by AutoX-AI-Labs · Agent Tool · ★ 855
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is AutoR safe to install? View the security audit →
AutoR: A Human-Centered Research OS AI handles execution. Humans own the direction. A terminal-first research harness, with a local browser Studio, that turns long, messy research work into reproducible, artifact-backed runs. Overview · News · Showcase · Quick Start · How It Works · Run Layout · Architecture · Roadmap
| Stars | 855 |
| Forks | 23 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 52.3907740928299/100 |
| Last Updated | 2026-06-15 |
| Created | 2026-03-13 |
| Platforms | claude-code, cli, python |
| Est. Tokens | ~22k |
Looking for a AutoR alternative? If you're comparing AutoR with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk
🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
The most autonomous agent framework. No approval loops. No babysitting. Configure once, forget forever.
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.
An introduction to the world of AI Agents
Explore other popular agent tool tools:
AutoR is AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.. It is categorized as a Agent Tool with 855 GitHub stars.
AutoR is primarily written in Python. It covers topics such as agent, ai, ai-scientist.
You can find installation instructions and usage details in the AutoR GitHub repository at github.com/AutoX-AI-Labs/AutoR. The project has 855 stars and 23 forks, indicating an active community.
The top alternatives to AutoR on Agent Skills Hub include AutoR, ResearchClawBench, aeon. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: