autoresearch repositories
Trending repositories tagged autoresearch, ranked by trending score. Updated daily.
-
1
Leeroo-AI/kapso
Kapso by Leeroo: an engine that runs experiments toward an objective, deploys the best solution on your stack and learns from every run into a bank of lessons with a credence score and a boundary. First on RelBench and ALE-Bench, top open-source on MLE-Bench, above every human contestant at IOAI 2026.
GitHub · Python · 230 stars · 33 forks · +93 stars in 24 hours · Trending score 3.45
-
2
alchaincyf/darwin-skill
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.
GitHub · HTML · 7,016 stars · 727 forks · +18 stars in 24 hours · Trending score 2.72
-
3
leo-lilinxiao/codex-autoresearch
Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.
GitHub · Python · 3,237 stars · 130 forks · 0 stars in 24 hours · Trending score 1.88
-
4
uditgoenka/autoresearch
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
GitHub · Shell · 6,850 stars · 492 forks · +4 stars in 24 hours · Trending score 1.31
-
5
onyx-robotics/onyx-agent
Use large-scale AI agent teams to rapidly discover code improvements and "autoresearch" your hardware systems.
GitHub · TypeScript · 72 stars · 2 forks · 0 stars in 24 hours · Trending score 1.10
-
6
Prism-Shadow/awesome-rsi
An Open Index of RSI Papers
GitHub · JavaScript · 617 stars · 38 forks · 0 stars in 24 hours · Trending score 0.94
-
7
tuan3w/qwen-warp
Fast Qwen3.8-27B for one RTX 3090. 200k context, 100+ tok/s. Custom CUDA decode engine, OpenAI-compatible API.
GitHub · Python · 50 stars · 6 forks · +1 stars in 24 hours · Trending score 0.83
-
8
alibaba/atrex-kernel-agent
An end-to-end agent project for GPU kernel implementation, analysis, profiling, and iterative optimization. It helps an agent turn PyTorch logic or an existing kernel into a high-performance GPU kernel through a structured, profile-driven workflow.
GitHub · Python · 212 stars · 41 forks · 0 stars in 24 hours · Trending score 0.83
-
9
dzhng/skills
Reusable AI agent skills for growing software farms: explore ideas, write specs, let agents build unattended, then curate what grew — weed, prune, and review. Works with Claude Code, Codex, and other skill-compatible agents.
GitHub · HTML · 1,504 stars · 86 forks · 0 stars in 24 hours · Trending score 0.55
-
10
outerloop-science/outerloop
Autoresearch agents that improve your benchmark: independent re-measurement, enforced budgets, results as pull requests
GitHub · Python · 44 stars · 7 forks · 0 stars in 24 hours · Trending score 0.26
-
11
isatimur/ai-engineering-book-lab
A source-anchored book on AI engineering, auto-researched from 794 practitioner talks. Every claim links to the exact second of the video it came from; every chapter is graded by a panel of three rival LLMs (no model grades its own style). Live at fromcopilottocolleague.com
GitHub · HTML · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.22
-
12
SeeleAI/Thoth
🐦 Thoth — Dashboard-First Orchestration Runtime for Autoresearch
GitHub · Python · 51 stars · 4 forks · 0 stars in 24 hours · Trending score 0.14
-
13
richardcsuwandi/kernaut
Kernel autoresearch for open-ended model discovery
GitHub · Python · 12 stars · 0 forks · 0 stars in 24 hours · Trending score 0.14
-
14
rekursiv-ai/trackinizer
Epistemological database for agent and human efforts, beliefs, and findings.
GitHub · Python · 129 stars · 25 forks · 0 stars in 24 hours · Trending score 0.10
-
15
hiloopai/piloop
Autoresearch for any repo: coding agents try ideas, piloop scores every commit and keeps what wins
GitHub · Python · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.09
-
16
forger-labs-hq/researchforge
A 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).
GitHub · Python · 10 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08
-
17
RightNow-AI/autokernel
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
GitHub · Python · 1,630 stars · 166 forks · 0 stars in 24 hours · Trending score 0.08
-
18
kongtou20070406/research-direction-selector
Evidence-driven autoresearch for academic research. Plan experiments, enforce budgets, preserve execution receipts, and verify supported results with Codex, Claude Code and Lean.
GitHub · Python · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.04
-
19
rekursiv-ai/priml
Strongly typed configurable building blocks for A/B testing ML research.
GitHub · Python · 55 stars · 16 forks · 0 stars in 24 hours · Trending score 0.04
-
20
rekursiv-ai/wesearch
A web research toolkit for agents.
GitHub · Python · 10 stars · 2 forks · 0 stars in 24 hours · Trending score 0.04
-
21
mikamikasuki/forest
FOREST 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
GitHub · Python · 354 stars · 54 forks · 0 stars in 24 hours · Trending score 0.03
-
22
OpenNSWM-Lab/FAROS
A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
GitHub · Python · 3,044 stars · 390 forks · 0 stars in 24 hours · Trending score 0.00
-
23
hyperspaceai/agi
The 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.
GitHub · JavaScript · 2,080 stars · 250 forks · 0 stars in 24 hours · Trending score 0.00
-
24
greyhaven-ai/autocontext
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
GitHub · Python · 1,326 stars · 117 forks · 0 stars in 24 hours · Trending score 0.00