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.
ResearchClaw is a personal AI assistant built for research: fast to set up, easy to run locally or in the cloud, and ready to integrate with the chat apps you already use. With extensible skills, it helps you streamline literature review, note-taking, experiment tracking, and paper writing—end to end.
| Date | Stars |
|---|---|
| 2026-08-03 | 311 |
| 2026-08-12 | 312 |
| 2026-08-18 | 311 |
| 2026-08-19 | 312 |
| 2026-08-24 | 313 |
| 2026-09-01 | 312 |
| 2026-09-14 | 312 |
| 2026-09-15 | 312 |
| 2026-09-17 | 313 |
| 2026-10-09 | 312 |
| 2026-10-11 | 312 |
| 2026-10-13 | 312 |
| 2026-10-19 | 313 |
| 2026-10-22 | 314 |
| 2026-10-23 | 315 |
| 2026-10-31 | 315 |
| 2026-11-02 | 314 |
| 2026-11-04 | 314 |
Today
— stars today
This week
-1 stars this week
This month
+1 stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <img src="console/public/researchclaw-logo.png" alt="ResearchClaw logo" width="340"> # ResearchClaw > Local-first Research OS for papers, workflows, experiments, channels, and automation. [](https://python.org)     [](LICENSE) [English](README.md) | [中文](README_zh.md) | [Docs](website/public/docs/intro.en.md) | [Roadmap](ROADMAP.md) | [Research-Equality Ecosystem](https://github.com/orgs/Research-Equality/repositories) Part of the [Research-Equality](https://github.com/orgs/Research-Equality/repositories) ecosystem for AI-native research workflows. Persistent research state · Multi-agent runtime · Skills + MCP · Automation + channels [Why ResearchClaw](#why-researchclaw) • [Quick Start](#quick-start) • [Research-Equality Ecosystem](#research-equality-ecosystem) • [What You Get Today](#what-you-get-today) • [Docs](#docs) </div> <a id="why-researchclaw"></a> ## Why ResearchClaw ResearchClaw is the runtime and workspace layer of the broader Research-Equality stack. It keeps long-horizon research work durable: projects, workflows, claims, evidence, experiments, artifacts, reminders, channels, and automation all live in one local-first system instead of dissolving across chat threads, terminals, and scattered folders. | Common AI research workflow pain | What ResearchClaw does instead | | --- | --- | | Research work disappears into one-off chats or shell history | Persists `project -> workflow -> task -> artifact` state with notes, claims, evidence, drafts, and reminders | | Tools for search, execution, writing, and follow-up are split apart | Puts console, automation, channels, APIs, papers, experiments, and memory into one runtime | | It is hard to hand work over between web, terminal, and messaging surfaces | Exposes the same research state through the web console, IM channels, cron jobs, sessions, and control-plane APIs | | Skills, providers, and external tools are glued together ad hoc | Standardizes `SKILL.md`, MCP, provider routing, fallback chains, and per-agent workspace rules | Under the hood, the current codebase combines: - a long-running app runtime with control-plane APIs - a web console for chat, papers, research, channels, sessions, cron jobs, models, skills, workspace, environments, and MCP - multi-agent routing with per-agent workspaces and binding rules - a persistent research state layer for projects, workflows, tasks, notes, claims, evidence, experiments, artifacts, and drafts - built-in channels for `console`, `telegram`, `discord`, `dingtalk`, `feishu`, `imessage`, `qq`, and `voice` - model/provider management with multiple providers, multiple models per provider, and fallback chains - standard `SKILL.md` support, Skills Hub search/install APIs, MCP client management, and custom channels - automation triggers, cron jobs, heartbeat, proactive reminders, and runtime observability - paper search/download, BibTeX utilities, LaTeX helpers, data analysis, browser/file tools, and structured research memory It is still an Alpha project, but it is no longer just a platform shell. The code now includes a minimal research workflow runtime, claim/evidence graph, experiment tracking, blocker remediation, and project dashboard. The biggest remaining gaps are evidence-matrix quality, stronger claim-evidence validation, richer external execution adapters, and submission/reproducibility packaging. <a id="quick-start"></a> ## Quick Start
Excerpt of 11,928 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:79130b1395e6a364, llm:Repository description: 'ResearchClaw is a personal AI assistant built for research... extensible skills... streamline literature review, note-taking, experiment tracking, and paper writing' and topics: agent, copaw, openclaw, personal, research, tools.
matched fp:79130b1395e6a364, llm:Repository description: 'ResearchClaw is a personal AI assistant built for research... extensible skills... streamline literature review, note-taking, experiment tracking, and paper writing' and topics: agent, copaw, openclaw, personal, research, tools.
matched fp:79130b1395e6a364, llm:Repository description: 'ResearchClaw is a personal AI assistant built for research... extensible skills... streamline literature review, note-taking, experiment tracking, and paper writing' and topics: agent, copaw, openclaw, personal, research, tools.