# Overmind

> Overmind is the model training platform for AI teams. Turn your production traces into specialised models you own, trained, benchmarked, and served.

Overmind turns an AI team's production agent traces into small open-weight models the team owns: trace, curate datasets, evaluate, optimise, train, and serve from one platform. Agents and scripts call it over REST at https://api.overmindlab.ai (header `X-Api-Key: ovr_...` or `Authorization: Bearer ovr_...`; OpenAPI at https://www.overmindlab.ai/openapi.json) or through the `overmind` (PyPI) and `@overmind-lab/trace-sdk` (npm) SDKs. Trained models are served OpenAI-compatible at https://api.overmindlab.ai/api/v1.

## When to use Overmind

- [Train and fine-tune small open-weight models on production traces](https://www.overmindlab.ai/product/model-training): Best fit when an AI team runs agents in production and wants a specialised model it owns instead of renting a frontier API. Training is automated from the agent's own traces, benchmarked against the baseline, and served on a hosted endpoint.
- [Build evals from real traffic and optimise agent code](https://www.overmindlab.ai/product/agent-testing): Use when you need regression tests for an agent: evals are generated from the context graph, scored on real traces, and the Optimiser turns the winning change into a GitHub PR.
- [Curate training datasets from traces](https://www.overmindlab.ai/product/data-workshop): Use when raw telemetry must become a labelled, PII-redacted dataset ready for SFT or RL.
- [Trace and observe agents over OTLP](https://www.overmindlab.ai/product/observability): Use when you want a context graph of an agent built from code and telemetry, with every run traced.
- [Serve trained and frontier models through one OpenAI-compatible endpoint](https://docs.overmindlab.ai/models/inference.md): Point any OpenAI SDK at https://api.overmindlab.ai/api/v1 with an ovr_ API key; trained ft-... models and frontier models share the same gateway.
- [How an agent should call Overmind](https://docs.overmindlab.ai/platform/api.md): REST base URL https://api.overmindlab.ai; authenticate with the X-Api-Key: ovr_... header (or Authorization: Bearer); JWT via POST /api/auth/token/; machine-readable spec at https://www.overmindlab.ai/openapi.json.

## Product

- [Home](https://www.overmindlab.ai/): Overmind is the model training platform for AI teams. Turn your production traces into specialised models you own, trained, benchmarked, and served.
- [Agent Testing](https://www.overmindlab.ai/product/agent-testing): Evals generated from the context graph and scoped to each agent. The Optimiser tests candidate diffs against your baseline on the same eval set and turns the winning change into a GitHub PR.
- [Data Workshop](https://www.overmindlab.ai/product/data-workshop): Curate datasets from production traces. Audited by deterministic checks and a coding agent, with PII redacted and a profile that sets up your training run.
- [Model Training](https://www.overmindlab.ai/product/model-training): Automated training from your agent’s own data. Hyperparameters from dataset statistics, adapter training or a full finetuning run, benchmarked against your baseline, then served on a hosted endpoint with an OpenAI-compatible API.
- [Observability](https://www.overmindlab.ai/product/observability): Overmind builds a context graph of your agents from code and telemetry, then traces every run. Your datasets, evals, and training runs read from both.
- [Model Library](https://www.overmindlab.ai/models): Open-weight models Overmind trains on your agent's own data, all trainable with LoRA or full finetuning.
- [Pricing](https://www.overmindlab.ai/pricing): Plans for tracing, testing, training, and deployment at any scale.

## Comparisons

- [All comparisons](https://www.overmindlab.ai/compare): How Overmind differs from observability, tracing, and fine-tuning tools, including the cases where a competitor is the better choice.
- [Overmind vs LangSmith](https://www.overmindlab.ai/compare/overmind-vs-langsmith): The most adopted agent observability platform. Its loop ends at dataset export; Overmind's ends at a model you own.
- [Overmind vs Langfuse](https://www.overmindlab.ai/compare/overmind-vs-langfuse): The open-source observability standard. Overmind imports its traces today and runs the training loop it deliberately leaves out.
- [Overmind vs OpenPipe](https://www.overmindlab.ai/compare/overmind-vs-openpipe): Proved that production requests should train cheaper models you own. Sunset July 2026; Overmind runs that idea as a full loop.

## Developers

- [API reference](https://docs.overmindlab.ai/platform/api.md): Base URL, authentication, and the endpoint map for the Overmind REST API.
- [OpenAPI spec (JSON)](https://www.overmindlab.ai/openapi.json): OpenAPI 3 description of the Overmind platform API for code generation and function calling.
- [OpenAPI spec (YAML)](https://www.overmindlab.ai/api/openapi.yaml)
- [Authentication](https://docs.overmindlab.ai/platform/api.md#authentication): API keys (X-Api-Key or Bearer), JWT tokens, and console sessions.
- [Quickstart](https://docs.overmindlab.ai/quickstart.md): Create an API key and send the first traces in minutes.
- [Python SDK](https://docs.overmindlab.ai/tracing/sdk-python.md): The `overmind` package on PyPI: init(), auto-instrumentation, span decorators.
- [TypeScript SDK](https://docs.overmindlab.ai/tracing/sdk-typescript.md): The `@overmind-lab/trace-sdk` package on npm for Node.js agents.
- [Inference API](https://docs.overmindlab.ai/models/inference.md): OpenAI-compatible chat completions at https://api.overmindlab.ai/api/v1.
- [Developer console](https://console.overmindlab.ai): Sign in to manage projects, API keys, traces, datasets, and training runs.
- [API catalog](https://www.overmindlab.ai/.well-known/api-catalog): RFC 9727 linkset pointing at the spec and docs.

## Documentation

- [Docs](https://docs.overmindlab.ai/): Product documentation, guides, and API reference (see also https://docs.overmindlab.ai/llms.txt).

## Research

- [How to train your agent](https://www.overmindlab.ai/research/how-to-train-your-agent): Seven patterns from teams running AI agents in production: instrument every trace, build evals from real traffic, and label before you collect.
- [Unwrapping the wrappers](https://www.overmindlab.ai/research/who-trains-their-own-models): Cursor, Intercom, Replit, and Perplexity all trained specialist models on their own production data. What each one built, how, and what it bought them.
- [How do you turn traces into a training dataset?](https://www.overmindlab.ai/research/traces-to-training-dataset): The four stages from agent telemetry to a training dataset: capture every run as a trace, sample what to label, score it, and build for SFT or RL.
- [Prompt engineering vs fine-tuning](https://www.overmindlab.ai/research/prompt-engineering-vs-fine-tuning): Prompting changes what you say to the model. Fine-tuning changes the model. How to tell which one you need, and when prompting hits its ceiling.
- [What are the different types of fine-tuning?](https://www.overmindlab.ai/research/types-of-fine-tuning): The four fine-tuning options and how to pick: supervised fine-tuning, reinforcement fine-tuning with GRPO, distillation, and LoRA or QLoRA to run them cheaply.
- [Open-weights LLMs vs frontier APIs](https://www.overmindlab.ai/research/open-weights-vs-frontier-apis): Fine-tune or call an API: LLM inference cost and the crossover point, latency, data residency, and when a self-hosted open-weights model wins.
- [The anatomy of an AI agent](https://www.overmindlab.ai/research/anatomy-of-an-ai-agent): What an AI agent is made of: the model, the agentic loop, tools, and memory, plus the trajectory they produce and why it's the unit of work.
- [So, you have observability. Now what?](https://www.overmindlab.ai/research/so-you-have-observability-now-what): You’ve instrumented prompts, traces, and tool calls. Here’s why observability can’t judge quality - and how to close the loop from traces to better models.
- [Secret Agent Overmind](https://www.overmindlab.ai/research/secret-agent-overmind): Diagnose and optimise production AI agents by fusing code, traces, evals, and datasets so every behaviour is explainable, sourced, and fixable.
- [Think Smaller](https://www.overmindlab.ai/research/think-smaller): Specialised small language models, fine-tuned on production data, beat frontier LLMs on most agent tasks. The case for SLMs and owning your weights.

## Company

- [About](https://www.overmindlab.ai/about): Who builds Overmind and why.
- [Contact](https://www.overmindlab.ai/contact): Email, booking a call, support, and company address.
- [Careers](https://www.overmindlab.ai/careers): Open engineering and research roles.
- [Privacy policy](https://www.overmindlab.ai/legals/privacy)
- [Terms](https://www.overmindlab.ai/legals/terms)

## Optional

- [Sitemap](https://www.overmindlab.ai/sitemap.xml)
- [Research RSS feed](https://www.overmindlab.ai/research/feed.xml)
- [Docs llms.txt](https://docs.overmindlab.ai/llms.txt)
- [Markdown versions of every page](https://www.overmindlab.ai/index.md): Append .md to any page path (for example https://www.overmindlab.ai/about.md) or send Accept: text/markdown.