🔬 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 — file-based operating model for human direction and agent execution.
• uditgoenka/autoresearch - Claude Code skill that generalizes autoresearch into a reusable loop for software, docs, security, shipping, debugging, and other measurable goals.
• leo-lilinxiao/codex-autoresearch - Codex-native autoresearch skill with resume support, lessons across runs, optional parallel experiments, and mode-specific workflows.
• junjunjunbong/research-loop - Autoresearch-style Agent Skill for Codex and Claude Code with a deterministic runner, plan-hash approval, isolated Git worktrees, authoritative metric evaluation, and an append-only experiment ledger.
• xieyulai/steer - Governed experiment framework where coding agents edit training code and run rounds while the task, scorer, and evidence stay fixed.
• SeeleAI/Thoth - Dashboard-first Claude Code and Codex runtime for autoresearch, with durable runs, locked work items, visible ledgers, and reviewable verdicts.
• supratikpm/gemini-autoresearch - Gemini CLI skill that generalises autoresearch to any measurable goal. Gemini-native: uses Google Search grounding as a live verification source inside the loop, true headless overnight mode via --yolo --prompt, and 1M token context. Also works in Antigravity IDE via .agents/skills/.
• davebcn87/pi-autoresearch - pi extension plus dashboard for persistent experiment loops, live metrics, confidence tracking, and resumable autoresearch sessions.
• drivelineresearch/autoresearch-claude-code - Claude Code plugin/skill port of pi-autoresearch, with a clean experiment-loop workflow and a concrete biomechanics case study.
• greyhaven-ai/autocontext - Closed-loop control plane for repeated agent improvement, with evaluation, persistent knowledge, staged validation, and optional distillation into cheaper local runtimes.
• Necmttn/ax - Local retro loop for AI coding agents: captures session traces, turns repeated friction into proposals, and tracks accepted fixes as experiments.
• jmilinovich/goal-md - Generalizes autoresearch into a GOAL.md pattern for repos where the agent must first construct a measurable fitness function before it can optimize.
• james-s-tayler/lazy-developer - Claude Code skill that orchestrates autoresearch across a prioritized sequence of optimization goals (coverage, test speed, build speed, complexity, LOC, performance) using GOAL.md as the engine. Supports standalone and Ralph Mode multi-instance execution.
• mutable-state-inc/autoresearch-at-home - Collaborative fork of upstream autoresearch that adds experiment claiming, shared best-config syncing, hypothesis exchange, and swarm-style coordination across many single-GPU agents.
• zkarimi22/autoresearch-anything - Generalizes autoresearch to any measurable metric — system prompts, API performance, landing pages, test suites, config tuning, SQL queries. "If you can measure it, you can optimize it."
• Entrpi/autoresearch-everywhere - Cross-platform expansion that auto-detects hardware config and starts the loop. The "glue and generalization" half of autoresearch.
• ShengranHu/ADAS - Automated Design of Agentic Systems — ICLR 2025. Meta-agents that invent novel agent architectures by programming them in code.
• MaximeRobeyns/self_improving_coding_agent - SICA: Self-Improving Coding Agent that edits its own codebase. ICLR 2025 Workshop paper demonstrating scaffold-level self-improvement on coding benchmarks.
• peterskoett/self-improving-agent - Alternative self-improving agent architecture with reflection and meta-learning cycles.
• metauto-ai/HGM - Huxley-Gödel Machine for coding agents — applies self-improvement to SWE-bench performance via meta-level optimization.
• gepa-ai/gepa - GEPA (Genetic-Pareto) — ICLR 2026 Oral. Reflective prompt evolution that outperforms RL (GRPO) on benchmarks. Optimizes any textual parameters against any metric using natural language reflection.
• sentient-agi/EvoSkill - Automated skill discovery for coding agents: evolves reusable skills and prompts from failed trajectories against benchmarks, with support for Claude Code, Codex CLI, OpenCode, OpenHands, and Goose.
• MrTsepa/autoevolve - GEPA-inspired autoresearch for self-play: mutate code strategies, evaluate head-to-head, rate with Elo/Bradley-Terry, branch from the Pareto front. Agent reads match traces to target mutations. Works as a Claude Code skill.
• HKUDS/ClawTeam - Agent swarm intelligence for autoresearch — spawns parallel GPU research directions, distributes work across agents, aggregates results.
• Orchestra-Research/AI-Research-SKILLs - Comprehensive skill library including autoresearch orchestration with two-loop architecture (inner optimization + outer synthesis).
• WecoAI/aideml - AIDE: Tree-search ML engineering agent that autonomously improves model performance via iterative code generation and evaluation.
• weco.ai - Weco: Cloud platform for AIDE with observability, e