{"data":{"node":{"slug":"allenai-olmo-eval","name":"olmo-eval","tagline":"Olmo Evaluation Framework for LLM Tasks","github_url":"https://github.com/allenai/olmo-eval","owner":"allenai","repo":"olmo-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/5667695?v=4","primary_language":"Python","stars":72,"forks":23,"topics":[],"archived":false,"github_pushed_at":"2026-10-11T15:38:57+00:00","maintenance_label":"Very active","stars_delta_30d":3,"url":"https://www.graphcanon.com/tools/allenai-olmo-eval","markdown_url":"https://www.graphcanon.com/tools/allenai-olmo-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/allenai-olmo-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=allenai-olmo-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":"datasets","name":"datasets"},{"slug":"evaluation","name":"evaluation"},{"slug":"llm","name":"llm"},{"slug":"python","name":"python"},{"slug":"tasks","name":"tasks"},{"slug":"uv","name":"uv"}],"edges":[],"neighbours":[{"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":"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":14192,"forks":3664,"topics":["evaluation-framework","language-model","transformer"],"archived":false,"github_pushed_at":"2026-09-14T10:51:06+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":"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":"andyyyy64-whichllm","name":"whichllm","tagline":"Command-line tool to find and benchmark local LLM performance","github_url":"https://github.com/Andyyyy64/whichllm","owner":"Andyyyy64","repo":"whichllm","owner_avatar_url":"https://avatars.githubusercontent.com/u/105579829?v=4","primary_language":"Python","stars":6666,"forks":368,"topics":["localllm"],"archived":false,"github_pushed_at":"2026-09-19T16:22:49+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/andyyyy64-whichllm","markdown_url":"https://www.graphcanon.com/tools/andyyyy64-whichllm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/andyyyy64-whichllm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=andyyyy64-whichllm","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":"stochasticai-xturing","name":"xTuring","tagline":"Build, personalize and control your own LLMs","github_url":"https://github.com/stochasticai/xTuring","owner":"stochasticai","repo":"xTuring","owner_avatar_url":"https://avatars.githubusercontent.com/u/66399337?v=4","primary_language":"Python","stars":2674,"forks":211,"topics":["adapter","deep-learning","fine-tuning","finetuning","gen-ai","generative-ai","gpt-2","gpt-j","language-model","llama","llm","lora","mistral","mixed-precision","peft","quantization"],"archived":false,"github_pushed_at":"2026-09-12T23:50:56+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/stochasticai-xturing","markdown_url":"https://www.graphcanon.com/tools/stochasticai-xturing.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/stochasticai-xturing","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=stochasticai-xturing","shared_categories":[]},{"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"]},{"slug":"georgian-io-llm-finetuning-toolkit","name":"LLM-Finetuning-Toolkit","tagline":"Toolkit for fine-tuning and testing open-source large language models","github_url":"https://github.com/georgian-io/LLM-Finetuning-Toolkit","owner":"georgian-io","repo":"LLM-Finetuning-Toolkit","owner_avatar_url":"https://avatars.githubusercontent.com/u/10764713?v=4","primary_language":"Python","stars":870,"forks":107,"topics":["ablation-study","classification","falcon","fine-tuning","finetuning","flan-t5","large-language-models","llama2","llm-test","lora","mistral-7b","nlp","nlp-machine-learning","qlora","redpajama","summarization","unit-testing","zephyr"],"archived":false,"github_pushed_at":"2026-05-04T16:33:40+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit","markdown_url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/georgian-io-llm-finetuning-toolkit","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=georgian-io-llm-finetuning-toolkit","shared_categories":[]},{"slug":"openinfer-project-openinfer","name":"openinfer","tagline":"Pure Rust CUDA LLM inference engine serving multiple models including Qwen3 and Kimi-K2","github_url":"https://github.com/openinfer-project/openinfer","owner":"openinfer-project","repo":"openinfer","owner_avatar_url":"https://avatars.githubusercontent.com/u/292134277?v=4","primary_language":"Rust","stars":705,"forks":107,"topics":["cuda","cuda-kernels","deepseek","gpu","inference","inference-engine","kimi","kimi-k2","kv-cache","llm","llm-inference","llm-serving","model-serving","moe","openai-api","paged-attention","qwen","qwen3","rust","vllm"],"archived":false,"github_pushed_at":"2026-09-18T17:57:56+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/openinfer-project-openinfer","markdown_url":"https://www.graphcanon.com/tools/openinfer-project-openinfer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openinfer-project-openinfer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openinfer-project-openinfer","shared_categories":[]},{"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":"Steady","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"]}]}}