Stargazer¶
Stargazer is a bioinformatics pipeline framework built on Flyte v2. It provides a library of composable tasks for common bioinformatics operations and exposes them through an MCP server that any AI-powered client can consume.
How It Works¶
- Assets carry structured metadata that describes every file's role in the system — reference genomes, read pairs, alignments, variant calls
- Tasks are atomic operations that fetch assets, run bioinformatics tools, and produce new assets
- Workflows compose tasks into end-to-end pipelines (e.g., germline variant calling for a cohort)
- MCP server exposes tasks, workflows, and storage as tools that LLM clients can invoke
Interface¶
Stargazer ships two end-user Docker images:
stargazer-note— a Marimo notebook for running pipelines and exploring datastargazer-chat— a pre-wired agentic interface (Claude Code + OpenCode) to the Stargazer MCP server
Both include the MCP server, which can also be connected to any MCP-compatible client (Claude Code, OpenCode, Cursor, etc.). Source contributors work natively against the repo — see Contributing.
Documentation¶
- Getting Started — go from zero to running your first workflow
- Architecture — how the system is designed and why
- Guides — step-by-step walkthroughs for common tasks
- Contributing — set up a dev environment and run tests
- API Reference — auto-generated from docstrings