opena2a.org
Organization@opena2a-org
Open-source security for AI agents
10
Published Tools
138
Total Stars
373
Weekly Downloads
31
GitHub Followers
22
Public Repos
Published Tools
3 MCP Servers5 Skills2 Agentsacross 5 categoriesecolibria
Find it. Break it. Fix it. The hacker's toolkit for AI agents.
ecolibria
One command to keep secrets out of AI. Works with Claude Code, Cursor, Copilot, Windsurf, and any AI coding tool.
opena2a-org
Production hardening guide for AI agents — prompt injection defense, tool sandboxing, and credential management
OpenA2A
Inline PII, credential, and regulated-data classifier for AI agent I/O. Dual-layer: deterministic regex + optional semantic Guard. Library + CLI. Python port of @opena2a/aicomply.
...moreGitHub Actions
Persistent NanoMind inference daemon with HTTP and IPC interfaces
GitHub Actions
Spec-compliant offline verifier for ATX (Agent Trust eXtension) credentials — Ed25519 signature verification over the canonical payload (v1.0 pipe / v1.1 JCS RFC 8785), expiry, revocation, issuer-trust, and issuer-chain checks. Byte-for-byte interoperable
...moreGitHub Actions
Tier-1 anonymous usage telemetry SDK for OpenA2A CLIs and tools. Fire-and-forget, opt-out, no content collection.
GitHub Actions
Tier-based AI package classification (native / adjacent / unrelated) for OpenA2A trust tooling
GitHub Actions
HTTP client for the OpenA2A Registry trust query endpoints. Shared by hackmyagent, opena2a-cli, and ai-trust.