# Overmind

## Docs

- [Introduction](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/index.md): Overmind improves production AI agents with their own data: traces in; datasets, evals, optimisation runs and trained models out.
- [Quickstart](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/quickstart.md): Sign up or self-host, paste one prompt into your coding agent, then improve the agent with /overmind commands.
- [Self-hosting](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/platform/self-hosting.md): Run the open-source platform yourself — Docker Compose, the environment reference, the agent and provider keys, training and serving backends, and billing modes.
- [Observability](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/core/observability.md): Get your agent's runs into Overmind and watch each one arrive scored.
- [Python SDK](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/tracing/sdk-python.md): Reference for the overmind package — init(), provider auto-instrumentation, the run boundary, span decorators, behaviours and capabilities, and runtime expectations.
- [TypeScript SDK](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/tracing/sdk-typescript.md): There is no TypeScript tracing SDK; instrument Node.js with OpenTelemetry against the OTLP endpoint.
- [Agent & Capabilities](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/core/capabilities.md): How Overmind models your agent — one graph per project, made of capabilities discovered by a local scan, described by agent-authored cards, and confirmed by telemetry.
- [Datasets](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/core/datasets.md): Turn your production traffic into the eval and training data your runs read.
- [Eval](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/agent-testing/eval.md): Evaluator kinds and their configuration, claims and behaviour bindings, eval sets, live trace scoring, and eval runs — with the endpoints behind them.
- [Decision engine](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/agent-testing/decision-engine.md): Jev-backed bounded decisions, generative fallback, provenance, and semantic dataset checks.
- [Trace scoring](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/agent-testing/trace-scoring.md): How a production trace becomes scored task executions — units, behaviours, verdicts, the execution score, and session scores.
- [Optimisers](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/agent-testing/optimisers.md): The optimisation loop — candidate code diffs generated and replayed in your repository, scored with your eval set on the platform, and the winning diff to apply locally; plus model comparison and hybrid runs.
- [Models](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/models/training.md): Train a model you own on your own traffic, and see it measured against the model you run today.
- [Inference](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/models/inference.md): Call your fine-tuned models through an OpenAI-compatible endpoint — deployment lifecycle, the capability alias, request fields, error codes, and the Console Inference page.
- [MCP](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/platform/mcp.md): The Overmind MCP server — setup per coding agent, the optional plugin, authentication, the 36 tools, 12 prompts, resources, workflow skills and the CLI handoff for local work.
- [CLI](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/platform/cli.md): The overmind command — init, sync, chassis, dataset upload and export, connectors, the optimise loop, model checkpoints, and skills.
- [REST API](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/platform/api.md): Base URL, authentication, and the endpoint map — everything the Console does is available over plain JSON.
- [Projects & Administration](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/platform/administration.md): Projects and membership, API keys, tracing connectors, running work, billing, and guest workspaces.
- [Glossary](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/platform/glossary.md): Definitions of terms used across Overmind, as they appear in the Console and the API.
- [Licensing](https://overmind-b84ae13c-codex-workshop-queue-capacity.mintlify.site/platform/licensing.md): AGPL-3.0 for the platform, MIT for the SDK and CLI, and a commercial licence for different terms.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.