Reflexio

evalship helps engineering teams test and improve LLM-powered software. At setup, your coding agent reviews every scorer, judge and prompt in your evals and finds their flaws, such as a judge that scores 1.0 when its call fails, each with fix instructions. On every pull request, evalship compares results with the default branch, reports the evals a change really broke and the likely cause, sets flaky evals aside, and flags AI calls no eval exercises. Its check can block a merge that breaks an eval. Optimize has your coding agent try prompt and model changes on your machine, such as a cheaper model or clearer instructions, and evalship says which win beyond chance and by how much in pass rate, cost and time. Evals run with your own keys, in your own GitHub Actions or on your machine. evalship reads results from pytest, Vitest, Jest, promptfoo, Langfuse, Braintrust and LangSmith, with no SDK to add. Public repositories are free; paid plans start at $19 a month.

Overmind is a model training and deployment platform for teams building AI agents. It ingests production traces through OpenTelemetry and creates datasets from trace data, file uploads, and connectors for Langfuse, LangSmith, Braintrust, and Galileo. Teams can inspect agent context and runtime behavior, prepare and score datasets, evaluate prompts and models against their own examples, and optimize agent behavior through scored changes. The platform supports LoRA and full fine-tuning of open-weight models, benchmarking with configured evaluators, and deployment through an OpenAI-compatible endpoint; trained weights can also be downloaded. Users can work in the hosted console or run the platform on their own infrastructure with Docker Compose. It is designed for AI engineering and product teams operating agents in production that want to test, improve, or specialize models using their own data.