Guardrails for secure and robust agent development
☆415Jan 12, 2026Updated 3 months ago
Alternatives and similar repositories for invariant
Users that are interested in invariant are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- LLM proxy to observe and debug what your AI agents are doing.☆72Nov 6, 2025Updated 6 months ago
- Let Claude control a web browser on your machine.☆44Jun 5, 2025Updated 11 months ago
- Code snippets to reproduce MCP tool poisoning attacks.☆192Apr 10, 2025Updated last year
- Learning Certified Individually Fair Representations☆24Nov 7, 2020Updated 5 years ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆548Mar 30, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆94Jan 30, 2026Updated 3 months ago
- ☆20Feb 3, 2025Updated last year
- MCPSafetyScanner - Automated MCP safety auditing and remediation using Agents. More info: https://www.arxiv.org/abs/2504.03767☆172Apr 10, 2025Updated last year
- A curated list of awesome resources about LLM supply chain security (including papers, security reports and CVEs)☆101Jan 20, 2025Updated last year
- Example agents for the Dreadnode platform☆33Dec 19, 2025Updated 4 months ago
- ☆10Apr 21, 2023Updated 3 years ago
- The goal of this repo is to become a benchmark for pentesting☆22Oct 25, 2024Updated last year
- First-of-its-kind AI benchmark for evaluating the protection capabilities of large language model (LLM) guard systems (guardrails and saf…☆62Mar 7, 2026Updated 2 months ago
- ☆57Oct 4, 2024Updated 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.
- mcp scan that scans any mcp server for indirect attack vectors and security or configuration vulnerabilities☆87May 2, 2026Updated last week
- Set of tools to assess and improve LLM security.☆4,162Updated this week
- A framework for evaluating the effectiveness of chain-of-thought reasoning in language models.☆19Feb 6, 2025Updated last year
- SSE to Stdio MCP Proxy Server☆24Mar 9, 2026Updated 2 months ago
- All about llm-agents security,attack,vulnerabilities and how to do them for cybersecurity.☆50Apr 8, 2026Updated last month
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆78Apr 24, 2026Updated 2 weeks ago
- ☆129Jul 14, 2024Updated last year
- A bash script that turns a version-controlled paper into a cool timelapse.☆14Mar 21, 2013Updated 13 years ago
- [NeurIPS 2024 / ICML 2025] LLM Quantization Attacks☆50Jan 15, 2026Updated 3 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.
- Benchmarking tool for assessing LLM models' performance across different hardwares☆17Dec 8, 2023Updated 2 years ago
- Do you want to learn AI Security but don't know where to start ? Take a look at this map.☆31Apr 23, 2024Updated 2 years ago
- Convex Layerwise Adversarial Training (COLT)☆29Jan 13, 2021Updated 5 years ago
- A comprehensive security checklist for MCP-based AI tools. Built by SlowMist to safeguard LLM plugin ecosystems.☆828Apr 28, 2025Updated last year
- The Security Toolkit for LLM Interactions☆2,925Dec 15, 2025Updated 4 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆87Sep 1, 2025Updated 8 months ago
- Certifying Geometric Robustness of Neural Networks☆16Mar 24, 2023Updated 3 years ago
- Agent Security Bench (ASB)☆231Apr 16, 2026Updated 3 weeks ago
- Damn Vulnerable MCP Server☆1,287Dec 8, 2025Updated 5 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.
- Adding guardrails to large language models.☆6,818Updated this week
- ☆12Jun 7, 2025Updated 11 months ago
- ☆13Oct 21, 2021Updated 4 years ago
- Protection against Model Serialization Attacks☆687Feb 18, 2026Updated 2 months ago
- Auditing agents for fine-tuning safety☆21Oct 21, 2025Updated 6 months ago
- TrustAgent: Towards Safe and Trustworthy LLM-based Agents☆56Feb 7, 2025Updated last year
- Code for evaluating AI systems on the MASK honesty benchmark.☆20Mar 6, 2025Updated last year