethz-spylab-agentdojo.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ethz-spylab-agentdojo","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ethz-spylab-agentdojo","shared_categories":["evaluation-observability","ai-agents"]},{"slug":"relari-ai-continuous-eval","name":"continuous-eval","tagline":"Data-Driven Evaluation for LLM-Powered Applications","github_url":"https://github.com/relari-ai/continuous-eval","owner":"relari-ai","repo":"continuous-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/135984758?v=4","primary_language":"Python","stars":515,"forks":38,"topics":["evaluation-framework","evaluation-metrics","information-retrieval","llm-evaluation","llmops","rag","retrieval-augmented-generation"],"archived":false,"github_pushed_at":"2026-08-10T22:12:03+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/relari-ai-continuous-eval","markdown_url":"https://www.graphcanon.com/tools/relari-ai-continuous-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/relari-ai-continuous-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=relari-ai-continuous-eval","shared_categories":["evaluation-observability"]}]}}