Better subagent experience for Codex and Claude users

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local alternative to SERP APIs with MCP server integration.

Anti-detect browser automation CLI & Skills for AI agents — Camoufox-powered fingerprint spoofing, no bot-detectable Playwright leaks

Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.

Local-first workspace for Claude Code, Codex CLI, and Gemini CLI with sessions, analytics, workflows, and tools

Multi-Agent + Automation: Workflows, Automation, Self-Improving Agents

Agenta is a workspace where you and your team build agents and automations.

Agor - team command center for all things agentic

A public gallery of animated pets for Codex, Claude Code, DeepSeek Harness, Hermes, OpenCode, Gemini CLI, and more.

secure multiplexed execution paths for agents - zero trust, zero setup, zero latency.

Type `ralph "prompt"` to start open code in a ralph loop. Also supports a prompt file & status check. Open Code, Claude Code, Codex, Copilot

Remote approvals, policy checks, and execution evidence for unattended AI agents.

Learn it. Build it. Ship it for others.

Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

Agent-friendly ComfyUI workflow skills for OpenClaw, Hermes Agent, Codex, and Claude Code; complementary to Comfy official local MCP.

Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-hosted server, or Docker.

Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.

Comate is a desktop AI workspace that brings Claude Code into a polished, native app experience. Organize multiple projects in folder-backed workspaces, chat with AI through streaming sessions, explore files, and manage tasks — all in one place.

A self-hosted workspace where people and coding agents work together across projects, sessions, and providers.

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

The fastest workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

🦦 ADHDev — Agent Dashboard Hub. Monitor & control AI coding agents from a single dashboard. Self-hosted, open-source.