Programmable chat templates for LLM training and inference.
☆156Sep 10, 2026Updated this week
Alternatives and similar repositories for renderers
Users that are interested in renderers are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Environments by the Prime Intellect Research Team☆128Updated this week
- Ludic – an LLM-RL library for the era of experience☆67Aug 9, 2026Updated last month
- Lab Cookbook☆42Aug 5, 2026Updated last month
- ☆16Feb 22, 2026Updated 6 months ago
- MoE training for Me and You and maybe other people☆399Mar 15, 2026Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Agentic RL Training at Scale☆2,034Updated this week
- ☆27Jan 22, 2026Updated 7 months ago
- FrontierSmith, a new system that uses AI to synthesize open-ended coding problems at scale☆52May 30, 2026Updated 3 months ago
- autonomous nanogpt optimizer speedrun☆110May 14, 2026Updated 3 months ago
- Forcing Diffuse Distributions out of Language Models☆18Sep 10, 2024Updated 2 years ago
- Our library for RL environments + evals☆4,607Updated this week
- PyTorch-native post-training at scale☆702Updated this week
- ☆139Mar 20, 2025Updated last year
- Official repository for Parallax (Parameterized Local Linear Attention)☆69Jul 30, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICML 2026] Code for V1: Unifying Generation and Self-Verification for Parallel Reasoners.☆39Mar 5, 2026Updated 6 months ago
- Benchmark to measure what the real knowledge cutoff of a model is☆21Sep 2, 2026Updated last week
- Training and evaluating with OpenReward☆33Apr 28, 2026Updated 4 months ago
- ☆81Feb 18, 2026Updated 6 months ago
- ☆119Apr 7, 2026Updated 5 months ago
- peer-to-peer compute and intelligence network that enables decentralized AI development at scale☆139Nov 10, 2025Updated 10 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,295Updated this week
- Lightly-reviewed collection of community environments☆257Updated this week
- An LLM post-training framework with vLLM for RL Scaling☆458Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Scale digital agent rollouts without pain.☆36Jun 18, 2026Updated 2 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,810Updated this week
- A framework for optimizing DSPy programs with RL☆339Jan 12, 2026Updated 8 months ago
- PyTorch Single Controller☆1,076Updated this week
- ☆20May 23, 2025Updated last year
- ☆10Dec 21, 2024Updated last year
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,504Apr 17, 2026Updated 4 months ago
- Agentic RL on Any Harness at Scale☆837Aug 13, 2026Updated last month
- Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours☆554Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A minimal hackable implementation of policy gradient methods (GRPO, PPO, REINFORCE)☆17Feb 20, 2026Updated 6 months ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆432Aug 5, 2026Updated last month
- ☆39Apr 15, 2026Updated 4 months ago
- Modal-style sandbox API on top of Hugging Face Jobs☆159Jul 6, 2026Updated 2 months ago
- ☆16Updated this week
- Storing long contexts in tiny caches with self-study☆324Mar 23, 2026Updated 5 months ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆159Sep 12, 2025Updated last year