Counting visitors…
Browse all docs
Start · 9Find your path through RunifoldLearn Runifold in 45 minutesUnderstand the complete Runifold platformYour first trustworthy runChoose the right execution APIChoose crates and Cargo featuresBuild common Runifold applicationsRunifold frequently asked questionsTroubleshoot Runifold applications
Execution kernel · 7Understand RunContextCoordinate external effects safelyBound work with budgets and cancellationHandle errors and retries safelyEvents, journals, and execution evidenceDesign capability-safe executionRecover safely from checkpoints
Models & providers · 7Route across models without duplicate outputChoose and configure a providerUse the provider-neutral model protocolBuild on the Provider Runtime contractUse OpenAI control-plane and Realtime APIsTest and benchmark provider adaptersSet up OpenAI, Anthropic, Gemini, and Ollama
Agents · 7Build and configure an AgentGive an Agent typed toolsAdd conversations and semantic memoryDelegate to child Agents safelyReturn structured Rust valuesStream without losing semanticsGround an Agent with retrieval
Durable workflows · 7Compose deterministic workflowsMake workflows durableOperate durable workflow workersCoordinate timers, signals, and durable waitsRun multi-tenant workflow infrastructureRun parallel branches and safe racesVersion and evolve durable workflows
Integrations · 7Connect through MCPChoose stores and persistence boundariesExpose durable work through MCP TasksBuild and evaluate retrieval pipelinesUse MCP Resources, Prompts, and SamplingCache MCP responses without crossing authorityDeploy Runifold in a Rust web service
Quality & operations · 10Test without the networkEvaluate quality and prevent regressionsObserve the complete run treeRun safely in browsers and at the edgeRead reliability claims preciselyRun reproducible evaluations in CIOperate Runifold with SLOsGovern Task retention and deletionArchive audit evidence to S3-compatible WORM storageManage compatibility and trusted releases
Docs/Platform map
NEW TO RUNIFOLD?Build the complete mental model in 45 minutes
Platform map

Understand the complete Runifold platform

See how the execution kernel, model protocol, Agents, workflows, stores, MCP, evaluation, and observability fit together.

Practical guide·10 min

The platform in one view

Runifold is not only an Agent framework. It is a layered execution platform:

ApplicationAgent / Workflow / MCPRun kernelModel / Tool / Store

The application chooses the product surface. Every surface reuses the same identity, cancellation, budget, capability, event, and effect semantics. A workflow can call an Agent; an MCP Task can represent a workflow; an Agent can use retrieval and typed tools; all of them can share one causal Run tree.

Seven product surfaces

SurfaceOwnsDoes not own
execution kernelidentity, lifetime, authority, accounting, eventsmodel or workflow policy
model protocolprovider-neutral request, stream, response, capability evidenceAgent loops
Agentsmodel-tool loop, structured output, conversation, delegationdurable business transitions
workflowsdeterministic composition, checkpoints, workers, waits, leasesprompt semantics
integrationsMCP, retrieval, vector stores, SQL storesapplication authorization
evaluationdeterministic doubles, scorers, experiments, CI gatesproduction traffic
observabilitytraces, metrics, journals, SLO assetsbusiness reconciliation

This separation lets you use the model layer directly, build a deterministic workflow with no Agent, or expose durable work over MCP without pretending every workload is a chat assistant.

Crate map

Crate familyMain responsibility
runifold-coreRun IDs, context, budgets, cancellation, capabilities, events, journals
runifold-model, runifold-providerscanonical model protocol and provider adapters
runifold-tool, runifold-agent, runifold-effectcallable boundaries and Agent execution
runifold-workflowdurable orchestration, workers, waits, tenancy, retention
runifold-mcp, runifold-retrieval*external capability and knowledge edges
runifold-store-*SQLite and PostgreSQL durability
runifold-testkit, runifold-eval-clioffline correctness and quality evidence
runifold-observability-otelOpenTelemetry and operational policy
runifoldfeature-gated facade that re-exports the public platform

Applications normally start with the facade. Infrastructure libraries can depend on narrower crates to keep dependency and feature boundaries explicit.

Choose your entry point

You are buildingStart with
one provider-neutral model callModel protocol
a bounded model-and-tool loopAgents
deterministic multi-step business workWorkflows
restart-safe background executionWorkflow workers
an MCP server or client edgeMCP
durable MCP operationsMCP Tasks
quality gates for model behaviorEvaluation CLI
production platform operationsSLO operations

Architectural laws

  1. Streaming is the source of truth for model invocation.
  2. A Run owns control state; conversation history is separate model context.
  3. Registering a callable does not grant authority to execute it.
  4. External writes cross an explicit Effect boundary.
  5. Durable recovery never guesses that an ambiguous operation failed.
  6. Workflow ownership is fenced; a stale Worker cannot commit.
  7. Tenant identity is part of authorization, accounting, and storage lookup.
  8. Reliability claims name the evidence that supports them.

These laws are more stable than individual builder methods. Learn them first; use the API reference for the exact version you compile.