Skip to content
@opena2a-org

opena2a.org

Open-source security for AI agents
README.md

OpenA2A

OpenA2A builds the trust layer for AI agents. Agents now act on people's behalf, calling APIs, querying data, and executing tasks, without the identity, authorization, audit, and trust primitives traditional infrastructure has had for decades. OpenA2A fills that gap with open, self-hostable tools and open standards, vendor-neutral by design, so no single platform owns the layer that verifies its own agents.

Built by and for the developers, security teams, and researchers working on AI agents.

Visit opena2a.org to learn more.

Pinned Loading

  1. opena2a opena2a Public

    Open-source security tools for AI agents. Find vulnerabilities, fix root causes, prove compliance.

    TypeScript 14 5

  2. hackmyagent hackmyagent Public

    Security toolkit for AI agents - verify skills, harden setups, scan for exposures

    TypeScript 28 2

  3. agent-identity-management agent-identity-management Public

    AIM - The open-source NHI platform for AI agents. Cryptographic identity, governance, and access control.

    Go 45 14

  4. ai-trust ai-trust Public

    Trust check for AI packages before you install them. ai-trust check <pkg> returns a 0-100 score from the OpenA2A Registry, covering security scans, advisories, and community consensus. For MCP serv…

    TypeScript 2

  5. secretless-ai secretless-ai Public

    One command to keep secrets out of AI (LLMs). Works with Claude Code, Cursor, Copilot, Windsurf, and any AI coding tool.

    TypeScript 19 4

  6. nanomind nanomind Public

    On-device models that detect and classify AI agent attacks. A 2M-param classifier (<1ms, offline) and a 1.7B-param analyst, shipping inside HackMyAgent, Secretless, and the OpenA2A CLI.

    Python 2

Repositories

Showing 10 of 21 repositories
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…