AgentMux is the open-source AI agent control plane with architectural governance. Every interaction audited. Every agent accountable. Your data stays on your infrastructure.
AgentMux sits at the interaction layer — the routing point through which all AI agent requests and responses transit. Governance isn't bolted on. It's the architecture.
No data sent to AgentMux servers. No analytics. No phone-home. Verify in the source code.
All agent interactions stay on your machine. No cloud relay. No third-party data processors.
100% Rust — no buffer overflows, no use-after-free, no GC pauses. Compile-time memory safety.
Tokio async channels for inter-pane communication. No network exposure. Process-level isolation.
Building toward comprehensive coverage across the frameworks that matter most to regulated enterprises and government agencies.
Govern, Map, Measure, Manage — all four functions addressed
Audit trails, risk classification, human oversight, transparency
AI management system certification pathway
Trust service criteria audit in progress
Local-first architecture provides inherent data residency
Cryptographic module validation for government use
Every AI interaction produces a complete, tamper-evident record. The evidence regulators and auditors demand.
Open source means trust through transparency. Audit every line. Verify the build. No black boxes.
Apache 2.0. Full source available. Community-verified. No proprietary dependencies.
Memory-safe language with compile-time guarantees. No runtime vulnerabilities from GC or unsafe memory access.
cargo-audit integration for continuous vulnerability scanning of the dependency tree.
Signed binaries for Windows and macOS. Verifiable provenance for every release.
Deterministic build pipeline so anyone can verify the binary matches the source.
Software Bill of Materials for every release. Full dependency transparency.
From individual developer workstations to classified environments. Deploy AgentMux where your security requirements demand.
Standard installation on employee workstations. Every interaction logged locally with structured export.
IT-deployed with centralized policy presets. Agents launch with pre-approved configurations only.
Fully offline operation for classified and restricted environments. No internet connection required.
Enterprise-grade identity management for AI agents and their operators. Coming in Phase 3 (Claw).
Role-based agent permissions. Control which agents each team member can launch, which tools agents can access, and what data they can touch.
SAML and OIDC integration for single sign-on. Every agent session tied to an authenticated enterprise identity.
Smart card authentication for government and defense environments. Hardware-backed identity verification.
Every agent action attributable to an authenticated user session. Full chain of custody from human to outcome.
Whether you're preparing for EU AI Act compliance, building FedRAMP-ready infrastructure, or eliminating shadow AI in your organization — we'd like to help.