Built for Governed Enterprises
AgentMux is the open-source AI agent control plane with architectural governance. Every interaction audited. Every agent accountable. Your data stays on your infrastructure.
Security Architecture
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.
Zero Telemetry
No data sent to AgentMux servers. No analytics. No phone-home. Verify in the source code.
Local-Only Data Path
All agent interactions stay on your machine. No cloud relay. No third-party data processors.
Memory-Safe Backend
100% Rust — no buffer overflows, no use-after-free, no GC pauses. Compile-time memory safety.
IPC Security
Tokio async channels for inter-pane communication. No network exposure. Process-level isolation.
Detailed posture in the docs: Trust model, Network exposure, Data sovereignty.
Compliance Framework Coverage
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
Audit Trail
Every AI interaction produces a complete, tamper-evident record. The evidence regulators and auditors demand.
What's Logged
- Every prompt and response
- Every tool call and its result
- Every agent-to-agent delegation
- Every file read, write, and modification
- Every sub-agent spawn and termination
- Session identity and timestamps
Log Characteristics
- Structured JSONL format — machine-parseable
- Append-only with integrity verification
- SIEM-ready export (Splunk, Datadog, Sentinel)
- Full decision chain: human to agent to outcome
- Configurable retention policies
- Decision replayability: same input, same output
What stays local vs. what leaves the machine: Data sovereignty.
Supply Chain Security
Open source means trust through transparency. Audit every line. Verify the build. No black boxes.
Open Source
LiveApache 2.0. Full source available. Community-verified. No proprietary dependencies.
100% Rust
LiveMemory-safe language with compile-time guarantees. No runtime vulnerabilities from GC or unsafe memory access.
Dependency Auditing
Livecargo-audit integration for continuous vulnerability scanning of the dependency tree.
Code Signing
RoadmapSigned binaries for Windows and macOS. Verifiable provenance for every release.
Reproducible Builds
RoadmapDeterministic build pipeline so anyone can verify the binary matches the source.
SBOM Generation
RoadmapSoftware Bill of Materials for every release. Full dependency transparency.
Update + tool-download model in the docs: Update model.
Deployment Models
From individual developer workstations to classified environments. Deploy AgentMux where your security requirements demand.
Desktop
Standard installation on employee workstations. Every interaction logged locally with structured export.
- Windows, macOS, Linux
- Per-user agent configs
- Local audit trail
- Zero network dependency
Enterprise Managed
IT-deployed with centralized policy presets. Agents launch with pre-approved configurations only.
- Group policy / MDM deployment
- Locked-down agent configs
- Centralized audit collection
- RBAC enforcement
Air-Gapped
Fully offline operation for classified and restricted environments. No internet connection required.
- Zero internet dependency
- Offline installer package
- Local-only data path
- FISMA / CMMC ready
Posture per deployment topology: Trust model.
Identity & Access
Enterprise-grade identity management for AI agents and their operators. Coming in Phase 3 (Claw).
RBAC
RoadmapRole-based agent permissions. Control which agents each team member can launch, which tools agents can access, and what data they can touch.
Enterprise SSO
RoadmapSAML and OIDC integration for single sign-on. Every agent session tied to an authenticated enterprise identity.
PIV/CAC Support
RoadmapSmart card authentication for government and defense environments. Hardware-backed identity verification.
Session Attribution
RoadmapEvery agent action attributable to an authenticated user session. Full chain of custody from human to outcome.
Today's credential model: Identity & credential storage.
Ready to govern your AI agents?
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.