A Framework for Evaluating AI Agent Safety in Realistic Environments
☆38Aug 10, 2026Updated 3 weeks ago
Alternatives and similar repositories for OpenAgentSafety
Users that are interested in OpenAgentSafety are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- TRACE, a framework for turn-aware credit assignment for multi-turn jailbreak optimization☆22Updated this week
- ☆14Jan 12, 2022Updated 4 years ago
- AgentWard – Built for all, hardened for OpenClaw.☆64Jun 4, 2026Updated 2 months ago
- Official codebase for the paper "Auditing Agent Harness Safety"☆53May 19, 2026Updated 3 months ago
- The Code for the EMNLP 2023 main conference paper "Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition…☆13Dec 10, 2023Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [ICML 2026] Official implementations of ``SafeSearch: Automated Red-Teaming of LLM-Based Search Agents''☆19Mar 25, 2026Updated 5 months ago
- Official implementation of Vector-ICL: In-context Learning with Continuous Vector Representations (ICLR 2025)☆24Jun 2, 2025Updated last year
- ☆67May 21, 2025Updated last year
- AIR-Bench 2024 is a safety benchmark that aligns with emerging government regulations and company policies☆30Aug 14, 2024Updated 2 years ago
- [COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model☆26Nov 25, 2025Updated 9 months ago
- About Official PyTorch implementation of "Query-Efficient Black-Box Red Teaming via Bayesian Optimization" (ACL'23)☆15Jul 9, 2023Updated 3 years ago
- Benchmarking Dark Patterns in LLMs (ICLR 2025)☆18Mar 29, 2025Updated last year
- Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"☆53Updated this week
- ☆27Mar 17, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- State-of-the-art neural tagger and lemmatizer for ancient languages☆16Aug 13, 2026Updated 2 weeks ago
- ☆48Dec 9, 2025Updated 8 months ago
- Agent Security Bench (ASB)☆292Apr 16, 2026Updated 4 months ago
- ☆83Mar 30, 2025Updated last year
- ☆26May 28, 2025Updated last year
- Code for "Neural Retrievers are Biased Towards LLM-Generated Content"☆14Oct 18, 2024Updated last year
- Slightly patched clone of canonical gevel project from Teodor Sigaev☆12Dec 16, 2021Updated 4 years ago
- Source code of "Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers" EMNLP 2025☆17Jan 12, 2026Updated 7 months ago
- Consuming Resrouce via Auto-generation for LLM-DoS Attack under Black-box Settings☆25Sep 1, 2025Updated 11 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆24Jun 16, 2025Updated last year
- The official code for ``An Engorgio Prompt Makes Large Language Model Babble on''☆24Aug 9, 2025Updated last year
- Mobile GUI Agents under Real-world Threats: Are We There Yet?☆18Aug 4, 2026Updated 3 weeks ago
- ☆17Nov 3, 2024Updated last year
- DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching☆25Apr 15, 2026Updated 4 months ago
- Code and data for the paper: IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Large Language Models …☆12Apr 27, 2024Updated 2 years ago
- [ICLR 2022] "Sparsity Winning Twice: Better Robust Generalization from More Efficient Training" by Tianlong Chen*, Zhenyu Zhang*, Pengjun…☆40Mar 20, 2022Updated 4 years ago
- Stateless Network Fuzzer for QEMU (Targeting SLiRP)☆17Oct 19, 2020Updated 5 years ago
- Kuintessence is an advanced computing orchestration system designed to revolutionize HPC workload and cluster management, to empower HPC …☆13Mar 20, 2024Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- pytorch implement of Label Smoothing☆32Dec 16, 2019Updated 6 years ago
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆89Feb 26, 2025Updated last year
- Code used for "Training Agents to Self-Report Misbehavior"☆18Feb 27, 2026Updated 6 months ago
- ☆12Jul 25, 2023Updated 3 years ago
- [NeurIPS 2024 poster] Cross-model Control: Improving Multiple Large Language Models in One-time Training☆15Oct 25, 2024Updated last year
- [ACL 2025] LongSafety: Evaluating Long-Context Safety of Large Language Models☆16Jun 18, 2025Updated last year
- ☆132Jul 29, 2026Updated last month