openai / harmonyLinks
Renderer for the harmony response format to be used with gpt-oss
☆4,171Updated last month
Alternatives and similar repositories for harmony
Users that are interested in harmony are comparing it to the libraries listed below
Sorting:
- Our library for RL environments + evals☆3,809Updated this week
- The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—b…☆2,726Updated this week
- OpenAI Frontier Evals☆994Updated 2 months ago
- ☆2,577Updated this week
- Post-training with Tinker☆2,805Updated this week
- This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software E…☆1,439Updated 6 months ago
- A benchmark for LLMs on complicated tasks in the terminal☆1,494Updated 2 weeks ago
- Democratizing Reinforcement Learning for LLMs☆5,081Updated this week
- Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, im…☆3,399Updated last month
- Kimi K2 is the large language model series developed by Moonshot AI team☆10,257Updated 2 weeks ago
- MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.☆3,075Updated 7 months ago
- Sky-T1: Train your own O1 preview model within $450☆3,370Updated 6 months ago
- Muon is Scalable for LLM Training☆1,426Updated 6 months ago
- Code for BLT research paper☆2,027Updated 3 months ago
- ☆1,388Updated 4 months ago
- Async RL Training at Scale☆1,044Updated this week
- Training Large Language Model to Reason in a Continuous Latent Space☆1,496Updated 5 months ago
- Everything about the SmolLM and SmolVLM family of models☆3,594Updated 3 weeks ago
- ☆1,283Updated 2 months ago
- General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.☆2,028Updated this week
- A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring…☆2,856Updated this week
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆1,301Updated 3 weeks ago
- Humanity's Last Exam☆1,352Updated 4 months ago
- τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment☆717Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,547Updated this week
- Scalable toolkit for efficient model reinforcement☆1,293Updated this week
- Synthetic data curation for post-training and structured data extraction☆1,626Updated 2 weeks ago
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,759Updated 9 months ago
- Supercharge Your LLM with the Fastest KV Cache Layer☆6,839Updated this week
- Optimize prompts, code, and more with AI-powered Reflective Text Evolution☆2,214Updated last week