Search

A general immune system for LLM applications: two lines, every call, reflexes at every boundary.

Terminal proxy that intercepts AI agent shell commands and requires human confirmation before destructive operations

LangChain integration for TrustAgents - protected document loaders, retrievers, and threat scanning

Static analyzer for prompt injection and confused-deputy risks in LLM agent code.

Reverse proxy firewall + LLM Gateway for AI agents

The verifiable audit trail for AI agents. Off-box, hash-chained, tamper-evident record of what an agent did, independently verifiable. Observability you can take to court.

CLI to fetch markdown templates and sync AI agent skills

Hydra is a NodeJS light-weight library for building distributed computing applications such as microservices

Runtime EDR for AI agents — zero-code-change monitoring for LangChain, LangGraph, OpenAI Assistants, and the Anthropic SDK

Secret scanning CLI for Claude Code

AI agent for cybersecurity triage — ingests logs, PCAP & CVEs, returns threat explanation, attack path & mitigations (GPT + tool calling)

A hardened, containerized environment for running Claude Code as an AI agent with access to local tools via the Model Context Protocol (MCP).

Find the API keys and passwords your coding agents spilled into their logs: Claude Code, Codex, Gemini CLI, Cline and more. Scan, scrub, and block the next one.

Agent Control Specification: a stateless policy decision runtime implementing the agent-hooks interceptor contract.

LangChain / LangGraph integration for mnki (Agent Trust): guard tools so every call is verified against delegated authority, with evidence, before it runs.

Official Node/TypeScript SDK for InjectShield — prompt-injection firewall for AI agents.

Reproducible benchmark of denial-of-wallet attacks and defenses for LLM agents

Inspectable LangGraph coding agent with verified patches, resumable trajectories, sandboxed tools, and HMAC-authenticated Undo.

Local least-authority gateway connecting Web AI clients to user-approved developer resources.

v0.6 signing-time gate for Solana: decode any base64 tx offline, classify 37 danger primitives + Native Stake + bounded ATA/Memo recognition + a 14-program DeFi/NFT clear-signing registry, resolve ALTs and clear-sign Squads proposals with --rpc, optionall