Official codebase for the paper "Auditing Agent Harness Safety"
☆58Oct 12, 2026Updated last month
Alternatives and similar repositories for HarnessAudit
Users that are interested in HarnessAudit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2026] Official codebase for the paper "WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction"☆33May 29, 2026Updated 5 months ago
- [NeurIPS 2025] More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models☆84May 31, 2025Updated last year
- ☆10Oct 7, 2026Updated last month
- A safety evaluation framework for agents.☆15Jul 23, 2026Updated 3 months ago
- Safety benchmark for personal AI agents under realistic prompt injection. 120 test cases across 5 professional domains, 3 injection vecto…☆20Apr 15, 2026Updated 6 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Proof search with a diversity-balanced symbolic frontier, bounded future atlas, and optional language-model guidance.☆22Oct 21, 2026Updated 3 weeks ago
- [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"☆38Jun 23, 2025Updated last year
- Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (…☆245Sep 13, 2026Updated last month
- CD-LAM is a LAM-side causal debiasing method for continuous latent actions. CD-LAM keeps the downstream action conditioning format unchan…☆21Jul 21, 2026Updated 3 months ago
- ☆29Aug 31, 2025Updated last year
- The code for paper "MemGym: a Long-Horizon Memory Environment for LLM Agents".☆23Jun 2, 2026Updated 5 months ago
- MyPhoneBench: Do Phone-Use Agents Respect Your Privacy?☆26Apr 3, 2026Updated 7 months ago
- ☆20Aug 30, 2026Updated 2 months ago
- ☆22Sep 30, 2026Updated last month
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [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
- ☆39Jun 13, 2026Updated 4 months ago
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆86Nov 5, 2026Updated last week
- Contextualized Logic☆13Jun 8, 2024Updated 2 years ago
- Implementation and datasets for "Training Language Models to Generate Quality Code with Program Analysis Feedback"☆43Jul 21, 2025Updated last year
- [SIGGRAPH Asia 2025] The official implementation of the paper "DvD: Unleashing a Generative Paradigm for Document Dewarping via Coordinat…☆36Mar 10, 2026Updated 8 months ago
- Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI☆39Updated this week
- ☆11Mar 15, 2025Updated last year
- Data and code for ACL 2026 Paper "Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems…☆23Apr 30, 2026Updated 6 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 Code for Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification.☆22Jul 1, 2026Updated 4 months ago
- [CICAI2026] Efficiently creating diverse multi-turn Text-to-SQL training samples in 3 steps! 🚀☆15Oct 7, 2026Updated last month
- FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments☆21Jun 4, 2026Updated 5 months ago
- Code for COLM 2026 Paper "Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs"☆36Jul 1, 2026Updated 4 months ago
- [CVPR 2026] Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning☆43Sep 27, 2026Updated last month
- SafeHarness: Security-Aware Harness Architecture for Safe AI Agent Deployment☆18May 12, 2026Updated 6 months ago
- ☆21Apr 7, 2025Updated last year
- 1,017 system prompts from real AI products, audited span by span against the eight AISPA assurance dimensions☆37Oct 13, 2026Updated 3 weeks ago
- ☆15Feb 11, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Evaluating Agent Safety in Realistic, High-Risk Simulations☆42Aug 10, 2026Updated 3 months ago
- 🥇 Amazon Nova AI Challenge Winner - ASTRA emerged victorious as the top attacking team in Amazon's global AI safety competition, defeati…☆78May 11, 2026Updated 6 months ago
- Reference implementation for DPO (Direct Preference Optimization)☆13Jan 18, 2024Updated 2 years ago
- ☆70May 21, 2025Updated last year
- Gathers data science and machine learning problem solving using PySpark and Hadoop.☆11Jan 22, 2019Updated 7 years ago
- Phare is a LLM benchmark that evaluates models across key AI security & safety dimensions☆13Dec 11, 2025Updated 11 months ago
- Wiki Knowledge Compiler: Turn your documents into a personal LLM knowledge base☆12Apr 13, 2026Updated 6 months ago
Are these results useful?