Guardrails for secure and robust agent development
☆436Jan 12, 2026Updated 6 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.☆78Nov 6, 2025Updated 8 months ago
- A better way of testing, inspecting, and analyzing AI Agent traces.☆59Jan 12, 2026Updated 6 months ago
- Security scanner for AI agents, MCP servers and agent skills.☆2,833Updated this week
- Code snippets to reproduce MCP tool poisoning attacks.☆200Apr 10, 2025Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆694Jun 2, 2026Updated last month
- 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.
- MCPSafetyScanner - Automated MCP safety auditing and remediation using Agents. More info: https://www.arxiv.org/abs/2504.03767☆176Apr 10, 2025Updated last year
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆113Mar 12, 2024Updated 2 years ago
- Learning Certified Individually Fair Representations☆25Nov 7, 2020Updated 5 years ago
- MCPCorpus is a comprehensive dataset for analyzing the Model Context Protocol (MCP) ecosystem, containing ~14K MCP servers and 300 MCP cl…☆34Sep 1, 2025Updated 10 months ago
- SRI Group Website☆12Updated this week
- A comprehensive security checklist for MCP-based AI tools. Built by SlowMist to safeguard LLM plugin ecosystems.☆835Apr 28, 2025Updated last year
- Security scanner for MCP servers☆554Apr 26, 2025Updated last year
- ☆21Feb 3, 2025Updated last year
- ☆101Jan 30, 2026Updated 5 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.
- PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents☆31Mar 26, 2025Updated last year
- MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols☆35Mar 4, 2026Updated 4 months ago
- A curated list of awesome resources about LLM supply chain security (including papers, security reports and CVEs)☆105Jan 20, 2025Updated last year
- [ICML'25] MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents☆37Jul 31, 2025Updated 11 months ago
- Protection against Model Serialization Attacks☆752Feb 18, 2026Updated 5 months ago
- A security scanner for your LLM agentic workflows☆1,021Nov 27, 2025Updated 8 months ago
- ☆154Jul 2, 2024Updated 2 years ago
- Adding guardrails to large language models.☆7,224Updated this week
- the LLM vulnerability scanner☆8,618Updated 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.
- Set of tools to assess and improve LLM security.☆4,318Updated this week
- ☆29Aug 31, 2025Updated 10 months ago
- The Security Toolkit for LLM Interactions☆3,200Jul 8, 2026Updated 3 weeks ago
- Every practical and proposed defense against prompt injection.☆716Feb 22, 2025Updated last year
- NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.☆6,829Updated this week
- ☆225Dec 16, 2025Updated 7 months ago
- [NeurIPS 2024 / ICML 2025] LLM Quantization Attacks☆53May 11, 2026Updated 2 months ago
- Security Threats related with MCP (Model Context Protocol), MCP Servers and more☆50Apr 24, 2025Updated last year
- Official release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks☆53May 6, 2026Updated 2 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆86Apr 24, 2026Updated 3 months ago
- Repo for the paper "Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks".☆70Jun 11, 2026Updated last month
- A demonstration toolkit revealing potential security vulnerabilities in MCP (Model Context Protocol) frameworks through data poisoning, J…☆98Jul 6, 2025Updated last year
- All about llm-agents security,attack,vulnerabilities and how to do them for cybersecurity.☆54Jul 11, 2026Updated 2 weeks ago
- Code for the paper "Defeating Prompt Injections by Design"☆360Jun 20, 2025Updated last year
- ☆17Jun 23, 2026Updated last month
- GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation, and Risk-Attenuating Information Limits☆17Jul 21, 2025Updated last year