Skip to content
Change the repository type filter

All

    Repositories list

    • MedVerse

      Public
      Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution
      Python
      Apache License 2.0
      0310Updated Apr 15, 2026Apr 15, 2026
    • WebXSkill

      Public
      WebXSkill: Skill Learning for Autonomous Web Agents
      0510Updated Apr 13, 2026Apr 13, 2026
    • SkillRL

      Public
      SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
      Python
      MIT License
      4463810Updated Apr 11, 2026Apr 11, 2026
    • MetaClaw

      Public
      🦞 Just talk to your agent — it learns and EVOLVES 🧬.
      Python
      MIT License
      4133.5k74Updated Apr 11, 2026Apr 11, 2026
    • Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
      Python
      MIT License
      1.3k11k33Updated Apr 10, 2026Apr 10, 2026
    • ClawArena

      Public
      Python
      MIT License
      04420Updated Apr 7, 2026Apr 7, 2026
    • SimpleMem

      Public
      SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
      Python
      MIT License
      3263.3k71Updated Apr 4, 2026Apr 4, 2026
    • AutoHarness

      Public
      AutoHarness: Automated Harness Engineering for AI Agents
      Python
      MIT License
      1924100Updated Apr 2, 2026Apr 2, 2026
    • SimpleOCR

      Public
      [ACL'26 Findings] SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read
      Python
      Apache License 2.0
      1710Updated Mar 12, 2026Mar 12, 2026
    • Agent0

      Public
      Agent0 Series: Self-Evolving Agents from Zero Data
      Python
      Apache License 2.0
      1391.2k50Updated Feb 17, 2026Feb 17, 2026
    • MIRA

      Public
      When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought
      Python
      Apache License 2.0
      03010Updated Feb 14, 2026Feb 14, 2026
    • SynthAgent

      Public
      SynthAgent: Adapting Web Agents with Synthetic Supervision
      Python
      13010Updated Feb 5, 2026Feb 5, 2026
    • SimpleMem-Page

      Public
      Python
      0100Updated Jan 7, 2026Jan 7, 2026
    • ATP

      Public
      Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails
      Python
      MIT License
      01020Updated Oct 7, 2025Oct 7, 2025
    • ReAgent-V

      Public
      [NeurIPS'25] ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
      Python
      25230Updated Sep 21, 2025Sep 21, 2025
    • GLIMPSE

      Public
      [EMNLP'25 Oral] GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?
      Python
      Apache License 2.0
      0920Updated Aug 22, 2025Aug 22, 2025
    • MDocAgent

      Public
      MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
      Python
      MIT License
      3332360Updated Aug 8, 2025Aug 8, 2025
    • [ICLR'26] EduVisAgent: A Benchmark and Multi-Agent Framework for Pedagogical Visualization
      Python
      23010Updated Aug 5, 2025Aug 5, 2025
    • CITER

      Public
      [COLM'25] CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing
      Python
      31930Updated Jun 25, 2025Jun 25, 2025
    • MMedPO

      Public
      [ICML'25] MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization
      Python
      Apache License 2.0
      77320Updated Jun 5, 2025Jun 5, 2025
    • Python
      1800Updated May 27, 2025May 27, 2025
    • GRAPE

      Public
      GRAPE: Guided-Reinforced Vision-Language-Action Preference Optimization
      Python
      MIT License
      8159140Updated Apr 6, 2025Apr 6, 2025
    • Anyprefer

      Public
      0100Updated Mar 2, 2025Mar 2, 2025
    • MJ-Video

      Public
      [NeurIPS'25 Spotlight] MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation
      Python
      22120Updated Feb 23, 2025Feb 23, 2025
    • HTML
      Other
      0100Updated Feb 6, 2025Feb 6, 2025
    • MMIE

      Public
      [ICLR'25 Oral] MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
      Python
      MIT License
      3100Updated Nov 3, 2024Nov 3, 2024
    • RULE

      Public
      [EMNLP'24] RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models
      Python
      MIT License
      5100Updated Oct 22, 2024Oct 22, 2024
    • MMed-RAG

      Public
      [ICLR'25] MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
      Python
      MIT License
      24300Updated Oct 20, 2024Oct 20, 2024
    • CREAM

      Public
      [ICLR'25] Code for paper "CREAM: Consistency Regularized Self-Rewarding Language Models".
      2100Updated Oct 15, 2024Oct 15, 2024
    • CARES

      Public
      [NeurIPS'24] CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
      Python
      Creative Commons Attribution 4.0 International
      8100Updated Sep 26, 2024Sep 26, 2024
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.