0xwilliamortiz
Featured
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It ranks #1 on ResearchClawBench, offers a fully auditable desktop workflow as an open-source alternative to Claude Science, and integrates browser control, remote access via phone, and model-agnostic runtime.
Who it is for
- Academic researchers automating literature surveys and experiments
- Data scientists seeking reproducible AI-assisted workflows
- Open science advocates wanting local-first, privacy-preserving tools
- Developers building custom AI research pipelines with MCP and skills
Use cases
- End-to-end research: from a broad direction to a finished paper with figures and citations
- Literature survey generation with real DOIs and LaTeX source
- Automated experiment design, execution, and result provenance capture
- Remotely monitoring research runs from a phone via token-authenticated gateway
Strengths
- Local-first: all data stays on your machine by default, enhancing privacy
- Model-agnostic: works with any model supported by OpenCode via pluggable providers
- Full provenance: every artifact links to its generating code, inputs, and conversation
- Extensible: supports custom agent skills, MCP connectors, and shell commands
Considerations
- Beta software with outputs labeled as drafts—requires manual verification
- Builds are not code-signed or notarized, causing gatekeeper warnings on macOS
- Setting up from source requires Node.js, pnpm, Rust, and system dependencies
README quick start
Open Science Desktop
Local-first, model-agnostic AI research workbench for macOS, Windows & Linux.
Formerly Open Science. An open-source desktop alternative to Claude Science and similar AI-for-science workbenches — built with Tauri, MCP, agent skills, and reproducible artifacts. It connects agents, notebooks, files, figures, reports, runs, and review into one auditable desktop workflow.
English · 简体中文 · 日本語 · Español · Deutsch · Français · 한국어
News
- 2026-07-21 — 🌐 Access from anywhere — even your phone. A token-authenticated gateway serves the real desktop UI to a CLI, a browser on your LAN, or your phone (loopback by default; LAN is opt-in). Start a run at your desk and read the finished figure and report on your phone. (v0.2.3)
- 2026-07-21 — 🧭 Browser control. The agent can drive your own Chrome — profile and logins intact — to read the live web the way you do, or an isolated private browser on demand. (v0.2.3)
- 2026-07-09 — 🎉 #1 on ResearchClawBench. Open Science Desktop ranks #1 by scored-task average on ResearchClawBench, an end-to-end benchmark for autonomous scientific research agents (Pass@1 leaderboard).
Contents
- ✨ What it does
- 🎬 See it in action
- 🧪 Current capabilities
- 🔌 Skills and connectors
- 📦 Install
- 🚀 Build from source
- 🔒 Safety and privacy
- 🗂️ Repository layout
- 📌 Status
- 🤝 Contributing
- 📖 Citation
- ⚖️ License
What it does
Runs the whole research loop — from a broad direction to a finished paper: exploration, literature survey, hypothesis, experiment code, analysis, figures, and write-up, in one continuous, auditable session.
- Autonomous research agents — the bundled
ai4s-agentchains specialist skills end to end (explore → survey → experiment → write), and each stage drops a real, inspectable artifact into your workspace, not just a chat reply. - Everything traces back — figures, tables, reports, notebooks, and run outputs link to the exact code, inpu
Description
Open Science — an open AI workbench for scientists. Open-source alternative to Claude Science: local-first, model-agnostic, reproducible AI research desktop (macOS & Windows), built on Tauri + MCP + agent skills.
Related repositories
Similar projects matched by category, topics, and programming language.
makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
hahhforest
Featured
pi-textbook
A hands-on course that walks through building a Pi-style coding agent from scratch across 15 checkpoints, starting from an offline agent trajectory.