A Framework for Evaluating AI Agent Safety in Realistic Environments
☆39Aug 10, 2026Updated 2 months 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:
- An Adversarial Co-Evolution Framework for LLM Agent Safety☆33Oct 16, 2026Updated 2 weeks ago
- TRACE, a framework for turn-aware credit assignment for multi-turn jailbreak optimization☆22Aug 26, 2026Updated 2 months ago
- Code for paper "JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills."☆27Sep 3, 2026Updated last month
- Official Code for Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification.☆21Jul 1, 2026Updated 3 months ago
- The repository of the NeurIPS25 paper: Contextual Integrity in LLMs via Reasoning and Reinforcement Learning.☆16Jun 8, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆13Sep 29, 2025Updated last year
- AHA is autoresearch for agent safety: one agent red-teams a production agent overnight and comes back with reusable explanations of why t…☆37Sep 26, 2026Updated last month
- Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation☆16Apr 23, 2025Updated last year
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆18Jun 2, 2025Updated last year
- Official codebase for the paper "Auditing Agent Harness Safety"☆57Oct 12, 2026Updated 2 weeks ago
- [EMNLP 2025] The code repo of paper "X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Com…☆40Nov 24, 2025Updated 11 months ago
- Official Repository for "WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented Dialogue"…☆11Oct 7, 2025Updated last year
- A curated list of LLM/MLLM guardrails, safety benchmarks, guard models, jailbreak attacks, moderation datasets, and evaluation tools.☆39Oct 7, 2026Updated 3 weeks ago
- [ICML 2026] Official implementations of ``SafeSearch: Automated Red-Teaming of LLM-Based Search Agents''☆20Mar 25, 2026Updated 7 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Official code for the paper: "Multi-User Large Language Model Agents"☆36Sep 1, 2026Updated last month
- ICLR 206☆14Aug 18, 2026Updated 2 months ago
- ☆70May 21, 2025Updated last year
- AIR-Bench 2024 is a safety benchmark that aligns with emerging government regulations and company policies☆31Aug 14, 2024Updated 2 years ago
- Official implementation of "HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety"☆21Aug 19, 2026Updated 2 months ago
- [COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model☆26Nov 25, 2025Updated 11 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)☆19Mar 29, 2025Updated last year
- Official implementation of Vector-ICL: In-context Learning with Continuous Vector Representations (ICLR 2025)☆25Jun 2, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- The official implementation of "Interpreting the repeated token phenomenon in LLMs"☆15Sep 23, 2025Updated last year
- Security scanner for MCP servers. Every finding carries its evidence, including the server's actual response bytes.☆12Sep 4, 2026Updated last month
- ☆17Feb 8, 2026Updated 8 months ago
- 🧠 Useful utility functions and wrappers for hooking onto layers within PyTorch models for feature extraction.☆12Sep 29, 2024Updated 2 years ago
- ☆49Dec 9, 2025Updated 10 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆103May 9, 2025Updated last year
- ☆26May 28, 2025Updated last year
- [NeurIPS 2026] The official implementation of our NeurIPS 2026 paper "When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-…☆14Sep 25, 2026Updated last month
- ☆85Mar 30, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"☆59Oct 15, 2026Updated 2 weeks ago
- Consuming Resrouce via Auto-generation for LLM-DoS Attack under Black-box Settings☆25Sep 1, 2025Updated last year
- Source code of "Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers" EMNLP 2025☆18Jan 12, 2026Updated 9 months ago
- 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?☆19Aug 4, 2026Updated 2 months ago
- ☆50Mar 29, 2026Updated 7 months ago
- PIBench is an open-source benchmark for evaluating AI coding agents on realistic, end-to-end payment integration tasks.☆27Aug 6, 2026Updated 2 months ago