{"data":{"node":{"slug":"re-align-just-eval","name":"just-eval","tagline":"A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.","github_url":"https://github.com/Re-Align/just-eval","owner":"Re-Align","repo":"just-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/150300417?v=4","primary_language":"Python","stars":90,"forks":7,"topics":["evaluation","gpt4","llm","llm-eval","llm-evaluation","llm-evaluation-toolkit"],"archived":false,"github_pushed_at":"2024-01-29T23:45:40+00:00","maintenance_label":"Dormant","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/re-align-just-eval","markdown_url":"https://www.graphcanon.com/tools/re-align-just-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/re-align-just-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=re-align-just-eval"},"categories":[{"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":"evaluation","name":"evaluation"},{"slug":"gpt4","name":"gpt4"},{"slug":"llm","name":"llm"},{"slug":"llm-eval","name":"llm-eval"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"llm-evaluation-toolkit","name":"llm-evaluation-toolkit"}],"edges":[],"neighbours":[{"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":"Very 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":"confident-ai-deepeval","name":"deepeval","tagline":"LLM Evaluation Framework.","github_url":"https://github.com/confident-ai/deepeval","owner":"confident-ai","repo":"deepeval","owner_avatar_url":"https://avatars.githubusercontent.com/u/130858411?v=4","primary_language":"Python","stars":18342,"forks":1953,"topics":["evaluation-framework","evaluation-metrics","llm-evaluation","llm-evaluation-framework","llm-evaluation-metrics","python"],"archived":false,"github_pushed_at":"2026-09-18T17:06:58+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/confident-ai-deepeval","markdown_url":"https://www.graphcanon.com/tools/confident-ai-deepeval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/confident-ai-deepeval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=confident-ai-deepeval","shared_categories":["evaluation-observability"]},{"slug":"eleutherai-lm-evaluation-harness","name":"lm-evaluation-harness","tagline":"A framework for few-shot evaluation of language models.","github_url":"https://github.com/EleutherAI/lm-evaluation-harness","owner":"EleutherAI","repo":"lm-evaluation-harness","owner_avatar_url":"https://avatars.githubusercontent.com/u/68924597?v=4","primary_language":"Python","stars":13906,"forks":3547,"topics":["evaluation-framework","language-model","transformer"],"archived":false,"github_pushed_at":"2026-09-01T13:51:29+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/eleutherai-lm-evaluation-harness","markdown_url":"https://www.graphcanon.com/tools/eleutherai-lm-evaluation-harness.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eleutherai-lm-evaluation-harness","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eleutherai-lm-evaluation-harness","shared_categories":["evaluation-observability"]},{"slug":"oumi-ai-oumi","name":"oumi","tagline":"Easily fine-tune, evaluate and deploy open source LLMs/VLMs","github_url":"https://github.com/oumi-ai/oumi","owner":"oumi-ai","repo":"oumi","owner_avatar_url":"https://avatars.githubusercontent.com/u/167452922?v=4","primary_language":"Python","stars":9387,"forks":790,"topics":["dpo","evaluation","fine-tuning","gpt-oss","gpt-oss-120b","gpt-oss-20b","inference","llama","llms","open-weight","open-weight-models","open-weights","sft","slms","vlms"],"archived":false,"github_pushed_at":"2026-09-20T05:45:37+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/oumi-ai-oumi","markdown_url":"https://www.graphcanon.com/tools/oumi-ai-oumi.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/oumi-ai-oumi","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=oumi-ai-oumi","shared_categories":["evaluation-observability"]},{"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":"hegelai-prompttools","name":"prompttools","tagline":"Open-source tools for prompt testing and experimentation","github_url":"https://github.com/hegelai/prompttools","owner":"hegelai","repo":"prompttools","owner_avatar_url":"https://avatars.githubusercontent.com/u/136523567?v=4","primary_language":"Python","stars":3055,"forks":256,"topics":["deep-learning","developer-tools","embeddings","large-language-models","llms","machine-learning","prompt-engineering","python","vector-search"],"archived":false,"github_pushed_at":"2026-02-11T03:24:04+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/hegelai-prompttools","markdown_url":"https://www.graphcanon.com/tools/hegelai-prompttools.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hegelai-prompttools","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hegelai-prompttools","shared_categories":[]},{"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"]},{"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"]},{"slug":"curated-awesome-lists-awesome-llms-fine-tuning","name":"awesome-llms-fine-tuning","tagline":"A comprehensive collection of resources for fine-tuning Large Language Models.","github_url":"https://github.com/Curated-Awesome-Lists/awesome-llms-fine-tuning","owner":"Curated-Awesome-Lists","repo":"awesome-llms-fine-tuning","owner_avatar_url":"https://avatars.githubusercontent.com/u/142611331?v=4","primary_language":null,"stars":527,"forks":80,"topics":["ai","awesome-list","deep-learning","fine-tuning","gpt","large-language-models","llms","machine-learning","nlp","transformers"],"archived":false,"github_pushed_at":"2026-09-04T19:22:27+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/curated-awesome-lists-awesome-llms-fine-tuning","markdown_url":"https://www.graphcanon.com/tools/curated-awesome-lists-awesome-llms-fine-tuning.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/curated-awesome-lists-awesome-llms-fine-tuning","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=curated-awesome-lists-awesome-llms-fine-tuning","shared_categories":[]},{"slug":"jonathanchaveztamales-llm-leaderboard","name":"llm-leaderboard","tagline":"Comprehensive LLM benchmark scores and provider prices","github_url":"https://github.com/JonathanChavezTamales/llm-leaderboard","owner":"JonathanChavezTamales","repo":"llm-leaderboard","owner_avatar_url":"https://avatars.githubusercontent.com/u/22694942?v=4","primary_language":"JavaScript","stars":356,"forks":40,"topics":["llm","llm-agents","llm-evaluation","llmops","llms-benchmarking"],"archived":false,"github_pushed_at":"2025-10-24T17:47:59+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/jonathanchaveztamales-llm-leaderboard","markdown_url":"https://www.graphcanon.com/tools/jonathanchaveztamales-llm-leaderboard.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jonathanchaveztamales-llm-leaderboard","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jonathanchaveztamales-llm-leaderboard","shared_categories":["evaluation-observability"]},{"slug":"verifywise-ai-verifywise","name":"verifywise","tagline":"Complete AI governance and LLM Evals platform","github_url":"https://github.com/verifywise-ai/verifywise","owner":"verifywise-ai","repo":"verifywise","owner_avatar_url":"https://avatars.githubusercontent.com/u/262239808?v=4","primary_language":"TypeScript","stars":354,"forks":117,"topics":["ai","ai-auditing","ai-compliance","ai-governance","ai-governance-model","ai-risk","audit","auditing","compliance","eu-ai-act","governance","grc","iso27001","iso42001","llm-eval","llm-evaluation","nist-ai-rmf","risk-management"],"archived":false,"github_pushed_at":"2026-09-19T19:03:23+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/verifywise-ai-verifywise","markdown_url":"https://www.graphcanon.com/tools/verifywise-ai-verifywise.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/verifywise-ai-verifywise","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=verifywise-ai-verifywise","shared_categories":["evaluation-observability"]},{"slug":"athina-ai-athina-evals","name":"athina-evals","tagline":"Python SDK for evaluating LLM generated responses","github_url":"https://github.com/athina-ai/athina-evals","owner":"athina-ai","repo":"athina-evals","owner_avatar_url":"https://avatars.githubusercontent.com/u/139258696?v=4","primary_language":"Python","stars":301,"forks":22,"topics":["evaluation","evaluation-framework","evaluation-metrics","llm-eval","llm-evaluation","llm-evaluation-toolkit","llm-ops","llmops"],"archived":false,"github_pushed_at":"2025-06-06T15:54:38+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/athina-ai-athina-evals","markdown_url":"https://www.graphcanon.com/tools/athina-ai-athina-evals.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/athina-ai-athina-evals","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=athina-ai-athina-evals","shared_categories":["evaluation-observability"]}]}}