Skip to content

@AI45Lab OpenAI45Lab

All

    Repositories list

    68 repositories

    • Awesome-Trustworthy-Embodied-AI

      Public
      JavaScript
      •3•101•0•0•Updated Oct 6, 2026Oct 6, 2026

    • OpenART

      Public
      OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. …
      agentdockerbenchmark
      agentdockerbenchmarkjailbreakred-teamred-teamingtool-useprompt-injectionllm-securityllm-evaluation
      Python
      •
      GNU Affero General Public License v3.0
      •25•230•0•0•Updated Oct 3, 2026Oct 3, 2026

    • MAGIC

      Public
      Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"
      Python
      •
      Apache License 2.0
      •4•57•0•0•Updated Oct 1, 2026Oct 1, 2026

    • SAfactory

      Public
      SAfactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
      Python
      •26•236•18•2•Updated Sep 24, 2026Sep 24, 2026

    • DataElf

      Public
      DataElf is an intelligent data workflow engine that turns natural-language tasks into secure, extensible, and executable data pipelines.
      Python
      •1•24•0•1•Updated Sep 22, 2026Sep 22, 2026

    • wt-data-platform-sdk

      Public
      SDK for writing, querying, and managing agent trajectory data on lancedb-based data platform.
      Python
      •4•2•1•1•Updated Sep 20, 2026Sep 20, 2026

    • Safin-1

      Public
      MIT License
      •0•10•1•0•Updated Sep 1, 2026Sep 1, 2026

    • DeepSafe

      Public
      All-in-One Safety Evaluation Framwork
      securitybenchmarkalignment
      securitybenchmarkalignmentbenchmark-frameworkai-safetysecurity-tools
      Python
      •0•56•1•1•Updated Aug 12, 2026Aug 12, 2026

    • DeepSafe-Sci

      Public
      Python
      •
      Apache License 2.0
      •1•6•0•1•Updated Aug 11, 2026Aug 11, 2026

    • ActorAttack

      Public
      Python
      •12•134•0•0•Updated Jul 29, 2026Jul 29, 2026

    • RouteLens

      Public
      RouteLens: OpenAI-compatible API observability and protection platform
      TypeScript
      •
      Other
      •0•97•0•0•Updated Jul 26, 2026Jul 26, 2026

    • iDeer

      Public
      这倒是提醒我了
      Python
      •
      GNU Affero General Public License v3.0
      •57•416•10•3•Updated Jul 26, 2026Jul 26, 2026

    • OpenRT

      Public
      Open-source red teaming framework for MLLMs with 42+ attack methods
      high-throughputai-safetyred-teaming
      high-throughputai-safetyred-teamingmultimodal-llmsafety-evaluationagentic-attacks
      Python
      •
      GNU Affero General Public License v3.0
      •23•276•0•1•Updated Jul 17, 2026Jul 17, 2026

    • Code

      Public
      Agentic Agent Framework
      Rust
      •
      MIT License
      •6•135•0•2•Updated Jul 2, 2026Jul 2, 2026

    • Box

      Public
      MicroVM Runtime
      Rust
      •
      MIT License
      •7•53•3•1•Updated Jul 1, 2026Jul 1, 2026

    • SentrySkills

      Public
      LLM-native skill package that teaches agents to protect themselves
      Python
      •
      MIT License
      •1•9•0•0•Updated Jun 25, 2026Jun 25, 2026

    • TrinityGuard

      Public
      TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
      Python
      •
      MIT License
      •24•220•2•0•Updated Jun 25, 2026Jun 25, 2026

    • PseudoBench

      Public
      Python
      •
      MIT License
      •1•2•0•0•Updated Jun 22, 2026Jun 22, 2026

    • HomeGuard

      Public
      [ECCV 2026] The code repo of paper "HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task"
      Python
      •0•13•1•0•Updated Jun 21, 2026Jun 21, 2026

    • ClawSentry

      Public
      Python
      •
      MIT License
      •1•19•1•0•Updated Jun 14, 2026Jun 14, 2026

    • AgentDoG

      Public
      A Diagnostic Guardrail Framework for AI Agent Safety and Security
      Python
      •35•700•1•1•Updated Jun 8, 2026Jun 8, 2026

    • skill-safety-bench

      Public
      Python
      •
      Apache License 2.0
      •4•32•1•0•Updated May 14, 2026May 14, 2026

    • AgentHarnessProtocol

      Public
      Agent Harness Protocol (AHP)
      Rust
      •
      MIT License
      •0•4•0•0•Updated May 5, 2026May 5, 2026

    • ai45lab.github.io

      Public
      ai45lab.github.io
      TypeScript
      •0•0•0•0•Updated Apr 27, 2026Apr 27, 2026

    • ScientificSafetyLevels

      Public
      SSL: Scientific Safety Levels for Responsible Autonomous Science
      1•2•0•0•Updated Apr 16, 2026Apr 16, 2026

    • Human-like-Interactive-Evaluation

      Public
      Python
      •
      MIT License
      •2•3•0•0•Updated Apr 13, 2026Apr 13, 2026

    • SafeClaw

      Public
      Secure Personal AI Assistant with TEE Support
      1•23•0•0•Updated Apr 11, 2026Apr 11, 2026

    • UniMark

      Public
      AIGC watermark & identification toolkit for text, image, audio, video. Supports invisible watermarking and visible marking.
      watermarkvideo-watermarkimage-watermark
      watermarkvideo-watermarkimage-watermarktext-watermarkaudio-watermarkingdeepfake-detection
      Jupyter Notebook
      •5•19•0•0•Updated Apr 1, 2026Apr 1, 2026

    • Ghost-EI

      Public
      Python
      •
      MIT License
      •3•1•0•0•Updated Mar 30, 2026Mar 30, 2026

    • ClawReverse

      Public
      The native version-control plugin for OpenClaw. Avoid rework and save tokens with easy checkpoints, rollbacks, and safe trial-and-error branching.
      JavaScript
      •2•0•0•0•Updated Mar 20, 2026Mar 20, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.