Alternatives and similar repositories for harmony

Users that are interested in harmony are comparing it to the libraries listed below

• safety-research / circuit-tracer
  ☆2,546Updated this week
• thinking-machines-lab / tinker-cookbook
  Post-training with Tinker
  ☆2,719Updated this week
• PrimeIntellect-ai / verifiers
  Our library for RL environments + evals
  ☆3,748Updated this week
• MiniMax-AI / MiniMax-M1
  MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
  ☆3,037Updated 6 months ago
• laude-institute / terminal-bench
  A benchmark for LLMs on complicated tasks in the terminal
  ☆1,350Updated 3 weeks ago
• openai / frontier-evals
  OpenAI Frontier Evals
  ☆983Updated last month
• SWE-agent / mini-swe-agent
  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…
  ☆2,530Updated this week
• MoonshotAI / Kimi-K2
  Kimi K2 is the large language model series developed by Moonshot AI team
  ☆9,818Updated 2 months ago
• NovaSky-AI / SkyThought
  Sky-T1: Train your own O1 preview model within $450
  ☆3,367Updated 6 months ago
• bespokelabsai / curator
  Synthetic data curation for post-training and structured data extraction
  ☆1,602Updated 2 weeks ago
• google / tunix
  A Lightweight LLM Post-Training Library
  ☆2,106Updated this week
• openai / SWELancer-Benchmark
  This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software E…
  ☆1,437Updated 6 months ago
• rllm-org / rllm
  Democratizing Reinforcement Learning for LLMs
  ☆4,995Updated this week
• ml-explore / mlx-lm
  Run LLMs with MLX
  ☆3,326Updated this week
• LiveBench / LiveBench
  LiveBench: A Challenging, Contamination-Free LLM Benchmark
  ☆1,010Updated this week
• OpenPipe / ART
  Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…
  ☆8,139Updated last week
• HazyResearch / minions
  Big & Small LLMs working together
  ☆1,242Updated this week
• MoonshotAI / Moonlight
  Muon is Scalable for LLM Training
  ☆1,407Updated 5 months ago
• huggingface / lighteval
  Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
  ☆2,251Updated last week
• PrimeIntellect-ai / prime-rl
  Async RL Training at Scale
  ☆1,005Updated this week
• deepseek-ai / Engram
  Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
  ☆1,612Updated last week
• microsoft / rStar
  ☆1,381Updated 4 months ago
• QwenLM / Qwen3-Omni
  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…
  ☆3,280Updated last week
• natolambert / rlhf-book
  Textbook on reinforcement learning from human feedback
  ☆1,416Updated this week
• facebookresearch / blt
  Code for BLT research paper
  ☆2,024Updated 2 months ago
• OpenCoder-llm / OpenCoder-llm
  The Open Cookbook for Top-Tier Code Large Language Model
  ☆1,994Updated last year
• MoonshotAI / Kimi-Linear
  ☆1,268Updated 2 months ago
• policy-gradient / GRPO-Zero
  Implementing DeepSeek R1's GRPO algorithm from scratch
  ☆1,747Updated 9 months ago
• openai / mle-bench
  MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
  ☆1,276Updated this week
• gepa-ai / gepa
  Optimize prompts, code, and more with AI-powered Reflective Text Evolution
  ☆2,078Updated 2 weeks ago