GitHub Trending: Autonomous Research and Self-Improving Agents Inspired by Karpathy
tom_doerr · x · 2026-08-11
This repository curates a high-signal index of autonomous improvement loops, research agents, and systems inspired by Andrej Karpathy's autoresearch. The list covers several key areas:
- General-purpose descendants: Frameworks like recursive-improve where agents capture execution traces, analyze failures, and apply targeted fixes.
- Research-agent systems: File-based operating models for autonomous AI labs like auto-research.
- Platform ports & adaptations: Tools generalizing the concept into Claude Code skills for software, docs, and debugging.
- Evaluation & use cases: Includes benchmarks and detailed writeups.
More from coding & agent
- Malicious VS Code Extensions Deliver XWorm via Marketplace — cyb3rops · 2026-08-11
- RAG Me Up: A Comprehensive Open-Source Tutorial for RAG in Production — FutureClubNL · 2026-08-11
- Anthropic's 'Loop Engineering' Hype Called Out as Repackaged Cron Jobs — thor123321 · 2026-08-11
- Goodbye Stale Notes: Building a Local-First Memory System for Agents — linklore_dev · 2026-08-11
- Open-Source AI Penetration Testing Agent EVA Generates Attack Strategies and Executes Commands — tom_doerr · 2026-08-11
- After 6 Months of AI Doc Agents: Context-Gathering Beats Writing — Stock-Parking-411 · 2026-08-11