
OpenShell
Sandboxed runtime for autonomous AI agents with declarative YAML policies enforcing filesystem, network, and process constraints, plus endpoint-bound…

Sandboxed runtime for autonomous AI agents with declarative YAML policies enforcing filesystem, network, and process constraints, plus endpoint-bound…

Secure, private AI agent operating system with local encrypted storage, OAuth/SSO authentication, policy-based access control, and extensible…

Security control plane for LLM agents: allowlists, owner kill switch, PIN sessions, rate limits, prompt-injection detection, and output scrubbing to…

A HTTP credential proxy and vault for AI agents like Claude Code, OpenClaw, Hermes, custom agents + harnesses, and more.

Secure agents in seconds with permissions enforced at runtime.

Safety cannot be a prompt instruction. TBP provides an external execution-layer boundary for autonomous agents, enforcing hard F/I/W invariants via…

An open-source framework for verifiably private AI inference

Security gateway for MCP servers with per-tool policy enforcement, Ed25519-signed audit receipts, and shadow-mode logging. Supports Cedar, OPA, and…

Governed execution cells for AI agents.

Agent Control Protocol (ACP) — Official English specification. Cryptographically verifiable authorization architecture for autonomous AI agents.

Ed25519 signed receipts + Cedar policies for AI agents. Finance mandate gate (Legate), proof packs, 3 IETF Internet-Drafts. npx protect-mcp

Overlay network protocol giving AI agents permanent addresses, authenticated encrypted tunnels, and a trust model over UDP. Includes NAT traversal,…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord,…

cMCP: Confidential MCP Gateway. Hardware-attested policy enforcement for MCP tool calls.

Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

Cryptographically signed delegation receipts for AI agents. Define exactly what an AI can and can't do — signed, verifiable, tamper-proof.

The Governed Agentic AI Operating System — Rust + Tauri 2.0 | 65 crates, 658 commands, 84 pages, 5,029 tests, 10/10 OWASP