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
  ☆2,617Updated this week
• PrimeIntellect-ai / verifiers
  Our library for RL environments + evals
  ☆3,655Updated last week
• safety-research / circuit-tracer
  ☆2,507Updated this week
• 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…
  ☆2,385Updated last week
• openai / frontier-evals
  OpenAI Frontier Evals
  ☆967Updated 3 weeks ago
• MiniMax-AI / MiniMax-M1
  MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
  ☆3,005Updated 5 months ago
• ml-explore / mlx-lm
  Run LLMs with MLX
  ☆3,111Updated last week
• laude-institute / terminal-bench
  A benchmark for LLMs on complicated tasks in the terminal
  ☆1,260Updated this week
• 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…
  ☆3,157Updated 2 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…
  ☆1,438Updated 5 months ago
• MoonshotAI / Kimi-K2
  Kimi K2 is the large language model series developed by Moonshot AI team
  ☆9,763Updated last month
• rllm-org / rllm
  Democratizing Reinforcement Learning for LLMs
  ☆4,896Updated last week
• HazyResearch / minions
  Big & Small LLMs working together
  ☆1,230Updated last week
• huggingface / smollm
  Everything about the SmolLM and SmolVLM family of models
  ☆3,499Updated last month
• facebookresearch / blt
  Code for BLT research paper
  ☆2,018Updated last month
• NovaSky-AI / SkyThought
  Sky-T1: Train your own O1 preview model within $450
  ☆3,363Updated 5 months ago
• SakanaAI / text-to-lora
  Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input
  ☆933Updated 6 months ago
• google / tunix
  A Lightweight LLM Post-Training Library
  ☆2,055Updated this week
• MoonshotAI / Moonlight
  Muon is Scalable for LLM Training
  ☆1,387Updated 4 months ago
• deepseek-ai / DeepSeek-Prover-V2
  ☆1,226Updated 5 months ago
• bespokelabsai / curator
  Synthetic data curation for post-training and structured data extraction
  ☆1,586Updated 5 months ago
• LiveBench / LiveBench
  LiveBench: A Challenging, Contamination-Free LLM Benchmark
  ☆989Updated this week
• policy-gradient / GRPO-Zero
  Implementing DeepSeek R1's GRPO algorithm from scratch
  ☆1,718Updated 8 months ago
• LeapLabTHU / Absolute-Zero-Reasoner
  Official Repository of Absolute Zero Reasoner
  ☆1,779Updated 4 months ago
• LMCache / LMCache
  Supercharge Your LLM with the Fastest KV Cache Layer
  ☆6,451Updated this week
• algorithmicsuperintelligence / openevolve
  Open-source implementation of AlphaEvolve
  ☆4,981Updated this week
• thinking-machines-lab / batch_invariant_ops
  ☆941Updated last month
• microsoft / rStar
  ☆1,369Updated 3 months ago
• deepseek-ai / DeepSeek-V3.2-Exp
  ☆1,383Updated last month
• facebookresearch / large_concept_model
  Large Concept Models: Language modeling in a sentence representation space
  ☆2,313Updated 11 months ago