Search

just-bash provider for ComputeSDK - local sandboxed bash execution with virtual filesystem

An http(s).Agent implementation that block request Private IP address.

Drop-in trust enforcement for AI agent frameworks — Vercel AI SDK, and more

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

KYA (Know Your Agent) identity verification for LangChain agents

LangChain middleware for the EISFI Weaver integrity chain: a tool call whose integrity precondition fails is never executed.

VulnClaw penetration-testing mode for the DeepSeek Harness: nmap, HTTP probing, directory/JS recon, traffic evidence, reports and PoCs as native Harness tools. Based on VulnClaw (MIT) by UncleC.

Linter, scorer, and evaluator for AI agent skill files (Agent Skills spec)

AI agent governance framework with audit trails, safety checks, and replayable decision making for autonomous systems

Cryptographic identity and trust for AI agents

LLM-driven pentest/CTF agent harness: scope-enforced, sandboxed, audit-logged

PII redaction guardrails for OpenAI Agents SDK

TypeScript SDK client for the Argentor AI agent framework REST API

Local secret vault for LLM-safe environments — encrypted secrets that agents can't bulk-discover

AgentGuard installation entry point

Forge Verify tools and guardrails for CrewAI — verify every agent action before execution

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

Read-only reliability and safety auditor for AI agent repositories

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

EMILIA Protocol guard for LangChain tools: a named human approves the exact irreversible action (Face ID / passkey) before it executes — fail-closed, with offline-verifiable Trust Receipts.