Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
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.
| Date | Stars |
|---|---|
| 2026-07-30 | 420 |
| 2026-08-08 | 991 |
| 2026-08-09 | 991 |
| 2026-08-16 | 1112 |
| 2026-08-18 | 1010 |
| 2026-08-19 | 1017 |
| 2026-08-20 | 1020 |
| 2026-08-21 | 1024 |
| 2026-08-22 | 1025 |
| 2026-08-23 | 1030 |
| 2026-08-24 | 1035 |
| 2026-08-25 | 1040 |
| 2026-08-26 | 1046 |
| 2026-08-27 | 1052 |
| 2026-08-28 | 1058 |
| 2026-08-29 | 1064 |
| 2026-08-30 | 1069 |
| 2026-08-31 | 1078 |
| 2026-09-01 | 1080 |
| 2026-09-02 | 1086 |
| 2026-09-03 | 1090 |
| 2026-09-04 | 1093 |
| 2026-09-05 | 1098 |
| 2026-09-06 | 1098 |
| 2026-09-07 | 1105 |
| 2026-09-08 | 1114 |
| 2026-09-09 | 1117 |
| 2026-09-10 | 1119 |
| 2026-09-11 | 1126 |
| 2026-09-12 | 1129 |
| 2026-09-13 | 1132 |
| 2026-09-14 | 1135 |
| 2026-09-15 | 1140 |
| 2026-09-16 | 1143 |
| 2026-09-17 | 1147 |
| 2026-09-18 | 1151 |
| 2026-09-19 | 1152 |
| 2026-09-20 | 1156 |
| 2026-09-21 | 1158 |
| 2026-09-22 | 1162 |
| 2026-09-23 | 1164 |
| 2026-09-24 | 1167 |
| 2026-09-25 | 1170 |
| 2026-09-26 | 1171 |
| 2026-09-27 | 1172 |
| 2026-09-28 | 1173 |
| 2026-09-29 | 1176 |
| 2026-09-30 | 1179 |
| 2026-10-01 | 1180 |
| 2026-10-02 | 998 |
| 2026-10-03 | 1000 |
| 2026-10-04 | 1001 |
| 2026-10-05 | 1003 |
| 2026-10-06 | 1008 |
| 2026-10-07 | 1012 |
| 2026-10-08 | 1021 |
| 2026-10-09 | 1023 |
| 2026-10-10 | 1026 |
| 2026-10-11 | 1027 |
| 2026-10-12 | 1032 |
| 2026-10-13 | 1037 |
| 2026-10-14 | 1040 |
| 2026-10-15 | 1042 |
| 2026-10-16 | 1043 |
| 2026-10-17 | 1044 |
| 2026-10-18 | 1045 |
| 2026-10-19 | 1046 |
| 2026-10-20 | 1047 |
| 2026-10-21 | 1049 |
| 2026-10-22 | 1050 |
| 2026-10-23 | 1052 |
| 2026-10-24 | 1054 |
| 2026-10-25 | 1055 |
| 2026-10-26 | 1054 |
| 2026-10-27 | 1055 |
| 2026-10-28 | 1056 |
| 2026-10-29 | 1057 |
| 2026-10-30 | 1059 |
| 2026-10-31 | 1060 |
| 2026-11-01 | 1061 |
| 2026-11-02 | 1062 |
| 2026-11-03 | 1063 |
| 2026-11-04 | 1064 |
Today
+1 stars today
This week
+8 stars this week
This month
+61 stars this month
Momentum
72.0
growth rate 0.76%/day
<div align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/assets/wordmark-dark.svg" /> <source media="(prefers-color-scheme: light)" srcset="docs/assets/wordmark-light.svg" /> <img src="docs/assets/wordmark-light.svg" alt="Wisp Science" width="360" /> </picture> # Wisp Science **The open-source, local-first AI research workbench.** WISP — *Workspace for Intelligent Scientific Practice* <a href="https://github.com/xuzhougeng/wisp-science/releases"><img src="https://img.shields.io/github/v/release/xuzhougeng/wisp-science" alt="Release"></a> <a href="https://github.com/xuzhougeng/wisp-science/releases"><img src="https://img.shields.io/github/downloads/xuzhougeng/wisp-science/total" alt="Downloads"></a> <a href="https://doi.org/10.5281/zenodo.22009273"><img src="https://zenodo.org/badge/1285857639.svg" alt="DOI"></a> <a href="https://github.com/xuzhougeng/wisp-science/blob/main/LICENSE"><img src="https://img.shields.io/github/license/xuzhougeng/wisp-science" alt="License"></a> <a href="https://github.com/xuzhougeng/wisp-science/stargazers"><img src="https://img.shields.io/github/stars/xuzhougeng/wisp-science?style=social" alt="Stars"></a> <br> <a href="https://github.com/xuzhougeng/wisp-science/releases"><img src="https://img.shields.io/badge/Windows-supported-0078D4" alt="Windows supported"></a> <a href="https://github.com/xuzhougeng/wisp-science/releases"><img src="https://img.shields.io/badge/macOS-supported-000000" alt="macOS supported"></a> <a href="https://github.com/xuzhougeng/wisp-science/releases"><img src="https://img.shields.io/badge/Linux-supported-FCC624" alt="Linux supported"></a> [English](README.md) · [简体中文](README_zh.md) · [Website](https://wispscience.com/) · [Releases](https://github.com/xuzhougeng/wisp-science/releases) <img src="docs/assets/app-home.png" alt="Wisp Science desktop app running a bundled RNA-seq analysis demo" width="100%" /> </div> 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](docs/exploration-branches.md) to try a direction without touching the mainline. A [Publication Workspace](docs/publication-evidence.md) 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](docs/project-sync.md) and [project transfer](docs/project-transfer.md) — nothing syncs in the background. ## Get started 1. Open the [download page](https://wispscience.com/?lang=en#download), choose your operating system and processor, and download via Cloudflare. [GitHub Releases](https://github.com/xuzhougeng/wisp-science/releases) is also available. 2. Open a bundled demo — no API key needed — to see a full RNA-seq trajectory. 3. Add a model in **Settings → Models** and start a project. | Platform | Package | |--------
Excerpt of 23,891 characters
Read on GitHub
965
414
7
Codex · OpenAI
5
Cursor Agent
3
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:99b80bfa29fba173, topic:mcp, topic:model-context-protocol, readme:model context protocol
matched fp:99b80bfa29fba173, topic:bioinformatics, topic:scientific-computing, desc:bioinformatics