Code agents

High-signal multi-agent pull request reviews for Pi

Production-grade SEO, AEO, and GEO agent skill with auditable detection, claim governance, evidence validation, and multi-agent installation.

Profile-driven, harness-neutral multi-agent workflow runtime for repository-local AI teams.

Next-generation multi-agent AI collaborative development platform. Combines XKZOOM multi-agent collaboration with Claude Code style single-agent coding efficiency, fully autonomous and controllable.

Multi-agent OpenCode config for coding, content, research, and QA workflows

Multi-agent roundtable debate plugin for OpenCode. Real cross-examination, quality-gated consensus, and dissent tracking.

Shared utility modules for Atabey — AI Governance & Multi-Agent Platform / Orchestrator

HiAi OpenCode Plugin — multi-agent orchestration for OpenCode with 10 agents, LSP tools, browser automation, Memory, Session management, and Caveman protocol

ShellX Cognitive Developer Engine — goal-driven CLI with LinkX memory, IDE integration, and multi-agent diagnostics

Local-first delivery cockpit and multi-agent workflow for software projects.

Installable TradingAgents multi-agent stock-analysis skill + Rust data tool (bunx/npx; installer + stock/news/fundamentals/sentiment/fund CLI)

CLI-first autonomous multi-agent engineering loop for any codebase

AI coding agent with multi-agent orchestration and a terminal-first workflow

Local agent orchestration CLI with task routing, backend delegation, multi-agent workflows, governed remote coding, and optional memory integrations.

Allye multi-agent plugin for OpenCode — planning, building, reviewing, and delivering with structured workflows

Agent-aware port ownership and guarded orchestration for multi-agent local development

Governed multi-agent SDLC pipeline for opencode

Pluggable tmux-based multi-agent crew for Claude Code — drop into any repo.

Gearbox — single-source-of-truth AGENTS.md protocol for multi-agent (Claude Code + Z Code) projects. Scaffold + downstream sync tools.

Fleet-style multi-agent framework scaffolder for Claude Code (Captain -> Firstmate -> Crews).

Code Intelligence MCP Server — multi-agent SDLC pipeline with semantic memory, code graph, and draw.io integration

IMH-Code — Imam Hussain Coding Harness Platform. A fast-first multi-agent AI coding framework with intelligent model routing. 19 generic role-based agents (planner, nextjs-executor, laravel-executor, etc.), configurable testing strategy, and 7 token-savin

Portable, stack-agnostic multi-agent development pipeline for Claude Code, Codex CLI, Cursor, Gemini CLI and OpenCode — install the core, run /cohorte-init-pipeline, and it adapts to your project's stack.

Local-first multi-agent ideation bridge for Omnibus.

Multi-agent software development workflow system

Multi-agent orchestration for coding CLIs — dispatch tasks to Claude Code, Codex, Kimi, OpenCode, or Gemini workers and block until they actually report back.

RakshakAI — AI-powered security scanner & chat. Scan 20+ languages, 150+ vulnerability patterns, 65+ AI models across 9 providers, multi-agent swarm, offline regex engine.

File-backed Memory MCP Server for multi-agent coordination

Swarm-first multi-agent messaging and task orchestration extension for Pi

Pi extension for delegating focused work to specialized subagents - foreground, background, and multi-agent chains.

SoMi — multi-agent engineering workflow system: plan, code, review — with SOLID/OWASP guardrails, deterministic hooks, and a global ruleset.

SNS-MyAgent — BYOK coding agent CLI. Multi-agent + Telegram + self-learning memory. ~120MB binary, zero forced cost.

Read-only TUI to watch Claude Code multi-agent workflows live

A coven of coding agents in your terminal — multi-agent, skill-driven, guarded.

Multi-agent orchestration suite for Pi — 6 modes, 43 extensions, 11 themes

CLI orchestrator for multi-agent AI debates and decision-making with Codex, Claude Code, OpenCode, Vibe, and Ollama.

Multi-agent orchestration for Pi: autonomous subagents, worktrees, swarms, schedules, handoffs, prompt compression, and live TUI observability.

Enterprise-grade multi-agent plugin for OpenCode — Vibe (rapid prototyping), Spec (structured specification), Ask (research assistant), and Quality Gate (ISO 25010 quality assurance).

Multi-agent orchestration for Claude Code via Redis streams and MCP

Scaffold production-grade multi-agent AI systems into any repository

Interactive setup for the Maestro skill orchestrator (multi-agent)

Weave your Claude Code & Codex sessions into a team that talks to each other — multi-agent messaging over tmux, no daemon, no MCP.

Local-first persistent vector memory, MCP tooling, and multi-agent workflows for AI assistants

Multi-agent orchestration for software teams — AI squads that spec, build, test, refactor, and review code

Real-time dashboard for OpenCode multi-agent activity, sessions, status, and tool usage

A source-first multi-agent CLI for planning, executing, reviewing, and resuming scoped code changes.

LiRoah coding agent CLI with multi-agent collaboration and plan/auto modes

Autonomous multi-agent UI software development factory

Draht GSD, multi-agent, TDD and DDD workflows as a Codex plugin. Install with `npx draht-codex install`.

Agent-Nuvira SDK — Build custom agents for the Agent-Nuvira multi-agent orchestration system

Spec-Driven Development harness: single source of truth in .forge/, multi-agent adapters (Claude/Codex/Cursor/Gemini/…), native code graph and deterministic validators. Zero runtime deps.

Multi-agent company, ETF and market-index research workflow for Codex & Claude Code: sourced evidence, method seats, bull/bear debate and portfolio-manager synthesis.

Deterministic runtime identity for multi-agent git worktrees

A universal initializer and Codex plugin for multi-agent product, spec, implementation, QA, and release workflows.

Draht GSD, multi-agent, TDD and DDD workflows as a Claude Code plugin. Install with `npx draht-claude install`.

nForma — Multi-agent coding orchestrator with quorum consensus and formal verification (TLA+, Alloy, PRISM). Consensus before code, proof before production.

Multi-agent orchestration for AI coding agents, designed to survive failure — a plain-file brain, git as the only durable layer, cheap subagent fleets, and guardrails enforced in code.

File-backed Memory MCP Server for multi-agent coordination

MetaHarness example — multi-agent research dossier scaffold for Claude Code with scout, web search, grading, synthesis (npx @metaharness/research my-bot)

Multi-agent skills for CloudGrid: login, claim, init, plug, logs, share, feedback, brain. Install in Claude Code, Codex, or Cursor.

Multi-agent orchestration framework — create AI squads that work together

A Codex-first multi-agent council that turns independent model debate into an inspectable Co-Result.

Category Theory-based Multi-Agent AI framework. Domains as Categories, Agents as Functors, communication as Natural Transformations, Meta AI as Lax Colimit.

Advanced AI-powered terminal coding assistant with multi-agent orchestration, sub-agent spawning, ACP protocol, OS-level sandboxing, spec-driven development, smart monitoring, multi-model routing, MCP Apps, auto-updater, and 23+ free models

Cross-IDE agent framework for Unity/C# game-development — one-command install

Izanagi AI - Modular Skill-Oriented AI Prompt & Agent Framework for Autonomous Software Engineering

An LLM-native Typescript VM built on top of botruntime Zui - code-generation agent framework

ReAct Agent framework for coding tasks

Queron AI Agent Framework — opencode setup wizard

myai — a self-owned, git-versioned AI memory + multi-agent framework. Plug any agent (Claude, Cursor, Gemini, Codex, opencode) into your own portable brain so it boots already knowing your projects, decisions, and context. Local-first (Docker), MCP-native

Eve (Vercel agent framework) telemetry integration for telemetry.dev.

The AI Agent Framework — sandboxed multi-agent orchestration, high-throughput stateful agents, modular agent session manager & runtime for pi / codex / claude

> Local tracing & observability devtool for the Rejelly agent framework — inspect traces, spans, tool calls, and token usage.

Runtime services for the Hanfani agent framework: the activity-summary grammar (emit + decode), an audit-log store and activity bus, a policy-monitor (objectives) engine, usage reporting, connection profiles, and an opt-in gate auto-approver.

Headless agent framework with Bash, Ripgrep, and MCP support - invocable via TypeScript SDK, Python SDK, and CLI

This project is a Claude-compatible, LLM-agnostic sub-agent framework that simulates a complete SaaS product team. It is delivered as a reusable, developer-ready NPM package.

agentic — AI-powered terminal coding agent

An MCP Server acting as an Agentic SDLC Control Plane — helps AI coding agents plan, create, test, review, secure, and release software following GitHub Agentic AI best practices.

Eval-driven agentic harness for building production Stellar dApps. 6 specialist agents, 5 eval definitions, full contract/frontend/backend templates, and npx CLI scaffolding with npx skill support. https://stellar-agentic-framework.vercel.app

the pi adapter for agentic-kit — Constructive's typed db tools, confirm gate, and the run-log/metering/gate lanes attached to a pi coding-agent session

Vendor-neutral, evidence-backed readiness benchmark for agentic software development harnesses.

Machine-level setup, healing, and verification kit for your AI agent stack (ruflo/claude-flow, agentic-qe, Claude Code glue) — cross-platform, zero-dependency

Matrix — Agentic OS for OpenCode. Personalizable, communicating, self-improving, resilient.

A from-scratch harness for agentic coding.

Offline CLI for inspecting and safely installing Agentic Workflows bundles.

Agentic coding CLI for nenna.ai (Open WebUI) instances.

Agentic MCP — local coding tools for ChatGPT Developer Mode and other MCP clients. Tested with ChatGPT Plus via HTTPS tunnel; availability varies by plan and rollout. Independent project, not affiliated with OpenAI.

SynAIpse AI Delivery Harness for evidence-backed agentic software delivery

Code-aware agentic tester: map your app, write product flows with Claude, compile Playwright, run headless, and audit when the app changes.

Tau is a custom agentic harness built with pi extensions

Webpack adapter for Agentic React local dev integration

Agentic QA hub — spec-tool agnostic

One CLI to drive many agentic coding harnesses non-interactively and return uniform JSON.

Scaffold a guuey agentic app: code-mode agent + custom MCP + ggui + web, local pnpm dev, one-command guuey deploy.

Agentic platform for streamlining hardware and software development

agentic-debug-mode binary for Linux x64

agentic-debug-mode binary for Linux ARM64

agentic-debug-mode binary for Windows x64

agentic-debug-mode binary for macOS Intel

Cross-CLI agentic skills — install once, use with 45+ compatible AI coding tools