[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fCdjSdHwRYjAj-2nFHtKVgeiYR2EwCWezLF0yXWGLfNU":3},{"tool":4,"categoryPool":46},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":13,"createdAt":18,"repo":19,"articles":31,"related":45},"entity_01m1m80amye07bpxsk5akrtcjj","OpenEnv","openenv","An interface library for RL post training with environments.","https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fopenenv\u002Findex","https:\u002F\u002Fgithub.com\u002Fhuggingface\u002FOpenEnv","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fhuggingface-3e5fad40.png",true,[14],{"name":15,"slug":16,"count":17},"Post-Training","post-training",0,1788459625,{"id":20,"fullName":21,"url":10,"stars":22,"forks":23,"openIssues":24,"language":25,"license":26,"topics":27,"pushedAt":28,"archived":29,"licenseSpdx":26,"licenseOsi":12,"licenseVerifiedAt":30},"entity_01m1m80g1fe07bpxt4zt6hs79n","huggingface\u002FOpenEnv",2542,433,102,"Python","BSD-3-Clause",[],"2026-09-01T22:24:31Z",false,"2026-09-03T18:20:30.559Z",[32],{"id":33,"name":34,"slug":35,"summary":36,"url":37,"kind":38,"platform":39,"author":40,"publisher":41,"publishedAt":42,"about":43,"writtenBy":44},"entity_01m1m7wksfecs9ftpxgdxm7pjf","Training a coding model to paint watercolours with TRL and OpenEnv","training-a-coding-model-to-paint-watercolours-with-trl-and-openenv","An open reproduction of the viral watercolour-painting model: GRPO in TRL over an OpenEnv environment, with the reward split between HPSv3 and a pairwise judge scored against 178 hand-rated paintings — RL over taste.","https:\u002F\u002Fhuggingface.co\u002Fblog\u002Ftrain-to-paint-with-code","article","web","Sergio Paniego","Hugging Face","2026-09-03",[],[],[],[47,70,97,107],{"id":48,"name":49,"slug":50,"description":51,"url":52,"githubUrl":53,"logoUrl":54,"openSource":12,"categories":55,"createdAt":57,"repo":58,"articles":68,"related":69},"entity_01m0bh5ad4fztszqt82mqfptv3","Miles","miles","Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.","https:\u002F\u002Fmiles.radixark.com\u002F","https:\u002F\u002Fgithub.com\u002Fradixark\u002Fmiles","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fapple-touch-icon-e1f83c20.png",[56],{"name":15,"slug":16,"count":17},1787093494,{"id":59,"fullName":60,"url":53,"stars":61,"forks":62,"openIssues":63,"language":25,"license":64,"topics":65,"pushedAt":66,"archived":29,"licenseSpdx":64,"licenseOsi":12,"licenseVerifiedAt":67},"entity_01m0bh5fz2fztszqv64369avxx","radixark\u002Fmiles",2431,435,1195,"Apache-2.0",[],"2026-09-03T19:05:59Z","2026-08-18T22:51:39.779Z",[],[],{"id":71,"name":72,"slug":73,"description":74,"url":75,"githubUrl":75,"logoUrl":76,"openSource":12,"categories":77,"createdAt":79,"repo":80,"company":89,"articles":95,"related":96},"entity_01kyjhhkh2eh0v8dwkexzpmgmj","Molt","molt","An agentic-first RL framework for research. Ray · vLLM · NVIDIA AutoModel — the smallest PyTorch-native stack for 1T-class fully-async, multimodal, multi-turn agentic RL.","https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002Flabs-molt","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002FNVIDIA-NeMo-dd56beca.png",[78],{"name":15,"slug":16,"count":17},1785181294,{"id":81,"fullName":82,"url":75,"stars":83,"forks":84,"openIssues":85,"language":25,"license":64,"topics":86,"pushedAt":87,"archived":29,"licenseSpdx":64,"licenseOsi":12,"licenseVerifiedAt":88},"entity_01kyjhhp1weh0v8dxn62dj8kz5","NVIDIA-NeMo\u002Flabs-molt",1012,98,18,[],"2026-09-02T00:33:31Z","2026-08-09",{"id":90,"name":91,"slug":92,"url":93,"bio":94,"githubOrg":91},"entity_01kzrxjf0ze8h9epsbfe0560wm","NVIDIA","nvidia","https:\u002F\u002Fwww.nvidia.com","NVIDIA invents the GPU and drives advances in AI, HPC, gaming, creative design, autonomous vehicles, and robotics.",[],[],{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":10,"logoUrl":11,"openSource":12,"categories":98,"createdAt":18,"repo":100,"articles":102,"related":106},[99],{"name":15,"slug":16,"count":17},{"id":20,"fullName":21,"url":10,"stars":22,"forks":23,"openIssues":24,"language":25,"license":26,"topics":101,"pushedAt":28,"archived":29,"licenseSpdx":26,"licenseOsi":12,"licenseVerifiedAt":30},[],[103],{"id":33,"name":34,"slug":35,"summary":36,"url":37,"kind":38,"platform":39,"author":40,"publisher":41,"publishedAt":42,"about":104,"writtenBy":105},[],[],[],{"id":108,"name":109,"slug":110,"description":111,"url":112,"githubUrl":112,"logoUrl":113,"openSource":12,"categories":114,"createdAt":116,"repo":117,"company":125,"articles":131,"related":132},"entity_01kyjv3cm1fzvt3avvgastqaax","PorTAL","portal","PorTAL generates portable task specific LoRA adapters that can efficiently transfer across language models.","https:\u002F\u002Fgithub.com\u002Framp-public\u002Fportallib","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Framp-public-076e634e.png",[115],{"name":15,"slug":16,"count":17},1785191314,{"id":118,"fullName":119,"url":112,"stars":120,"forks":121,"openIssues":122,"language":25,"license":64,"topics":123,"pushedAt":124,"archived":29,"licenseSpdx":64,"licenseOsi":12,"licenseVerifiedAt":88},"entity_01kyjv3g1cf25sc697f5q4syj2","ramp-public\u002Fportallib",118,7,4,[],"2026-07-27T21:38:51Z",{"id":126,"name":127,"slug":128,"url":129,"githubOrg":130},"entity_01kzmf00gwe8krkm7xkvnn42dn","Ramp","ramp","https:\u002F\u002Framp.com\u002F","ramp-public",[],[]]