Guardrails for secure and robust agent development
☆427Jan 12, 2026Updated 5 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:
- A better way of testing, inspecting, and analyzing AI Agent traces.☆56Jan 12, 2026Updated 5 months ago
- LLM proxy to observe and debug what your AI agents are doing.☆74Nov 6, 2025Updated 7 months ago
- ToolFuzz is a fuzzing framework designed to test your LLM Agent tools.☆41Jul 20, 2025Updated 10 months ago
- Code snippets to reproduce MCP tool poisoning attacks.☆195Apr 10, 2025Updated last year
- Learning Certified Individually Fair Representations☆25Nov 7, 2020Updated 5 years ago
- 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.
- ☆97Jan 30, 2026Updated 4 months ago
- ☆21Feb 3, 2025Updated last year
- MCPSafetyScanner - Automated MCP safety auditing and remediation using Agents. More info: https://www.arxiv.org/abs/2504.03767☆173Apr 10, 2025Updated last year
- A curated list of awesome resources about LLM supply chain security (including papers, security reports and CVEs)☆105Jan 20, 2025Updated last year
- ☆11Jan 28, 2026Updated 4 months ago
- Example agents for the Dreadnode platform☆33Dec 19, 2025Updated 6 months ago
- Building self-refined guardrails via DSPy☆14Jul 2, 2024Updated last year
- The goal of this repo is to become a benchmark for pentesting☆23Oct 25, 2024Updated last year
- SRI Group Website☆11Jun 6, 2026Updated last week
- 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.
- An open source MCP proxy.☆18Jan 3, 2025Updated last year
- ☆57Oct 4, 2024Updated last year
- Set of tools to assess and improve LLM security.☆4,232Jun 12, 2026Updated last week
- A framework for evaluating the effectiveness of chain-of-thought reasoning in language models.☆19Feb 6, 2025Updated last year
- Evolving fuzzers with large language models☆17Dec 14, 2023Updated 2 years ago
- SSE to Stdio MCP Proxy Server☆30Mar 9, 2026Updated 3 months ago
- [NeurIPS 2024] Evaluation harness for SWT-Bench, a benchmark for evaluating LLM repository-level test-generation☆83Apr 28, 2026Updated last month
- Will send the same request to one or more sources to exchange cost for reduced latency for inference☆11Dec 17, 2024Updated last year
- A bash script that turns a version-controlled paper into a cool timelapse.☆14Mar 21, 2013Updated 13 years 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.
- ☆130Jul 14, 2024Updated last year
- 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
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆81Apr 24, 2026Updated last month
- A comprehensive security checklist for MCP-based AI tools. Built by SlowMist to safeguard LLM plugin ecosystems.☆829Apr 28, 2025Updated last year
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆90Sep 1, 2025Updated 9 months ago
- [NeurIPS 2024 / ICML 2025] LLM Quantization Attacks☆52May 11, 2026Updated last month
- The Security Toolkit for LLM Interactions☆3,067Dec 15, 2025Updated 6 months ago
- A duckdb extension that executes js (provided by you or generated via OpenAI) in an embedded v8 interpreter and returns a table☆19Jun 9, 2025Updated last year
- MCP Guard secures your MCP client from prompt injection attacks and more.☆53Updated 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.
- Adding guardrails to large language models.☆7,014Updated this week
- Damn Vulnerable MCP Server☆1,306Dec 8, 2025Updated 6 months ago
- ☆12Jun 7, 2025Updated last year
- Agent Security Bench (ASB)☆260Apr 16, 2026Updated 2 months ago
- ☆13Oct 21, 2021Updated 4 years ago
- MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols☆35Mar 4, 2026Updated 3 months ago
- Auditing agents for fine-tuning safety☆21Oct 21, 2025Updated 7 months ago