AHA is autoresearch for agent safety: one agent red-teams a production agent overnight and comes back with reusable explanations of why that agent breaks, ready to fire again on new tasks.
☆38Sep 26, 2026Updated last month
Alternatives and similar repositories for Auto-research-red-teaming
Users that are interested in Auto-research-red-teaming are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents☆17Oct 10, 2026Updated last month
- The Official Implementation of "SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment"☆22Sep 2, 2026Updated 2 months ago
- “ToolHazard: Scalable Red Teaming of LLM Agents via Adversarial Tool-Interactive Environment and Task Synthesis”☆15Aug 18, 2026Updated 2 months ago
- Agent3Sigma-Stage is an end-to-end security evaluation framework for autonomous agents (e.g., OpenClaw)☆17Jul 6, 2026Updated 4 months ago
- [ACL 2026] PIArena: A Platform for Prompt Injection Evaluation☆57Aug 31, 2026Updated 2 months 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.
- Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.☆41Updated this week
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆40Jul 31, 2026Updated 3 months ago
- [ICLR 2026] Fewer Weights, More Problems: A Practical Attack on LLM Pruning☆14Apr 6, 2026Updated 7 months ago
- A Trustworthy Machine Learning Algorithm Library☆12Jul 1, 2024Updated 2 years ago
- ☆18Mar 25, 2026Updated 7 months ago
- ☆104Updated this week
- One command to benchmark AI guardrails and coding agents across safety, security, jailbreak, prompt-injection, and secure-code tasks.☆19Jun 26, 2026Updated 4 months ago
- ☆33May 14, 2026Updated 5 months ago
- Official implementation of the paper "AWM: Accurate Weight-Matrix Fingerprint for Large Language Models"☆13Feb 20, 2026Updated 8 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆13Oct 7, 2025Updated last year
- ☆10May 23, 2025Updated last year
- Official Code for Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification.☆22Jul 1, 2026Updated 4 months ago
- A Framework for Evaluating AI Agent Safety in Realistic Environments☆39Aug 10, 2026Updated 3 months ago
- ☆20Updated this week
- PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents☆32Mar 26, 2025Updated last year
- A nano re-implementation of Cordis and DeepSeek Harness, an AI agent runtime built out of plugins, small enough to read in an afternoon.☆15Aug 18, 2026Updated 2 months ago
- Data for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder"☆20Oct 26, 2023Updated 3 years ago
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆18Jun 2, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Pwning AI Code Interpreters for fun and profit - by Phantom Labs☆28Aug 3, 2026Updated 3 months ago
- WebView-only Sub2API price monitor with single-exe releases☆21Jul 13, 2026Updated 3 months ago
- A benchmark for AI agents as teammates. Paper: https://arxiv.org/abs/2611.02633☆25Updated this week
- An automated pipeline that leverages LLM's meta-learning capability to iteratively design and refine red-teaming systems without human in…☆32May 24, 2026Updated 5 months ago
- A system that turns jailbreak papers into runnable attacks and benchmarks — live, as research evolves.☆174Updated this week
- ☆13Feb 24, 2025Updated last year
- Röttger et al. (2025): "MSTS: A Multimodal Safety Test Suite for Vision-Language Models"☆21Mar 31, 2025Updated last year
- ☆29Aug 31, 2025Updated last year
- Official implementation of "HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety"☆22Aug 19, 2026Updated 2 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.
- Official Implementation for the paper "The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Co…☆15Apr 15, 2026Updated 6 months ago
- ☆15Sep 14, 2026Updated last month
- Technical Advisory – Hash Denial-of-Service Attack in Multiple QUIC Implementations☆11May 7, 2025Updated last year
- [ICLR 2025] This repo is the official implementation of "The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs".☆13Jan 25, 2025Updated last year
- Artifacts for SoK: Can Trajectory Generation Combine Privacy and Utility?☆15Jun 27, 2024Updated 2 years ago
- Safety guardrails for LLM-enabled robots☆17Oct 1, 2025Updated last year
- [AAAI 2026] The official code for ``LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generation''☆17Mar 20, 2026Updated 7 months ago
Are these results useful?