AutoAgents: Build Agents in Rust
How to build production-ready agents in Rust with AutoAgents: providers, tools, and scalable runtimes.
Read articleLiquidOS
AutoAgents is our open-source Rust SDK for building reliable agent systems today. LiquidOS Platform is coming soon with enterprise tracing, policy controls, evals, and deployment workflows for teams shipping agents in regulated and mission-critical environments.
Available now
AutoAgents SDK
Open-source Rust runtime for agent systems.
Coming soon
Platform tracing
Audit-friendly traces, artifacts, and debugging context.
Coming soon
Policy + evals
Budgets, approvals, and regression suites.
Mission
LiquidOS is for teams that can’t rely on “best effort” AI. Run agents where your data lives, keep execution deterministic, and layer in platform-grade tracing, policy, and evaluation as you scale.
Platform (coming soon)
LiquidOS Platform is in active development. Join the waitlist for early access and roadmap previews.
Execution
Run where your data lives: on-prem, edge, and air-gapped without cloud lock-in.
Safety
Budgeting, approvals, and scoped tools to align agent behavior with operational rules.
Observability
End-to-end traces, artifacts, and debugging context for audit-ready deployments.
Evaluation
Measure reliability with repeatable evals and feedback loops that improve over time.
Portability
Portable, secure tool execution for consistent behavior across machines and environments.
Deployment
Enterprise deployment patterns with hardened installs and integration hooks for RBAC and compliance.
Overview
A research-driven, production-first effort to make agent systems reliable, observable, and deployable anywhere.
LiquidOS is building a local-first agent platform for environments where security, latency, reliability, and observability are non-negotiable — from enterprise on-prem deployments to local-first robotics.
AutoAgents is available now as the open-source SDK. The LiquidOS Platform layer is coming soon for teams that need audit-ready controls and operations.
Workflow
A platform flow that makes “agent in production” a repeatable process.
Step 1
Compose agents, tools, and memory with structured, testable interfaces.
Step 2
Tracing, policy, and evals to ship confidently in enterprise environments.
Step 3
Local-first execution across laptops, private servers, edge, and robots.
Why
A platform stance centered on locality, safety, speed, and measured outcomes.
Local-first
Run agents where your data lives — laptops, private servers, edge devices, and robots. No forced cloud dependency.
Production-grade
Observability, traceability, and hardened enterprise installs with policy controls and audit logs.
Performance
Native Rust runtimes keep overhead low while staying portable across environments.
Research → Production
Integrated evaluation, tracing, and feedback loops to move confidently from experiments to deployment.
Audience
Teams building AI systems where reliability and operational clarity are non-negotiable.
Enterprise teams
Deploying agents on-prem or in regulated environments.
Robotics teams
Building local-first autonomous systems.
Research teams
Need reproducibility, evaluation, and traceability.
Updates
Research notes, system design, and production lessons from building agents.
How to build production-ready agents in Rust with AutoAgents: providers, tools, and scalable runtimes.
Read articleLiquidOS Platform is launching soon. Join the waitlist for early access, roadmap previews, and enterprise onboarding.