Repositories list

• Awesome-Trustworthy-Embodied-AI

  Public
  JavaScript

  •33 forks in AI45Lab/Awesome-Trustworthy-Embodied-AI•101101 stars in AI45Lab/Awesome-Trustworthy-Embodied-AI•00 issues in AI45Lab/Awesome-Trustworthy-Embodied-AI•00 pull requests in AI45Lab/Awesome-Trustworthy-Embodied-AI•Updated Oct 19, 2026Oct 19, 2026

• wt-data-platform-sdk

  Public
  SDK for writing, querying, and managing agent trajectory data on lancedb-based data platform.

  Python

  •44 forks in AI45Lab/wt-data-platform-sdk•22 stars in AI45Lab/wt-data-platform-sdk•11 issue in AI45Lab/wt-data-platform-sdk•11 pull request in AI45Lab/wt-data-platform-sdk•Updated Oct 19, 2026Oct 19, 2026

• SAfactory

  Public
  SAfactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence

  Python

  •2727 forks in AI45Lab/SAfactory•237237 stars in AI45Lab/SAfactory•1919 issues in AI45Lab/SAfactory•33 pull requests in AI45Lab/SAfactory•Updated Oct 18, 2026Oct 18, 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+ 17

  agentdockerbenchmarkjailbreakred-teamred-teamingtool-useprompt-injectionllm-securityllm-evaluation+ 10

  Python

  •

  GNU Affero General Public License v3.0

  •2828 forks in AI45Lab/OpenART•248248 stars in AI45Lab/OpenART•00 issues in AI45Lab/OpenART•00 pull requests in AI45Lab/OpenART•Updated Oct 15, 2026Oct 15, 2026

• DeepSafe

  Public
  All-in-One Safety Evaluation Framwork

  securitybenchmarkalignment+ 3

  securitybenchmarkalignmentbenchmark-frameworkai-safetysecurity-tools

  Python

  •22 forks in AI45Lab/DeepSafe•5656 stars in AI45Lab/DeepSafe•11 issue in AI45Lab/DeepSafe•22 pull requests in AI45Lab/DeepSafe•Updated Oct 15, 2026Oct 15, 2026

• MAGIC

  Public
  Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"

  Python

  •

  Apache License 2.0

  •55 forks in AI45Lab/MAGIC•5959 stars in AI45Lab/MAGIC•00 issues in AI45Lab/MAGIC•00 pull requests in AI45Lab/MAGIC•Updated Oct 15, 2026Oct 15, 2026

• CompanionSafe

  Public
  Python

  •

  MIT License

  •11 fork in AI45Lab/CompanionSafe•33 stars in AI45Lab/CompanionSafe•00 issues in AI45Lab/CompanionSafe•00 pull requests in AI45Lab/CompanionSafe•Updated Oct 14, 2026Oct 14, 2026

• ReSI

  Public
  Python

  •

  MIT License

  •00 forks in AI45Lab/ReSI•77 stars in AI45Lab/ReSI•00 issues in AI45Lab/ReSI•00 pull requests in AI45Lab/ReSI•Updated Oct 11, 2026Oct 11, 2026

• DataElf

  Public
  DataElf is an intelligent data workflow engine that turns natural-language tasks into secure, extensible, and executable data pipelines.

  Python

  •11 fork in AI45Lab/DataElf•2424 stars in AI45Lab/DataElf•00 issues in AI45Lab/DataElf•11 pull request in AI45Lab/DataElf•Updated Sep 22, 2026Sep 22, 2026

• Safin-1

  Public
  MIT License

  •00 forks in AI45Lab/Safin-1•1010 stars in AI45Lab/Safin-1•11 issue in AI45Lab/Safin-1•00 pull requests in AI45Lab/Safin-1•Updated Sep 1, 2026Sep 1, 2026

• DeepSafe-Sci

  Public
  Python

  •

  Apache License 2.0

  •11 fork in AI45Lab/DeepSafe-Sci•66 stars in AI45Lab/DeepSafe-Sci•00 issues in AI45Lab/DeepSafe-Sci•11 pull request in AI45Lab/DeepSafe-Sci•Updated Aug 11, 2026Aug 11, 2026

• ActorAttack

  Public
  Python

  •1212 forks in AI45Lab/ActorAttack•134134 stars in AI45Lab/ActorAttack•00 issues in AI45Lab/ActorAttack•00 pull requests in AI45Lab/ActorAttack•Updated Jul 29, 2026Jul 29, 2026

• RouteLens

  Public
  RouteLens: OpenAI-compatible API observability and protection platform

  TypeScript

  •

  Other

  •00 forks in AI45Lab/RouteLens•9797 stars in AI45Lab/RouteLens•00 issues in AI45Lab/RouteLens•00 pull requests in AI45Lab/RouteLens•Updated Jul 26, 2026Jul 26, 2026

• iDeer

  Public
  这倒是提醒我了

  Python

  •

  GNU Affero General Public License v3.0

  •5656 forks in AI45Lab/iDeer•416416 stars in AI45Lab/iDeer•1010 issues in AI45Lab/iDeer•33 pull requests in AI45Lab/iDeer•Updated Jul 26, 2026Jul 26, 2026

• OpenRT

  Public
  Open-source red teaming framework for MLLMs with 42+ attack methods

  high-throughputai-safetyred-teaming+ 3

  high-throughputai-safetyred-teamingmultimodal-llmsafety-evaluationagentic-attacks

  Python

  •

  GNU Affero General Public License v3.0

  •2323 forks in AI45Lab/OpenRT•278278 stars in AI45Lab/OpenRT•00 issues in AI45Lab/OpenRT•11 pull request in AI45Lab/OpenRT•Updated Jul 17, 2026Jul 17, 2026

• Code

  Public
  Agentic Agent Framework

  Rust

  •

  MIT License

  •66 forks in AI45Lab/Code•135135 stars in AI45Lab/Code•00 issues in AI45Lab/Code•22 pull requests in AI45Lab/Code•Updated Jul 2, 2026Jul 2, 2026

• Box

  Public
  MicroVM Runtime

  Rust

  •

  MIT License

  •77 forks in AI45Lab/Box•5353 stars in AI45Lab/Box•33 issues in AI45Lab/Box•11 pull request in AI45Lab/Box•Updated Jul 1, 2026Jul 1, 2026

• SentrySkills

  Public
  LLM-native skill package that teaches agents to protect themselves

  Python

  •

  MIT License

  •11 fork in AI45Lab/SentrySkills•99 stars in AI45Lab/SentrySkills•00 issues in AI45Lab/SentrySkills•00 pull requests in AI45Lab/SentrySkills•Updated Jun 25, 2026Jun 25, 2026

• TrinityGuard

  Public

  AI45Lab/TrinityGuard’s past year of commit activity
  TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems

  Python

  •

  MIT License

  •2424 forks in AI45Lab/TrinityGuard•220220 stars in AI45Lab/TrinityGuard•22 issues in AI45Lab/TrinityGuard•00 pull requests in AI45Lab/TrinityGuard•Updated Jun 25, 2026Jun 25, 2026

• PseudoBench

  Public
  Python

  •

  MIT License

  •11 fork in AI45Lab/PseudoBench•22 stars in AI45Lab/PseudoBench•11 issue in AI45Lab/PseudoBench•00 pull requests in AI45Lab/PseudoBench•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

  •00 forks in AI45Lab/HomeGuard•1515 stars in AI45Lab/HomeGuard•11 issue in AI45Lab/HomeGuard•00 pull requests in AI45Lab/HomeGuard•Updated Jun 21, 2026Jun 21, 2026

• ClawSentry

  Public
  Python

  •

  MIT License

  •11 fork in AI45Lab/ClawSentry•1919 stars in AI45Lab/ClawSentry•11 issue in AI45Lab/ClawSentry•00 pull requests in AI45Lab/ClawSentry•Updated Jun 14, 2026Jun 14, 2026

• AgentDoG

  Public
  A Diagnostic Guardrail Framework for AI Agent Safety and Security

  Python

  •3535 forks in AI45Lab/AgentDoG•702702 stars in AI45Lab/AgentDoG•00 issues in AI45Lab/AgentDoG•11 pull request in AI45Lab/AgentDoG•Updated Jun 8, 2026Jun 8, 2026

• skill-safety-bench

  Public
  Python

  •

  Apache License 2.0

  •44 forks in AI45Lab/skill-safety-bench•3333 stars in AI45Lab/skill-safety-bench•11 issue in AI45Lab/skill-safety-bench•00 pull requests in AI45Lab/skill-safety-bench•Updated May 14, 2026May 14, 2026

• AgentHarnessProtocol

  Public
  Agent Harness Protocol (AHP)

  Rust

  •

  MIT License

  •00 forks in AI45Lab/AgentHarnessProtocol•44 stars in AI45Lab/AgentHarnessProtocol•00 issues in AI45Lab/AgentHarnessProtocol•00 pull requests in AI45Lab/AgentHarnessProtocol•Updated May 5, 2026May 5, 2026

• ai45lab.github.io

  Public
  ai45lab.github.io

  TypeScript

  •00 forks in AI45Lab/ai45lab.github.io•00 stars in AI45Lab/ai45lab.github.io•00 issues in AI45Lab/ai45lab.github.io•00 pull requests in AI45Lab/ai45lab.github.io•Updated Apr 27, 2026Apr 27, 2026

• ScientificSafetyLevels

  Public
  SSL: Scientific Safety Levels for Responsible Autonomous Science

  11 fork in AI45Lab/ScientificSafetyLevels•22 stars in AI45Lab/ScientificSafetyLevels•00 issues in AI45Lab/ScientificSafetyLevels•00 pull requests in AI45Lab/ScientificSafetyLevels•Updated Apr 16, 2026Apr 16, 2026

• Human-like-Interactive-Evaluation

  Public
  Python

  •

  MIT License

  •22 forks in AI45Lab/Human-like-Interactive-Evaluation•33 stars in AI45Lab/Human-like-Interactive-Evaluation•00 issues in AI45Lab/Human-like-Interactive-Evaluation•00 pull requests in AI45Lab/Human-like-Interactive-Evaluation•Updated Apr 13, 2026Apr 13, 2026

• SafeClaw

  Public
  Secure Personal AI Assistant with TEE Support

  11 fork in AI45Lab/SafeClaw•2323 stars in AI45Lab/SafeClaw•00 issues in AI45Lab/SafeClaw•00 pull requests in AI45Lab/SafeClaw•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+ 3

  watermarkvideo-watermarkimage-watermarktext-watermarkaudio-watermarkingdeepfake-detection

  Jupyter Notebook

  •55 forks in AI45Lab/UniMark•1919 stars in AI45Lab/UniMark•00 issues in AI45Lab/UniMark•00 pull requests in AI45Lab/UniMark•Updated Apr 1, 2026Apr 1, 2026