Skip to content
Change the repository type filter

All

    Repositories list

    • SkyRL

      Public
      SkyRL: A Modular Full-stack RL Library for LLMs
      Python
      Apache License 2.0
      314100Updated May 1, 2026May 1, 2026
    • sodium

      Public
      Reproduction Artifact for "SODIUM: From Open Web Data to Queryable Databases"
      Python
      0400Updated Apr 27, 2026Apr 27, 2026
    • Post-training with Tinker
      Python
      Apache License 2.0
      407100Updated Apr 22, 2026Apr 22, 2026
    • Python
      0000Updated Apr 21, 2026Apr 21, 2026
    • HTML
      0000Updated Apr 20, 2026Apr 20, 2026
    • BEAT

      Public
      Python
      2610Updated Apr 20, 2026Apr 20, 2026
    • [ICLR'2026] Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?
      C++
      0100Updated Apr 19, 2026Apr 19, 2026
    • Python
      0000Updated Apr 7, 2026Apr 7, 2026
    • rllm

      Public
      Democratizing Reinforcement Learning for LLMs
      Python
      MIT License
      548000Updated Apr 2, 2026Apr 2, 2026
    • Python
      0000Updated Apr 1, 2026Apr 1, 2026
    • DART

      Public
      Python
      0000Updated Apr 1, 2026Apr 1, 2026
    • ELT-Bench

      Public
      Python
      72331Updated Mar 25, 2026Mar 25, 2026
    • plop

      Public
      Official code for PLoP
      Python
      5000Updated Mar 19, 2026Mar 19, 2026
    • ParSEval

      Public
      Plan-aware Test Database Generation for SQL Equivalence Evaluation
      Python
      Apache License 2.0
      3000Updated Mar 3, 2026Mar 3, 2026
    • VeriEQL

      Public
      Python
      Other
      13000Updated Mar 3, 2026Mar 3, 2026
    • ReViSQL

      Public
      Python
      31200Updated Mar 2, 2026Mar 2, 2026
    • SHARE

      Public
      Python
      Apache License 2.0
      1000Updated Feb 25, 2026Feb 25, 2026
    • TypeScript
      GNU Affero General Public License v3.0
      0000Updated Feb 24, 2026Feb 24, 2026
    • HPTSA

      Public
      Teams of LLM Agents can Exploit Zero-Day Vulnerabilities
      Python
      0300Updated Feb 23, 2026Feb 23, 2026
    • [VLDB2026] Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards
      Python
      11120Updated Feb 22, 2026Feb 22, 2026
    • Python
      0000Updated Jan 25, 2026Jan 25, 2026
    • cve-bench

      Public
      CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities
      Python
      Apache License 2.0
      4121110Updated Jan 14, 2026Jan 14, 2026
    • PilotDB

      Public
      Online AQP with A Priori Error Guarantees
      Python
      2700Updated Jan 12, 2026Jan 12, 2026
    • drama

      Public
      [SIGMOD'2026] DRAMA: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries
      Python
      11310Updated Dec 6, 2025Dec 6, 2025
    • Collection of evals for Inspect AI
      C++
      MIT License
      312000Updated Nov 17, 2025Nov 17, 2025
    • SWE-bench

      Public
      SWE-bench: Can Language Models Resolve Real-world Github Issues?
      Python
      MIT License
      849000Updated Nov 14, 2025Nov 14, 2025
    • zk-torch

      Public
      Rust
      Apache License 2.0
      93831Updated Nov 7, 2025Nov 7, 2025
    • Python
      21100Updated Nov 3, 2025Nov 3, 2025
    • leap

      Public
      [VLDB'2025] LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data
      Python
      02000Updated Nov 3, 2025Nov 3, 2025
    • Java
      Apache License 2.0
      0000Updated Aug 27, 2025Aug 27, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.