Search

🐾 Self-hosted AI agent framework — OpenClaw-inspired, Docker-ready, LLM-powered

Python SDK for Agent Control - protect your AI agents with controls

Agent-action safety SDK: gate irreversible actions, commit exactly once, tamper-evident audit.

JavaScript SDK for checking AI agent actions before they run.

Ed25519 signed decision receipts for kyegomez/swarms multi-agent systems. Wrap any tool in a Swarms agent with tamper-evident, offline-verifiable receipts in the Veritas Acta format (IETF draft-farley-acta-signed-receipts).

SENTINEL — Drop-in LLM Trust & Safety SDK. 19-agent parallel mesh: prompt injection, PII, jailbreak pattern detection, DAN attacks, cost anomaly detection, agentic loop breaking, hallucination, and compliance routing.

Detect system prompt leakage in LLM model outputs via known patterns, configured-prompt substring matching, and unique fingerprint phrases. Python port of @mukundakatta/system-prompt-leak-scan.

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Hacker-style AI red team terminal — WAF bypass, hash crack, multi-model

Know Your Agent — trust scoring for AI agents. Check any wallet's trust score, verify ERC-8004 identity, get tier. Zero dependencies.

Parallel multi-agent pipeline for code analysis and transformation.

Autonomous reverse-engineering agent with a source-aware reverser/checker loop, objective verification, parity checks, and a Ghidra backend

FailSafe governance adapter for Microsoft Agent Governance Toolkit

Zero-config agentegrity adapter for the OpenAI Agents JS SDK (@openai/agents). Mirrors the Python agentegrity.openai_agents module.

PII redaction guardrails for OpenAI Agents SDK

Official JavaScript/TypeScript SDK for the Execlave AI agent governance platform — tracing, policy enforcement, and framework auto-instrumentation for LangChain

Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude Code and OpenAI Codex.

Adversarial resilience testing for multi-agent ecosystems

A local proxy that transparently injects API credentials into outbound HTTPS requests. Your apps and AI agents never hold real secrets.

Dynamic AI Agent Framework - Create, orchestrate, and manage AI agents with YAML configs, MCP tool integration, and linear workflow execution using AutoGen and Google Gemini.