Library
85,336 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
awesome-autoresearch
Agents & frameworksA curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.
git clone https://github.com/webfuse-com/awesome-autoresearch.git -
codex-autoresearch
SkillsA codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss, Lighthouse scores, memory use, query latency, or any other metric you can print from a script.
git clone https://github.com/TheGreenCedar/codex-autoresearch.git -
darwin-skill
Skills达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.
git clone https://github.com/alchaincyf/darwin-skill.git -
evo
Skillsturns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.
git clone https://github.com/evo-hq/evo.git -
Anti-Autoresearch
SkillsDon't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.
git clone https://github.com/wanshuiyin/Anti-Autoresearch.git -
awesome-rsi
AI repositoriesAn Open Index of RSI Papers
git clone https://github.com/Prism-Shadow/awesome-rsi.git -
NanoResearch
Skills🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
git clone https://github.com/OpenRaiser/NanoResearch.git -
FAROS
Agents & frameworksA blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
git clone https://github.com/OpenNSWM-Lab/FAROS.git -
autoguardrails
Datasets & benchmarksAlignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
git clone https://github.com/SantanderAI/autoguardrails.git -
aideml
Agents & frameworksAIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
git clone https://github.com/WecoAI/aideml.git -
CORAL
Agents & frameworksOpen-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
git clone https://github.com/Human-Agent-Society/CORAL.git -
skills
SkillsReusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, Codex, and other skill-compatible agents.
git clone https://github.com/dzhng/skills.git -
agi
AI repositoriesThe first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthroughs here. Fully peer-to-peer. Join from your browser or CLI.
git clone https://github.com/hyperspaceai/agi.git -
ResearcherSkill
PromptsAsks what to optimise and how to measure it, then runs experiments on its own branch.
git clone https://github.com/krzysztofdudek/ResearcherSkill.git -
Research-Assistant-Agent
Agents & frameworksMulti-agent research execution system: paper reproduction, benchmark evaluation, AutoResearch and claim-evidence graphs
git clone https://github.com/zzp1221/Research-Assistant-Agent.git -
forest
Agents & frameworksFOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence
git clone https://github.com/mikamikasuki/forest.git -
Simmer
MCP serversTrade prediction markets with AI agents — skill discovery, autoresearch, and execution.
simmer-mcp@3.3.2 -
researchforge
SkillsA lab protocol for coding agents. Freeze baselines, run hypotheses in isolated worktrees, reject failures and validate improvements from Claude Code, Cursor or a direct API key (Gemini/Anthropic/openAI).
git clone https://github.com/forger-labs-hq/researchforge.git -
Recursive: Flint (free)
ModelsFlint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...
recursive/flint-v1.0:free
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.