autoresearch
Autoresearch adapter — collaborative autonomous ML research over the Decentralized Knowledge Graph
Autonomous experiment loop for pi — run, measure, keep or discard. Inspired by karpathy/autoresearch.
Faithful OpenClaw port of pi-autoresearch.
OpenCode Autoresearch loop, benchmark, dashboard, and finalize plugin.
Orchestration controls for Pi-Rogue: scheduled loop, goal resolution, and autoresearch.
Autoresearch plugin for OpenCode - automated benchmark-driven optimization loop
MCP server for Simmer — skill discovery, execution, autoresearch, and AI market tools
Orchestration controls for PiRogue: loop, goal, and autoresearch.
Autoloop/autoresearch extension for Pi with multi-lane isolation
Autonomous trading strategy discovery for Base DEX — Karpathy-style autoresearch with LCM memory
Autonomous recursive self-improvement engine for OpenCode and Hermes Agent. Subagent-first iteration loop with mechanical verification.
Pi extension that lets smaller models phone a stronger advisor model when autoresearch gets stuck.
AutoResearch 平台 CLI 与 agent skill 初始化器
Multi-agent primitives for Claude Code: /stochastic (consensus), /model-chat (debate), /fanout (research), /skillbuilder (skill-craft), /autoresearch (hill-climb).
TUI tool for autoresearch — autonomous experiment loops on any codebase
Install an autonomous AI research harness for Codex, Claude Code, Hermes, and other coding agents.
Autonomous experiment loop for pi — run, measure, keep or discard. Inspired by karpathy/autoresearch.
Claude Code skill: apply the autoresearch methodology to any LLM application or model training project
Autonomously optimize travel plans using the autoresearch pattern
Scaffold autonomous webapp research loops — adapts karpathy/autoresearch for any web application
Pi extension that auto-sends a 'continue' message whenever the agent stops, so local agents can run autonomous overnight research loops (autoresearch-style) without babysitting.
Autonomous ML research harness for Claude Code. The autoresearch loop as a formal protocol — iteratively trains, evaluates, and improves ML models with structured experiment tracking, convergence detection, immutable evaluation infrastructure, and safety
Autonomous prompt optimizer using the Karpathy autoresearch pattern
Universal autoresearch CLI — install skills, track experiments, view results across any AI coding agent
Autonomous research engine — background research tasks and synthesis
ascent-research — an incremental research workflow CLI for AI agents. Every session resumes; knowledge accretes across runs. Mixes HTTP, browser, and local file ingest into a durable per-session wiki + figure-rich HTML report.
Agent-agnostic iterative optimization CLI
Clark Hash: stateless sparse Johnson-Lindenstrauss sketches for neural embeddings
Distributed autoresearch across multiple machines and contributors
Iterative-improvement harness: runs an agent CLI in sandboxed git worktrees against a scoring command, keeping improvements until a deadline fires.