Alternatives and similar repositories for harmony

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

• thinking-machines-lab / tinker-cookbook
  Post-training with Tinker
  ☆1,932Updated this week
• PrimeIntellect-ai / verifiers
  Environments for LLM Reinforcement Learning
  ☆3,495Updated this week
• safety-research / circuit-tracer
  ☆2,432Updated 2 weeks ago
• openai / frontier-evals
  OpenAI Frontier Evals
  ☆942Updated 2 weeks ago
• NovaSky-AI / SkyThought
  Sky-T1: Train your own O1 preview model within $450
  ☆3,352Updated 4 months ago
• 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…
  ☆2,060Updated this week
• MiniMax-AI / MiniMax-M1
  MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
  ☆2,992Updated 4 months ago
• 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…
  ☆1,439Updated 4 months ago
• laude-institute / terminal-bench
  A benchmark for LLMs on complicated tasks in the terminal
  ☆1,069Updated this week
• MoonshotAI / Kimi-K2
  Kimi K2 is the large language model series developed by Moonshot AI team
  ☆9,330Updated last week
• HazyResearch / minions
  Big & Small LLMs working together
  ☆1,200Updated this week
• rllm-org / rllm
  Democratizing Reinforcement Learning for LLMs
  ☆4,737Updated 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…
  ☆7,817Updated this week
• bespokelabsai / curator
  Synthetic data curation for post-training and structured data extraction
  ☆1,553Updated 3 months ago
• microsoft / rStar
  ☆1,339Updated 2 months ago
• gepa-ai / gepa
  Optimize prompts, code, and more with AI-powered Reflective Text Evolution
  ☆1,526Updated last week
• ml-explore / mlx-lm
  Run LLMs with MLX
  ☆2,868Updated this week
• huggingface / lighteval
  Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
  ☆2,108Updated this week
• algorithmicsuperintelligence / openevolve
  Open-source implementation of AlphaEvolve
  ☆4,551Updated this week
• LiveBench / LiveBench
  LiveBench: A Challenging, Contamination-Free LLM Benchmark
  ☆928Updated this week
• Continual-Intelligence / SEAL
  Self-Adapting Language Models
  ☆1,502Updated 3 months ago
• google / tunix
  A JAX-native LLM Post-Training Library
  ☆1,801Updated this week
• LMCache / LMCache
  Supercharge Your LLM with the Fastest KV Cache Layer
  ☆5,987Updated this week
• openai / mle-bench
  MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
  ☆1,178Updated this week
• facebookresearch / large_concept_model
  Large Concept Models: Language modeling in a sentence representation space
  ☆2,304Updated 9 months ago
• natolambert / rlhf-book
  Textbook on reinforcement learning from human feedback
  ☆1,313Updated this week
• huggingface / smollm
  Everything about the SmolLM and SmolVLM family of models
  ☆3,397Updated 2 months ago
• deepseek-ai / DeepSeek-Prover-V2
  ☆1,200Updated 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…
  ☆2,921Updated last month
• karpathy / rendergit
  Render any git repo into a single static HTML page for humans or LLMs
  ☆1,880Updated 2 months ago