{"data":{"node":{"slug":"alibaba-roll","name":"ROLL","tagline":"Scaling Library for Reinforcement Learning with Large Language Models","github_url":"https://github.com/alibaba/ROLL","owner":"alibaba","repo":"ROLL","owner_avatar_url":"https://avatars.githubusercontent.com/u/1961952?v=4","primary_language":"Python","stars":3383,"forks":311,"topics":["agentic","rlhf","rlvr"],"archived":false,"github_pushed_at":"2026-09-06T01:30:14+00:00","maintenance_label":"Very active","stars_delta_30d":29,"url":"https://www.graphcanon.com/tools/alibaba-roll","markdown_url":"https://www.graphcanon.com/tools/alibaba-roll.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alibaba-roll","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alibaba-roll"},"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"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"agentic","name":"agentic"},{"slug":"rlhf","name":"rlhf"},{"slug":"rlvr","name":"rlvr"}],"edges":[],"neighbours":[{"slug":"huggingface-open-r1","name":"open-r1","tagline":"Fully open reproduction of DeepSeek-R1","github_url":"https://github.com/huggingface/open-r1","owner":"huggingface","repo":"open-r1","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":26477,"forks":2452,"topics":[],"archived":false,"github_pushed_at":"2026-10-02T03:57:56+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-open-r1","markdown_url":"https://www.graphcanon.com/tools/huggingface-open-r1.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-open-r1","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-open-r1","shared_categories":["model-training"]},{"slug":"huggingface-trl","name":"trl","tagline":"Train transformer language models with reinforcement learning","github_url":"https://github.com/huggingface/trl","owner":"huggingface","repo":"trl","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":19336,"forks":3002,"topics":[],"archived":false,"github_pushed_at":"2026-09-18T06:20:19+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-trl","markdown_url":"https://www.graphcanon.com/tools/huggingface-trl.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-trl","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-trl","shared_categories":["model-training"]},{"slug":"0xplaygrounds-rig","name":"rig","tagline":"Build modular and scalable LLM Applications in Rust","github_url":"https://github.com/0xPlaygrounds/rig","owner":"0xPlaygrounds","repo":"rig","owner_avatar_url":"https://avatars.githubusercontent.com/u/93353392?v=4","primary_language":"Rust","stars":8679,"forks":974,"topics":["agent","ai","artificial-intelligence","automation","generative-ai","large-language-model","llm","llmops","rust","scalable-ai"],"archived":false,"github_pushed_at":"2026-09-19T23:48:13+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/0xplaygrounds-rig","markdown_url":"https://www.graphcanon.com/tools/0xplaygrounds-rig.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/0xplaygrounds-rig","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=0xplaygrounds-rig","shared_categories":[]},{"slug":"woooodyy-llm-agent-paper-list","name":"LLM-Agent-Paper-List","tagline":"Must-read papers for LLM-based agents.","github_url":"https://github.com/WooooDyy/LLM-Agent-Paper-List","owner":"WooooDyy","repo":"LLM-Agent-Paper-List","owner_avatar_url":"https://avatars.githubusercontent.com/u/48242229?v=4","primary_language":null,"stars":8222,"forks":499,"topics":["agent","large-language-models","llm","nlp","survey"],"archived":false,"github_pushed_at":"2025-09-12T03:08:58+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/woooodyy-llm-agent-paper-list","markdown_url":"https://www.graphcanon.com/tools/woooodyy-llm-agent-paper-list.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/woooodyy-llm-agent-paper-list","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=woooodyy-llm-agent-paper-list","shared_categories":["model-training","evaluation-observability"]},{"slug":"flashinfer-ai-flashinfer","name":"flashinfer","tagline":"FlashInfer is a kernel library for serving large language models","github_url":"https://github.com/flashinfer-ai/flashinfer","owner":"flashinfer-ai","repo":"flashinfer","owner_avatar_url":"https://avatars.githubusercontent.com/u/145061914?v=4","primary_language":"Cuda","stars":6452,"forks":1472,"topics":["attention","cuda","distributed-inference","gpu","jit","large-large-models","llm-inference","moe","nvidia","pytorch"],"archived":false,"github_pushed_at":"2026-09-19T01:31:07+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/flashinfer-ai-flashinfer","markdown_url":"https://www.graphcanon.com/tools/flashinfer-ai-flashinfer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/flashinfer-ai-flashinfer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=flashinfer-ai-flashinfer","shared_categories":[]},{"slug":"opendilab-awesome-rlhf","name":"awesome-RLHF","tagline":"A curated list of reinforcement learning with human feedback resources (continually updated)","github_url":"https://github.com/opendilab/awesome-RLHF","owner":"opendilab","repo":"awesome-RLHF","owner_avatar_url":"https://avatars.githubusercontent.com/u/86840398?v=4","primary_language":null,"stars":4422,"forks":258,"topics":["deep-learning","deep-reinforcement-learning","human-feedback","large-language-models","reinforcement-learning","rlhf"],"archived":false,"github_pushed_at":"2026-05-20T12:56:15+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/opendilab-awesome-rlhf","markdown_url":"https://www.graphcanon.com/tools/opendilab-awesome-rlhf.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/opendilab-awesome-rlhf","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=opendilab-awesome-rlhf","shared_categories":["model-training","evaluation-observability"]},{"slug":"eth-sri-lmql","name":"lmql","tagline":"A language for constraint-guided and efficient LLM programming.","github_url":"https://github.com/eth-sri/lmql","owner":"eth-sri","repo":"lmql","owner_avatar_url":"https://avatars.githubusercontent.com/u/5363413?v=4","primary_language":"Python","stars":4203,"forks":221,"topics":["chatgpt","huggingface","language-model","programming-language"],"archived":false,"github_pushed_at":"2025-05-22T07:32:31+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/eth-sri-lmql","markdown_url":"https://www.graphcanon.com/tools/eth-sri-lmql.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eth-sri-lmql","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eth-sri-lmql","shared_categories":[]},{"slug":"fasterdecoding-medusa","name":"Medusa","tagline":"Framework for accelerating LLM generation using multiple decoding heads","github_url":"https://github.com/FasterDecoding/Medusa","owner":"FasterDecoding","repo":"Medusa","owner_avatar_url":"https://avatars.githubusercontent.com/u/144572371?v=4","primary_language":"Jupyter Notebook","stars":2773,"forks":205,"topics":["llm","llm-inference"],"archived":false,"github_pushed_at":"2024-06-25T12:23:04+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/fasterdecoding-medusa","markdown_url":"https://www.graphcanon.com/tools/fasterdecoding-medusa.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fasterdecoding-medusa","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fasterdecoding-medusa","shared_categories":[]},{"slug":"internlm-lagent","name":"lagent","tagline":"A lightweight framework for building LLM-based agents","github_url":"https://github.com/InternLM/lagent","owner":"InternLM","repo":"lagent","owner_avatar_url":"https://avatars.githubusercontent.com/u/135356492?v=4","primary_language":"Python","stars":2276,"forks":238,"topics":["agent","gpt","llm","transformers"],"archived":false,"github_pushed_at":"2026-08-03T07:18:16+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/internlm-lagent","markdown_url":"https://www.graphcanon.com/tools/internlm-lagent.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/internlm-lagent","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=internlm-lagent","shared_categories":[]},{"slug":"jax-ml-scaling-book","name":"scaling-book","tagline":"Guide on scaling LLMs on TPUs","github_url":"https://github.com/jax-ml/scaling-book","owner":"jax-ml","repo":"scaling-book","owner_avatar_url":"https://avatars.githubusercontent.com/u/58486408?v=4","primary_language":"HTML","stars":1441,"forks":205,"topics":["jax","llm-inference","llms","roofline","tpus"],"archived":false,"github_pushed_at":"2026-09-19T16:14:09+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/jax-ml-scaling-book","markdown_url":"https://www.graphcanon.com/tools/jax-ml-scaling-book.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jax-ml-scaling-book","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jax-ml-scaling-book","shared_categories":[]},{"slug":"agi-arena-mars","name":"MARS","tagline":"Advanced optimizer for variance reduction in large model training.","github_url":"https://github.com/AGI-Arena/MARS","owner":"AGI-Arena","repo":"MARS","owner_avatar_url":"https://avatars.githubusercontent.com/u/188802235?v=4","primary_language":"Python","stars":722,"forks":48,"topics":["fine-tuning","large-language-models","optimization-algorithms","optimizer","pretraining"],"archived":false,"github_pushed_at":"2026-03-26T05:08:16+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/agi-arena-mars","markdown_url":"https://www.graphcanon.com/tools/agi-arena-mars.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/agi-arena-mars","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=agi-arena-mars","shared_categories":["model-training"]},{"slug":"salesforce-coderl","name":"CodeRL","tagline":"CodeRL: Combines pretrained models and reinforcement learning for code generation.","github_url":"https://github.com/salesforce/CodeRL","owner":"salesforce","repo":"CodeRL","owner_avatar_url":"https://avatars.githubusercontent.com/u/453694?v=4","primary_language":"Python","stars":576,"forks":69,"topics":["ai","codegeneration","languagemodel","machinelearning","programsynthesis","reinforcementlearning"],"archived":false,"github_pushed_at":"2026-06-02T18:14:33+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/salesforce-coderl","markdown_url":"https://www.graphcanon.com/tools/salesforce-coderl.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/salesforce-coderl","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=salesforce-coderl","shared_categories":["model-training"]}]}}