Renderer for the harmony response format to be used with gpt-oss
☆4,505Apr 8, 2026Updated 5 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☆20,420Jul 24, 2026Updated last month
- slime is an LLM post-training framework for RL Scaling.☆8,509Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,212Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆92,241Updated this week
- Our library for RL environments + evals☆4,635Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,503Updated this week
- Lightweight coding agent that runs in your terminal☆125,491Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,829Sep 12, 2026Updated last 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.☆76,481Updated this week
- Kimi K2 is the large language model series developed by Moonshot AI team☆11,118Jan 21, 2026Updated 8 months ago
- Train transformer language models with reinforcement learning.☆19,347Updated this week
- A framework for few-shot evaluation of language models.☆14,035Updated this week
- DSPy: The framework for programming—not prompting—language models☆38,161Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,004Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Fully open reproduction of DeepSeek-R1☆26,478Apr 2, 2026Updated 5 months ago
- Agentic RL Training at Scale☆2,059Updated this week
- Fast and memory-efficient exact attention☆24,984Updated this week
- Minimalistic large language model 3D-parallelism training☆2,825Updated this week
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆19,289Aug 17, 2026Updated last month
- Post-training with Tinker☆4,136Updated this week
- A lightweight, powerful framework for multi-agent workflows☆29,580Updated this week
- Structured Outputs☆15,843Updated this week
- The best ChatGPT that $100 can buy.☆58,164Sep 7, 2026Updated last 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.
- PyTorch native post-training library☆5,812Sep 9, 2026Updated last week
- Collection of scripts and notebooks for OpenAI's latest GPT OSS models☆507Aug 25, 2025Updated last year
- ☆4,637Apr 22, 2026Updated 4 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,460Updated this week
- MLX: An array framework for Apple silicon☆28,497Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,334Updated this week
- Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.☆21,995Apr 15, 2026Updated 5 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,547Updated this week
- ☆1,078Nov 4, 2025Updated 10 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆10,761Updated this week
- Tools for merging pretrained large language models.☆7,363Sep 12, 2026Updated last week
- Minimal reproduction of DeepSeek R1-Zero☆13,238Feb 27, 2026Updated 6 months ago
- Efficient Triton Kernels for LLM Training☆6,620Updated this week
- Development repository for the Triton language and compiler☆20,208Updated this week
- AllenAI's post-training codebase☆3,874Updated this week
- LLM inference in C/C++☆128,939Updated this week