Everruns Documentation
Everruns is a durable agentic harness engine built on Rust. It provides APIs for managing agents, sessions, and long-running tasks, with real-time SSE event streaming and PostgreSQL-backed durability.
Build directly inside a Rust application with the Everruns Framework, or use the Platform and SDK documentation for a durable deployment and remote clients.
What kind of help do you need?
The documentation is organised by what you’re trying to do.
FrameworkBuild and run agents in a Rust process with the application-facing everruns crate.
Learn — TutorialsHand-held lessons that take you from zero to a running agent. Start here if you're new.
Do — How-to guidesTask-oriented recipes for common problems. Use these when you know what you want to build.
Understand — ExplanationBackground and design rationale. Read these when reference docs aren't enough on their own.
Look up — ReferenceAPI endpoints, event types, capability catalog, CLI flags, environment variables. The dry stuff.
Getting started fast
- Choose the Framework for an in-process Rust application or Docker Compose for the full Platform.
- Run the Framework quickstart or follow the SDK tutorial.
- Browse How-to guides to do something specific.
Popular destinations
Core conceptsHarness, agent, session, capability, event — what they are and how they compose.
Capabilities catalogEvery built-in capability with tools, parameters, and dependencies.
Event referenceEvery event type in the Everruns event protocol, with payloads.
REST API referenceOpenAPI-generated reference for every endpoint.
Everruns FrameworkApplication-facing Rust agents, models, tools, sessions, events, and extension points.
SDKsOfficial client libraries for Rust, Python, and TypeScript.
CLICommand-line interface for managing agents, sessions, and conversations.
ArchitectureControl plane, workers, durable execution — and why.
Environment variablesEvery configuration knob for the control plane and workers.
Agent-first features
Agent triggersWake an agent on a recurring schedule and inspect its runs.
Session participantsInvite agents into a shared session and address one for a turn.
Agent and user memoryLearn the persistence, mount paths, and privacy rules for scoped memory.