Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.risolu.to/llms.txt

Use this file to discover all available pages before exploring further.

​
Frequently asked questions

Risoluto is a local orchestration engine that watches your tracker for eligible issues, launches sandboxed AI coding agents in Docker, and reports the result through pull requests, dashboard state, and API events.
Your repository data stays in workspaces you control. Risoluto still makes outbound calls to the services you configure, such as:
ServicePurpose
Linear APIRead issues and update issue state
OpenAI-compatible providerModel inference for the agent runtime
GitHub APIPull requests and repository actions
Slack APIOptional notifications
See the Trust Model for the full boundary breakdown.
Yes. Agent work runs inside Docker sandboxes, and the recommended quickstart also runs the orchestrator in Docker.If you run the orchestrator on the host for development, Docker is still required for worker isolation.
Risoluto uses the Codex runtime and defaults to gpt-5.4. You can change the model globally or per issue, and you can point the provider at an OpenAI-compatible endpoint.
curl -s -X POST http://127.0.0.1:4000/api/v1/MT-42/model \
  -H 'Content-Type: application/json' \
  -d '{"model":"gpt-5","reasoning_effort":"medium"}'
TrackerStatus
LinearPrimary adapter with polling, transitions, labels, and webhooks
GitHub IssuesSupported adapter using the same orchestration pipeline
See How It Works for the architecture behind tracker adapters.
Risoluto retries with exponential backoff until it reaches agent.maxContinuationAttempts.
FailureDetectionResponse
Agent errorNon-zero exit codeRetry with backoff
Container OOMExit code 137 / OOMKilledSurface as container_oom, then retry
Stalled turnNo events for codex.stallTimeoutMsKill the turn, then retry
Stalled agentNo events for agent.stallTimeoutMsKill the worker, then retry
Retries exhaustedMax attempts reachedMark the issue as failed
Attempt history stays visible in the dashboard and API.
You have three main surfaces:
SurfaceWhat it gives you
DashboardLive board, issue detail, attempts, logs, and settings
API + SSEScriptable state snapshots and live event streams
PrometheusService and runtime metrics at GET /metrics
Start with the Dashboard guide and Observability.
Yes. Use agent.maxConcurrentAgents for a global cap and agent.maxConcurrentAgentsByState for per-state limits. Each agent gets its own Docker container and workspace.
Risoluto itself is open source. Your direct cost comes from the model provider you configure and the amount of work each run consumes.The dashboard tracks issue-level and aggregate usage so you can see where spend is coming from.
Yes. Build a custom image and point codex.sandbox.image at it through the config overlay API or dashboard.The Custom Sandbox recipe walks through the pattern.
Not today. The default operating model is self-hosted and local-first.
ComponentMinimumRecommended
Node.jsv22+Latest LTS
DockerEngine 24+Latest stable
RAM4 GB + 4 GB per active agent16 GB+
Disk10 GB50 GB+
CPU2 cores + 2 per active agent8+ cores

​
What’s next

Quickstart

Start with the recommended first-run path.

Setup Wizard

See exactly what the wizard stores and validates.

Trust Model

Review the security posture and trust boundaries.

Troubleshooting

Diagnose setup and runtime failures.
Last modified on April 3, 2026