autoresearch
autoresearch: AI agents running research on single-GPU nanochat training automatically. It is ranked #240 on the Stars Radar, in AI agents. Agentik OS starred it 240 days ago, and it has 99.4k GitHub stars.
Alternatives to autoresearch
- security-audit-skill — A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
- unslop — A Claude skill that turns vibecoded, AI-looking UI into a designed interface
- hallmark — Anti-AI-slop design skill for Claude Code, Cursor, and Codex.
- TradingAgents — TradingAgents: Multi-Agents LLM Financial Trading Framework
- open-duet — Open-source, self-hosted alternative to Claude Duet: AI coworkers (named agents) with instructions, memory, routines,…
- agenttrail — Local observability for AI coding agents. Agenttrail Map shows project structure and activity; Agenttrail Kitchen…
autoresearch in numbers
- Rank on the Stars Radar: #240 of 314
- 99.4k GitHub stars
- Starred by Agentik OS 240 days ago, last push 225 days ago
- Owner: karpathy on GitHub
- Market: AI agents
FAQ
What is autoresearch?
AI agents running research on single-GPU nanochat training automatically Agentik OS starred it on GitHub 240 days ago; it is ranked #240 on the Stars Radar.
Is autoresearch free?
It is an open-source repository on GitHub; check its license before use.
Who makes autoresearch?
The GitHub account karpathy. The repository has 99.4k GitHub stars.
Every repository Agentik OS stars on GitHub is read and classified by AGK Intelligence: what it is, which market it belongs to, how useful and how mature. 314 repositories, 10 markets. The stars are read every 5 minutes — last update 2026-11-06 16:55 UTC. Full method.