The open-source AISI toolkit for sandboxing agentic evaluations
☆35Aug 7, 2025Updated last year
Alternatives and similar repositories for aisi-sandboxing
Users that are interested in aisi-sandboxing 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 Inspect extension for agentic cyber evaluations☆47Updated this week
- LLM templates to share☆19Apr 17, 2025Updated last year
- Misalignment Bounty submission template☆19Aug 26, 2025Updated last year
- Collection of evals for Inspect AI☆748Updated this week
- In-depth analysis of AI agent transcripts.☆91Updated this week
- 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.
- ☆60Updated this week
- 🎮 A configurable Breakout environment for reinforcement learning☆11Mar 20, 2018Updated 8 years ago
- Source code of "TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification", ACL2024 (findings)☆17Nov 20, 2024Updated last year
- Experiments in eliciting shutdown avoidance☆11Updated this week
- ☆47Feb 18, 2026Updated 9 months ago
- Ultima scripts related to downstream processing of WGS, MRD, methylation analysis☆11Sep 24, 2026Updated last month
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆270Updated this week
- ☆10Jun 20, 2023Updated 3 years ago
- Adversarial and poisoning attacks against multimodal retrieval-augmented generation (RAG)☆12Nov 12, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Can LLMs be provable computers?☆65Apr 15, 2026Updated 7 months ago
- This repository contains a visual studio project for training a classifier on the mnist dataset using the libtorch c++ wrapper.☆12Oct 13, 2020Updated 6 years ago
- ☆67Apr 17, 2024Updated 2 years ago
- ☆18Dec 10, 2025Updated 11 months ago
- [ICLR 2026] Official Implementation of the paper: "Two are better than one: Context window extension with multi-grained self-injection"☆12Feb 1, 2026Updated 9 months ago
- Data Analysis of the results of llmail-inject challenge☆12Jul 1, 2025Updated last year
- [42-b3yond-6ug] This repository hosts BugBuster, our team’s submission to the AI Cyber Challenge Final Competition.☆31Aug 19, 2025Updated last year
- The source code that empowers OpenROAD Cloud☆15Jun 29, 2020Updated 6 years ago
- Official implementation of the U-Space and U-Lens for training-free, interpretable uncertainty tracing in language-model reasoning.☆15Oct 19, 2026Updated 3 weeks 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.
- ☆14Aug 31, 2026Updated 2 months ago
- Code library for the DRMD framework from 'DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift'.☆13Nov 14, 2025Updated last year
- AI Control for Claude Code☆34Sep 27, 2026Updated last month
- Test of http://www.malwaredomainlist.com/hostslist/hosts.txt☆14Updated this week
- ☆34Sep 3, 2026Updated 2 months ago
- Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.☆145Oct 13, 2026Updated last month
- ☆18Mar 25, 2026Updated 7 months ago
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]☆78Sep 18, 2025Updated last year
- ZeroEntropy's Evaluation Suite to Benchmark various retrievers and rerankers.☆15Mar 2, 2026Updated 8 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Lint your file tree based on file sizes☆16Nov 4, 2026Updated 2 weeks ago
- ☆12Mar 21, 2014Updated 12 years ago
- ⚖️ Code for the paper "Ethical Adversaries: Towards Mitigating Unfairness with Adversarial Machine Learning".☆11Dec 8, 2022Updated 3 years ago
- Point of Concept: To help to automate the collection of evidence for SOC 2 Audits and etc.☆11May 13, 2024Updated 2 years ago
- Trusted and Tested Asterisk Build for Call Control☆28Jul 13, 2016Updated 10 years ago
- ☆10Sep 10, 2020Updated 6 years ago
- Takes a software bill of materials and outputs provenance, and activity data from trustypkg.dev☆10May 19, 2025Updated last year
Are these results useful?