Alternatives and similar repositories for Kimi-K2

Users that are interested in Kimi-K2 are comparing it to the libraries listed below

• MiniMax-AI / MiniMax-M1
  MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
  ☆3,075Updated 7 months ago
• zai-org / GLM-4.5
  GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
  ☆4,144Updated last week
• openai / harmony
  Renderer for the harmony response format to be used with gpt-oss
  ☆4,171Updated last month
• QwenLM / Qwen3-Coder
  Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
  ☆15,271Updated last week
• MiniMax-AI / MiniMax-01
  The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention
  ☆3,328Updated 7 months ago
• bytedance / trae-agent
  Trae Agent is an LLM-based agent for general purpose software engineering tasks.
  ☆10,730Updated 4 months ago
• bytedance / UI-TARS
  Pioneering Automated GUI Interaction with Native Agents
  ☆9,343Updated 2 weeks ago
• MoonshotAI / Kimi-k1.5
  ☆3,467Updated 11 months ago
• MiniMax-AI / MiniMax-M2
  MiniMax-M2, a model built for Max coding & agentic workflows.
  ☆2,357Updated 2 months ago
• QwenLM / qwen-code
  An open-source AI agent that lives in your terminal.
  ☆18,282Updated this week
• MoonshotAI / Kimi-Dev
  open-source coding LLM for software engineering tasks
  ☆1,127Updated 4 months ago
• MoonshotAI / kimi-cli
  Kimi Code CLI is your next CLI agent.
  ☆6,076Updated this week
• anthropics / claude-code
  Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing rout…
  ☆65,228Updated this week
• simular-ai / Agent-S
  Agent S: an open agentic framework that uses computers like a human
  ☆9,713Updated 3 weeks 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…
  ☆3,399Updated last month
• deepseek-ai / DeepSeek-Coder-V2
  DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
  ☆6,423Updated 3 months ago
• simplescaling / s1
  s1: Simple test-time scaling
  ☆6,636Updated 7 months ago
• GAIR-NLP / ASI-Arch
  AlphaGo Moment for Model Architecture Discovery.
  ☆1,131Updated 2 months ago
• zai-org / GLM-V
  GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
  ☆2,162Updated 2 weeks ago
• openai / gpt-oss
  gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
  ☆19,733Updated 3 weeks ago
• thinking-machines-lab / tinker-cookbook
  Post-training with Tinker
  ☆2,805Updated last week
• XiaomiMiMo / MiMo
  MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining
  ☆1,924Updated 8 months ago
• deepseek-ai / DeepSeek-Prover-V2
  ☆1,233Updated 6 months ago
• kortix-ai / suna
  Kortix – build, manage and train AI Agents.
  ☆19,325Updated 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…
  ☆8,596Updated this week
• jina-ai / node-DeepResearch
  Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
  ☆5,076Updated last month
• ByteDance-Seed / Bagel
  Open-source unified multimodal model
  ☆5,631Updated 3 months ago
• OpenManus / OpenManus-RL
  A live stream development of RL tunning for LLM agents
  ☆3,901Updated 4 months ago
• NovaSky-AI / SkyThought
  Sky-T1: Train your own O1 preview model within $450
  ☆3,370Updated 6 months ago
• centerforaisafety / hle
  Humanity's Last Exam
  ☆1,352Updated 4 months ago