Search

面向安全靶场的自主渗透 Agent：ReAct 双层架构 · 三层记忆 · 可自我扩展的 pentool 工具注册表，内核为 600 行 TypeScript nano-pi

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

Read-only scanner for prompt-injection and LLM anti-analysis text in files before agent review

Gate LangChain tool calls behind a Fidacy verdict. Wraps the tool itself, so a denied payment never executes: callbacks can only observe, this can stop.

Aegis ATV — Action Firewall + cryptographic audit chain for Claude Code (and OpenClaw, preview)

A fail-closed, fully-local, no-account in-loop verifier for AI-written code: deterministic checks the instant your agent writes, and it never claims 'safe'.

Open source computer-use agent — control your computer with natural language or voice

Universal AIGP (AI Governance Protocol) client — consent-based runtime AI governance

Sanitize LLM outputs before HTML, SQL, shell, or markdown sinks. Python port of @mukundakatta/llm-output-sanitizer.

Trace cross-file dependency blast radius with GitLab Orbit, before you break things.

TypeSafe AI driven agent tool execution guard for Claude Code hooks

Windows computer-use MCP server (26 tools) with a human-in-the-loop approval gate: physical-input-only dialogs, signed guard switches, deny/launch lists, hash-chained audit log. 70+ unit tests, green CI.

Odyssey: Empowering Minecraft Agents with Open-World Skills

A dotfile-driven firewall that protects the OS from destructive LLM agent tool calls

Aegis Python SDK -- policy-based tool guarding and LLM/agent observability (tracing, cost, redaction) for AI agents

A Node.js CLI wrapper for NVIDIA SkillSpector to evaluate AI agent skills

Public Preview — Agent Hypervisor: Runtime supervisor for multi-agent Shared Sessions with Execution Rings, Joint Liability, Saga Orchestration, and hash-chained audit trails

A Node.js CLI wrapper for NVIDIA SkillSpector to evaluate AI agent skills

Universal TIBET provenance for ANY Python code. @tibet_guard decorator, ASGI middleware, agent safety. OWASP LLM06 compliant.

AgentMesh trust layer integration for LangChain - cryptographic identity and trust-gated tool execution