open-science
Open Science Desktop: local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.
The Lens
By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.
Updated Oct 2026
Open Science Desktop is the free, MIT-licensed answer to Anthropic's Claude Science: one desktop app for the whole research loop, from literature survey and hypothesis to experiment code, figures and the paper. Every figure, table and notebook links back to the code, inputs and conversation that produced it.
You bring your own model. A bundled OpenCode runtime talks to whatever provider you pick. Runs can target your laptop, SSH or Slurm clusters, or your own Modal account, and osd server puts the same web UI on a machine with no screen. The macOS build is signed and notarized; Windows and Linux builds aren't signed yet.
Nothing to buy. Claude Science requires a paid Claude plan; this needs only your model bill, and paper-length agent sessions burn tokens. Solo researchers and grad students: free. Labs: free, and data stays in local folders. Larger groups: free, with API spend as the line item.
The catch: it's version 0.6 and calls itself beta. The agent can drive your real Chrome profile with your logins, operate desktop apps on your screen and submit cluster jobs, so keep the default approvals on. Its main sponsor, APEVON, also sells a paid research app, Apevon Science.
Free vs Self-Hosted vs Paid
fully freeFree: The whole app under MIT: research agents and skills, projects, memory, run tracking, provenance, the remote-access gateway and the osd command-line client. Installers for macOS (signed and notarized), Windows and Linux.
Self-hosted: It's a desktop app and local-first by default. osd server runs the same workbench headless on a server and serves the web UI over HTTP. Remote compute uses your own SSH or Slurm machines or your own Modal account.
Paid: No paid tier. The real cost is your model provider, and long agent sessions that write surveys and papers use a lot of tokens. For comparison, Anthropic's Claude Science is included only in Claude Pro, Max, Team and Enterprise plans. The project's main sponsor, APEVON, sells a separate hosted product, Apevon Science: Basic $10/month (550 credits), Plus $35/month (2,000 credits), Max $100/month (8,000 credits), billed monthly. You don't need it to use Open Science Desktop.
Free under MIT with no paid tier; your model API bill is the only cost. Claude Science does the same job but needs a paid Claude plan.
What to do by team size
- Solo
- free; bring your own model key
- Small team
- free; data stays in local folders
- Medium team
- free; budget for model API spend
- Large team
- free; model API spend scales with usage
Get tools like this every Wednesday
One featured tool, three on the radar. No fluff.
A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores
Trust Signals
License: MIT License
Bundled third-party skills keep their own licenses.
Commercial use: ✓ Yes
About
- Owner
- ai4s-research (Organization)
- Stars
- 2,092
- Forks
- 231
Explore Further
More tools in the directory
rea
Reverse engineer anything with agents, from app behavior down to native binaries.
453.7k ★everything-claude-code
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
301.6k ★hermes-agent
The agent that grows with you
262.8k ★