Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.
↓ Télécharger
Toutes les versions →
Wisp Science
The open-source, local-first AI research workbench.
WISP — Workspace for Intelligent Scientific Practice
English · 简体中文 · Website · Releases
Search the literature, run Python and R, query ~80 scientific databases, and keep the trail — figures, runs, decisions, and drafts — in one project. Your data, conversations, and credentials stay on your machines.
Bring your own model. Keep your science.
What you can do
An agent that does the work
Bring OpenAI-compatible or Anthropic models, or drive Codex / Claude Code over
ACP. The agent reads and writes project files, runs shell, and loads reusable
Skills (SKILL.md) without flooding the prompt. Approval gates stay on unless
you opt into Full Permission.
Compute from laptop to remote servers
Persistent Python and R kernels keep variables across cells and turns; each conversation gets its own isolated kernel, so parallel sessions never share state. Register local, WSL, and SSH hosts once; probe hardware; submit long Runs with live logs. Keys live in the OS keyring, never in SQLite.
Built for science
PubMed, GEO, and ~80 other databases through bundled MCP servers. Offline previews for notebooks, PDFs, Office files, and images. Isolated explorations to try a direction without touching the mainline. A Publication Workspace that freezes manuscript revisions into verifiable Evidence Capsules.
A workbench that remembers
Restart and the full history is back. Undo a turn's file edits. Attach
artifacts, files, and runtimes with @; search saved sessions with #; apply
a skill with /. Encrypted manual sync and
project transfer — nothing syncs in the background.
Get started
- Download from GitHub Releases.
- Open a bundled demo — no API key needed — to see a full RNA-seq trajectory.
- Add a model in Settings → Models and start a project.
| Platform | Package |
|---|---|
| Windows | Signed MSI / NSIS |
| macOS | Signed, notarized .dmg (Apple Silicon + Intel) |
| Linux | .deb / AppImage (x86_64 + aarch64) |
Setup walkthrough: basic configuration · model profiles · ACP agents
Build from source, CLI, and architecture: development.
Documentation
| Start | Basic setup · Models · ACP agents |
| Research | Explorations · Evidence capsules · Case studies |
| Projects | Transfer · Sync · Global library |
| Compute | Terminals · Remote files · Transfers |
| Extend | Skills · Plugins · Delegation · Channels · Browser |
| Develop | Development · Headless eval |
Community
Thanks to everyone who filed issues, sent PRs, and used Wisp on real projects.
Windows code signing by SignPath.io, certificate by the SignPath Foundation. Third-party notices live in development.
License
AGPL-3.0-only, except where a directory notes otherwise. Earlier releases keep the license published with them.
Citation
@software{xu2026wisp,
author = {Xu, Zhou-Geng},
title = {Wisp Science: a local-first AI research workbench},
version = {v1.5.0},
year = {2026},
publisher = {Zenodo},
doi = {10.5281/zenodo.22009273},
url = {https://doi.org/10.5281/zenodo.22009273}
}