#zero-trust

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

Client-side HTTPS egress proxy for TokenSaver — MITM capture for Claude Code / Cursor / agents.

Offline repo inspection and change review for AI coding agents. Scan instructions, compare saved scans, explain findings, and export local reports.

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

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.

Coding agents that never see your credentials. Claude Code, Codex and pi in gVisor sandboxes on your own hardware, behind a credential broker, driven from your phone, browser, terminal or VS Code.

Cloudflare exporter for OpenTelemetry. Access logins, per-request HTTP, AI Gateway (GenAI semconv) and the rest of Cloudflare's non-Enterprise log surface as OTLP logs, metrics and traces. Single Go binary, Grafana Cloud ready.

Agent skill que controla TODO o Cloudflare por terminal — Workers, Pages, DNS, Tunnels, Zero Trust, R2/KV/D1 — e publica qualquer URL local no seu domínio num comando (?token= preservado), derruba em 0,3 s e prepara a máquina sozinha (instala cloudflared/Node, faz o login no browser).

A security guard for AI assistants. It checks every tool an AI tries to use, preventing data leaks and unauthorized commands.

Fail-closed control plane for agentic SDLC. Portable skills, evidence ladder, SPIFFE/WIMSE identity. Intent is not a grant.

🛡️ Zero-trust security gate & vulnerability scanner for AI agent skills (Claude Code, Antigravity, OpenCode, Codex). Powered by NVIDIA SkillSpector.

P2P-Hub is a desktop P2P app platform. It turns your laptop into a peer, that an agent like Hermes can work with. It offers basic chat, a basic office suite, and task management / budgetting