awesome-autoresearch - autonomous research agent loops
Curated list of self-improvement loops, research agents, and autoresearch systems following Karpathy's framing. Useful index when designing multi-step agent harnesses.
This entry doesn't have a long-form writeup yet. Follow the source link above for the full context.
Recent discussion
From the wider webAgent-Analytics/awesome-multi-agent-orchestrators
github.com · Apr 29, 2026
njulj/Awesome-Agent-Based-Low-Level-Vision
github.com · Apr 29, 2026
peter123023/awesome-claude-api
github.com · Apr 29, 2026
rbbydotdev/awesome-just-bash
github.com · Apr 29, 2026
YouMind-OpenLab/awesome-gemini-3-prompts
github.com · Apr 29, 2026
Featured in
Claude Code tools, plugins, and integrations
The best tools, MCP servers, and harnesses for getting more out of Claude Code - orchestration, observability, telemetry, and remote control.
Multi-agent frameworks and orchestration
Frameworks, harnesses, and DSLs for coordinating multiple AI agents across handoffs, parallel waves, and tool use.
Related entries
agent-hub - one chat surface for every local and remote agent
Open-source hub that connects to Claude Code, Codex, Hermes, OpenClaw, and other agent runtimes - local or on remote machines - through a single chat UI. Less workflow-tied than Conductor.
my-claude-devteam - 12-agent dev team for Claude Code
Drop-in pack of 12 specialized agents and 15 automation hooks that wires Claude Code into a structured P7/P9/P10 review and delivery workflow.
Dispatch - background workers for Claude Code
Claude Code skill that offloads subtasks to background AI workers, freeing the main session's context window. Designed to expand effective context by parallelizing dispatched work.
agent-order - cross-model PRD planning workflow
Hack that has Claude and Codex independently draft PRDs for the same feature, then critique each other's plans before implementation. Avoids the anchoring bias when one model sees the other's answer first.