awesome-autoresearch — security grade SAFE, quality 52/100

Security audit verdict: SAFE · quality 52/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by webfuse-com · Agent Tool · ★ 2.5k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is awesome-autoresearch safe to install? View the security audit →

About awesome-autoresearch

🔬 Awesome Autoresearch A curated, high-signal index of autonomous improvement loops, research agents, and descendants inspired by karpathy/autoresearch. Contents 🛠️ General-purpose descendants 🔬 Research-agent systems 💻 Platform ports and hardware forks 🎯 Domain-specific adaptations 📊 Evaluation & benchmarks 📈 Notable use cases and writeups 📚 Related resources 📄 License 🛠️ General-purpose descendants kayba-ai/recursive-improve - Recursive self-improvement framework where agents capture execution traces, analyze failure patterns, and apply targeted fixes with keep-or-revert evaluation. vukrosic/auto-research - Docs-only control plane for an open autonomous AI research lab — fil

agentic-systemsai-agentsai-researchai-toolsautonomous-agentsautoresearchawesome-listclaude-codeexperiment-loopskarpathy

Quick Facts

Stars2,539
Forks193
CategoryAgent Tool
Quality Score52.3815673844076/100
Open Issues6
Last Updated2026-09-21
Created2026-03-20
Platformsclaude-code
Est. Tokens~15k

Compatible Skills

These tools work well together with awesome-autoresearch for enhanced workflows:

  • autoresearch — semantic(0.42)+complementary+rare_topics+similar_pop+shared_platform (64%)
  • awesome-autoresearch — semantic(1.00)+rare_topics+similar_pop+shared_platform (60%)
  • awesome-autoresearch — semantic(1.00)+rare_topics+similar_pop+shared_platform (60%)
  • evo — semantic(0.29)+complementary+rare_topics+similar_pop+shared_platform (55%)
  • de-anthropocentric-research-engine — semantic(0.26)+complementary+rare_topics+similar_pop+shared_platform (53%)

awesome-autoresearch alternative? Top 6 similar tools

Looking for a awesome-autoresearch alternative? If you're comparing awesome-autoresearch 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.

  • awesome-autoresearch by alvinreal · ⭐ 2.2k

    A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Ka

  • awesome-autoresearch by alvinunreal · ⭐ 995

    A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Ka

  • awesome-autoresearch by WecoAI · ⭐ 1.0k

    Curated list of AutoResearch use cases with optimization traces and open source implementations

  • CORAL by Human-Agent-Society · ⭐ 961

    Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with gradin

  • evo by evo-hq · ⭐ 1.5k

    turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then run

  • NanoResearch by OpenRaiser · ⭐ 1.4k

    🦞+🔬 NanoResearch: The Autonomous AI Research Assistant

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Frequently Asked Questions

What is awesome-autoresearch?

awesome-autoresearch is A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.. It is categorized as a Agent Tool with 2.5k GitHub stars.

How do I install or use awesome-autoresearch?

You can find installation instructions and usage details in the awesome-autoresearch GitHub repository at github.com/webfuse-com/awesome-autoresearch. The project has 2.5k stars and 193 forks, indicating an active community.

What are the best alternatives to awesome-autoresearch?

The top alternatives to awesome-autoresearch on Agent Skills Hub include awesome-autoresearch, awesome-autoresearch, awesome-autoresearch. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Agent Tool tools