Renderer for the harmony response format to be used with gpt-oss
☆4,525Apr 8, 2026Updated 6 months ago
Alternatives and similar repositories for harmony
Users that are interested in harmony are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI☆20,457Jul 24, 2026Updated 2 months ago
- slime is an LLM post-training framework for RL Scaling.☆8,632Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,988Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆93,564Updated this week
- Our library for RL environments + evals☆4,696Updated 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.
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,825Updated this week
- Lightweight coding agent that runs in your terminal☆128,647Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,860Updated this week
- Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.☆77,772Updated this week
- Kimi K2 is the large language model series developed by Moonshot AI team☆11,106Jan 21, 2026Updated 8 months ago
- Train transformer language models with reinforcement learning.☆19,489Updated this week
- A framework for few-shot evaluation of language models.☆14,187Sep 14, 2026Updated 3 weeks ago
- DSPy: The framework for programming—not prompting—language models☆38,591Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,007Sep 15, 2026Updated 3 weeks ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Fully open reproduction of DeepSeek-R1☆26,478Oct 2, 2026Updated last week
- Agentic RL Training at Scale☆2,152Updated this week
- Fast and memory-efficient exact attention☆25,115Updated this week
- Minimalistic large language model 3D-parallelism training☆2,836Updated this week
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆19,439Aug 17, 2026Updated last month
- Post-training with Tinker☆4,185Updated this week
- A lightweight, powerful framework for multi-agent workflows☆29,967Updated this week
- Structured Outputs☆15,920Sep 21, 2026Updated 2 weeks ago
- PyTorch native post-training library☆5,811Sep 9, 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.
- The best ChatGPT that $100 can buy.☆58,558Sep 7, 2026Updated last month
- Collection of scripts and notebooks for OpenAI's latest GPT OSS models☆509Aug 25, 2025Updated last year
- ☆4,658Apr 22, 2026Updated 5 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,588Updated this week
- MLX: An array framework for Apple silicon☆28,723Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,402Updated this week
- Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.☆22,048Apr 15, 2026Updated 5 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,554Updated this week
- ☆1,083Nov 4, 2025Updated 11 months ago
- 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.
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆10,792Updated this week
- Tools for merging pretrained large language models.☆7,392Sep 12, 2026Updated last month
- Minimal reproduction of DeepSeek R1-Zero☆13,249Feb 27, 2026Updated 7 months ago
- Efficient Triton Kernels for LLM Training☆6,653Updated this week
- Development repository for the Triton language and compiler☆20,347Updated this week
- AllenAI's post-training codebase☆3,891Updated this week
- LLM inference in C/C++☆130,827Updated this week