#zero-trust

Local-first, zero-trust agentic IDE for verifiable autonomous software development.

Zero-trust repo intake for AI coding agents — scan the instruction environment before Claude Code, Cursor, Codex, or Gemini touches a repo. Ships its own false-negative ledger.

Proxilion is the security layer for the agentic workforce. It turns managed AI agents into governed users by enforcing strict cryptographic boundaries on every API call to SaaS like Google Workspace, Salesforce, or Atlassian.

Bounded Agents: Delegation Security for Multi-Agent AI Systems - Reference Implementation and Evaluation Artifact

A JSON-RPC firewall for MCP agents — inspects every tools/call between an LLM and its MCP servers, blocking argument injection and capability creep before they reach the host.

P2P-Hub is a local-first application framework and peer-to-peer runtime. It turns any device on your LAN into an active peer that can securely host capabilities, publish static websites, route tasks between agents, and run local AI workflows — all without central infrastructure.