Alternatives and similar repositories for HRM

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

• SamsungSAILMontreal / TinyRecursiveModels
  ☆5,663Updated last month
• OpenPipe / ART
  Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…
  ☆7,848Updated this week
• GAIR-NLP / ASI-Arch
  AlphaGo Moment for Model Architecture Discovery.
  ☆1,114Updated 3 months ago
• HKUDS / DeepCode
  "DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
  ☆10,320Updated this week
• MoonshotAI / Kimi-K2
  Kimi K2 is the large language model series developed by Moonshot AI team
  ☆9,516Updated last week
• MiniMax-AI / MiniMax-M1
  MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
  ☆2,992Updated 4 months ago
• yichuan-w / LEANN
  RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal…
  ☆4,379Updated this week
• algorithmicsuperintelligence / openevolve
  Open-source implementation of AlphaEvolve
  ☆4,551Updated last week
• PrimeIntellect-ai / verifiers
  Environments for LLM Reinforcement Learning
  ☆3,495Updated this week
• LeapLabTHU / Absolute-Zero-Reasoner
  Official Repository of Absolute Zero Reasoner
  ☆1,747Updated 2 months ago
• jennyzzt / dgm
  Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
  ☆1,741Updated 3 months ago
• SakanaAI / continuous-thought-machines
  Continuous Thought Machines, because thought takes time and reasoning is a process.
  ☆1,396Updated last month
• thinking-machines-lab / tinker-cookbook
  Post-training with Tinker
  ☆1,932Updated last week
• Continual-Intelligence / SEAL
  Self-Adapting Language Models
  ☆1,502Updated 3 months ago
• openai / harmony
  Renderer for the harmony response format to be used with gpt-oss
  ☆4,007Updated 2 weeks ago
• Mega4alik / ollm
  ☆2,156Updated 2 weeks ago
• Agent-on-the-Fly / Memento
  Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
  ☆1,877Updated last month
• google / tunix
  A JAX-native LLM Post-Training Library
  ☆1,894Updated this week
• HKUDS / AutoAgent
  "AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"
  ☆7,808Updated last month
• Olow304 / memvid
  Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.
  ☆10,381Updated last month
• microsoft / agent-lightning
  The absolute trainer to light up AI agents.
  ☆8,393Updated this week
• zai-org / GLM-4.5
  GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
  ☆3,213Updated last month
• NovaSky-AI / SkyThought
  Sky-T1: Train your own O1 preview model within $450
  ☆3,357Updated 4 months ago
• octotools / octotools
  OctoTools: An agentic framework with extensible tools for complex reasoning
  ☆1,385Updated last month
• simplescaling / s1
  s1: Simple test-time scaling
  ☆6,597Updated 4 months ago
• simstudioai / sim
  Open-source platform to build and deploy AI agent workflows.
  ☆18,408Updated this week
• facebookresearch / blt
  Code for BLT research paper
  ☆2,008Updated 2 weeks ago
• shyamsaktawat / OpenAlpha_Evolve
  OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's A…
  ☆940Updated 5 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
• MoonshotAI / Kimi-k1.5
  ☆3,469Updated 8 months ago