Repositories list

• verina

  Public
  Verina (Verifiable Code Generation Arena) is a high-quality benchmark enabling a comprehensive and modular evaluation of code, specification, and proof generati…

  Lean

  •

  Apache License 2.0

  •9•53•4•2•Updated Mar 10, 2026Mar 10, 2026

• cybergym

  Public

  sunblaze-ucb/cybergym’s past year of commit activity
  CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerabili…

  Python

  •

  Apache License 2.0

  •30•187•0•0•Updated Feb 23, 2026Feb 23, 2026

• cybergym-page

  Public
  HTML

  •0•0•0•0•Updated Feb 20, 2026Feb 20, 2026

• cybergym-agent-examples

  Public

  sunblaze-ucb/cybergym-agent-examples’s past year of commit activity
  HTML

  •5•3•0•1•Updated Feb 2, 2026Feb 2, 2026

• Intuitor

  Public
  [ICLR 2026] Learning to Reason without External Rewards

  Python

  •43•403•14•0•Updated Jan 26, 2026Jan 26, 2026

• mirage-bench

  Public
  Python

  •

  Apache License 2.0

  •2•7•0•0•Updated Jan 26, 2026Jan 26, 2026

• llm-code-security

  Public
  HTML

  •0•1•0•0•Updated Dec 6, 2025Dec 6, 2025

• clue

  Public
  Go

  •

  GNU General Public License v3.0

  •2•6•0•0•Updated Nov 27, 2025Nov 27, 2025

• VMDT-page

  Public
  JavaScript

  •0•0•0•0•Updated Nov 24, 2025Nov 24, 2025

• rl-grok-recipe

  Public
  Code repository for "RL Grokking Recipe: How RL Unlocks and Transfers New Algorithms in LLMs""

  Python

  •1•32•1•0•Updated Oct 12, 2025Oct 12, 2025

• AgentSynth

  Public
  AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents

  Python

  •

  Apache License 2.0

  •3•39•2•0•Updated Oct 7, 2025Oct 7, 2025

• awesome-RLVR-boundary

  Public
  updated address: https://github.com/rdi-berkeley/awesome-RLVR-boundary

  0•0•0•1•Updated Oct 7, 2025Oct 7, 2025

• VMDT

  Public
  Python

  •

  Apache License 2.0

  •0•2•0•0•Updated Oct 2, 2025Oct 2, 2025

• progent

  Public
  Python

  •9•32•1•1•Updated Sep 11, 2025Sep 11, 2025

• omega

  Public
  Python

  •4•46•0•1•Updated Jun 24, 2025Jun 24, 2025

• agentsynth_web

  Public
  Webpage for AgentSynth Paper

  JavaScript

  •0•0•0•0•Updated Jun 18, 2025Jun 18, 2025

• cybergym-neurips-25

  Public
  HTML

  •1•1•0•0•Updated May 16, 2025May 16, 2025

• reasoning_ladder

  Public
  Python

  •4•35•0•0•Updated May 16, 2025May 16, 2025

• llm-api-audit

  Public
  Python

  •

  MIT License

  •0•8•1•0•Updated Apr 10, 2025Apr 10, 2025

• political_leaning_RepE

  Public
  Jupyter Notebook

  •

  MIT License

  •0•2•0•0•Updated Nov 8, 2024Nov 8, 2024

• simpleMPI

  Public
  Go

  •

  Apache License 2.0

  •2•0•0•0•Updated Sep 19, 2023Sep 19, 2023

• Libra

  Public
  Libra zero knowledge proof system

  C++

  •

  Apache License 2.0

  •14•55•1•1•Updated Mar 16, 2023Mar 16, 2023

• adversarial-protector

  Public
  Python

  •0•1•0•0•Updated Mar 9, 2023Mar 9, 2023

• zkcollective

  Public
  HTML

  •0•0•0•0•Updated Mar 9, 2023Mar 9, 2023

• bellman

  Public
  Bellman zkSNARK library for community with Ethereum's BN256 support

  C

  •

  Other

  •559•0•0•0•Updated Nov 17, 2022Nov 17, 2022

• program-synthesis

  Public
  HTML

  •2•2•1•0•Updated Oct 27, 2022Oct 27, 2022

• REFIT

  Public
  Python

  •

  MIT License

  •6•27•0•1•Updated Oct 17, 2022Oct 17, 2022

• Orion

  Public
  C++

  •

  Apache License 2.0

  •12•31•0•0•Updated Sep 19, 2022Sep 19, 2022

• eVSS

  Public
  C++

  •3•2•1•0•Updated Jan 16, 2022Jan 16, 2022

• Virgo

  Public
  C++

  •

  Apache License 2.0

  •17•61•3•0•Updated Dec 27, 2021Dec 27, 2021