coding-agent-orchestration

Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable workflows, and consistent engineering standards across AI coding agents and harnesses.

Asynchronous Pi subagents and agent fleet orchestration for parallel coding agents with nested delegation, background work, and supervision in herdr.

Open-source multi-agent orchestration harness for OpenCode — specialized agents, durable workflows, research, planning, implementation, review, and validation.

Craft is a Claude Code plugin that asks you the product questions and works out the technical ones. Features get planned, built, and tested, with your codebase read-only until you approve the work. Point at a live page to change it. The calls you make - decisions, design tokens, the tweaks you loved - carry into every build after.

Local-first AI mission orchestrator

Baton coordinates coding agents. Each worker handles a focused task, and one orchestrator checks the result.

ACRYL Blends - the extracted Cordis-based agentic framework: plugins, live extension, blueprints

Multi-agent orchestration extension for the pi coding agent: bounded worker threads, structured episode summaries, and a risk-based review workflow.

AI agent orchestration platform. Manage multiple coding agents (Claude, Vibe) through a unified interface with session management, real-time streaming, and task scheduling.

💬 Show your coding agent's implicit assumptions in a popup & correct them before they go off the rails. Built for Codex.

twindex runs 2 codex instances and let them pair program together

Local Messaging and Task Tracking to Connect Coding Agents

An AI coding agent built with Go & React 19. Reads, edits, runs code, and features a full undo safety loop.

Prompt automation for terminal-based agents, for VSCode.

AI coding agent for local LLMs (LM Studio, llama.cpp, Ollama, vLLM) with a built-in coding benchmark. Your code stays on your machine.

Governed agent runtime with tool-level policy enforcement

I want a multi-agent app with agents UX like cursor ai, but opensource MIT licensed.

Build high-quality software using a toolkit designed for predictable product outcomes and defined scenarios.

Orchestrating coding agents in browser and smart phone

Agent-Orchestrated Development – is a Claude Code plugin that turns one strong model into an architect and cheaper, cross-family coding agents into implementers.