Open-Science v1.0 ships open-source desktop workbench with portable .science research packages
lmoroney · x · 2026-10-16
AIPOCH released Open-Science v1.0.0, an open-source, local-first desktop research workbench for macOS, Windows, and Linux, designed to hand off AI-assisted experiments as a single file.
Key points:
- .science packages: carry selected conversation branches, file versions, Notebook records, and verification evidence for review or archiving; imports open read-only, without executing code or restoring credentials.
- Workbench: persistent Python/R Notebooks with execution history and .ipynb export; literature tools with PDF annotation and BibTeX/RIS export.
- Pluggable agents: Claude Code, OpenCode, Codex, or CodeBuddy as agent frameworks, plus custom model endpoints.
The author suggests supervisors export one small analysis as a .science package and open it on a second machine to stress-test the handoff workflow.
More from coding & agent
- VibeZero: one-shot an entire vibe coding platform on Cloudflare Void — cnakazawa · 2026-10-16
- Ant and Tsinghua open-source Realtime-Venus, an OpenAI Realtime API alternative — aigclink · 2026-10-16
- 'I remember when I was the harness for o1 pro' — dev on becoming the API for his model — timigod · 2026-10-16
- JevAgentHarness: a 4B decision model lets cheap agents offload tool choices from the LLM — youjiaxuan · 2026-10-16
- Coding agents keep opening 3 stacked PRs per chat, and merging them is a nightmare — holdenmatt · 2026-10-16
- Google-led paper uses sequential auctions to organize decentralized LLM agent workflows — _onionesque · 2026-10-16