# webfuse-com/awesome-autoresearch

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

Repository: https://github.com/webfuse-com/awesome-autoresearch
Canonical: https://ross.abutalabs.com/products/awesome-autoresearch
Homepage: https://www.webfuse.com/autoresearch
License: NOASSERTION
License Family: other
Topics: agentic-systems, ai-agents, ai-research, ai-tools, autonomous-agents, autoresearch, awesome-list, claude-code, llm-agents, research-agents, scientific-discovery, self-improving-systems, experiment-loops, karpathy, karpathy-inspired
Last push: 2026-08-10T11:34:18+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 11
- inputs: {"age_days": 166, "days_push": 23, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2499, forks 187 (observed 2026-08-28T04:06:56.856936+00:00)

## What it is
A curated awesome-list indexing autonomous improvement loops, research agents, and autoresearch-style systems inspired by Andrej Karpathy's autoresearch keep-or-revert loop. It catalogs general-purpose descendants, research-agent systems, platform ports, domain-specific adaptations, and evaluation benchmarks.

## Use cases
- find autonomous AI research agent frameworks
- discover tools that run automated experiment loops with keep-or-revert evaluation
- compare autoresearch implementations for Claude Code and Codex
- learn how Karpathy's autoresearch loop works
- find self-improving agent systems for ML training optimization
- locate benchmarks for autonomous research agents

## When to choose
- you want a curated index of autoresearch-style tools and adaptations rather than a single implementation
- you are exploring the ecosystem of autonomous research loops before picking a framework
- you want references across domains like ML training, GPU kernels, and software metrics

## When to avoid
- you need a runnable autoresearch tool itself rather than a list of links
- you need guaranteed permissive licensing for the listed projects (the list itself has a non-standard license notice)
- you need production support or maintenance guarantees for any listed project

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, machine-learning, developer-tools
- domain: artificial-intelligence, machine-learning, awesome-lists
- platform: cross-platform
- tags: awesome-list, autoresearch, research-agents, self-improving-systems, keep-or-revert, karpathy, experiment-loops, curated-list, ai-agents, research

## Member repositories
- webfuse-com/awesome-autoresearch (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:56.856936+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:27:00.611075+00:00, confidence not recorded.
  - readme: https://github.com/webfuse-com/awesome-autoresearch (fetched 2026-08-28T04:06:56.856936+00:00, sha 8f246cc0223e)
  - homepage: https://www.webfuse.com/autoresearch (fetched 2026-08-29T10:09:45.450393+00:00, sha b868ab804c9b)
  - site_page: https://www.webfuse.com/about (fetched 2026-08-29T10:09:45.457009+00:00, sha a39f054cad38)
  - site_page: https://www.webfuse.com/pricing (fetched 2026-08-29T10:09:45.453599+00:00, sha 9e565fb00f40)
  - site_page: https://dev.webfuse.com (fetched 2026-08-29T10:09:45.455393+00:00, sha 4facf1eeecfd)
- Data as of 2026-08-30T08:39:29.467469+00:00.