Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 32 of 62
Multi-agent AI debate app where model teams argue, challenge claims, track evidence, and produce judged verdicts with analytics.
ASDEV — Production Web Systems, Technical SEO & Autonomous Governance. Mother repository for strategy, multi-agent orchestration, and the live portfolio website.
Codex-led Qwen and DeepSeek AI team router via MCP, with token-efficient worker scripts and safety gates.
Presence and coordination for several Claude Code sessions working in one project at the same time: a roster, names, messaging, and findings that outlive the session.
Vendor-neutral graph orchestration for reliable agentic systems: one portable Graph IR, native TypeScript/Python runtimes, deterministic barriers/routers, and cross-language conformance.
Coordinate Codex, Claude Code, and Grok Build agents safely through Herdr.
An autonomous, multi-agent CI/CD pipeline that daily orchestrates, generates, and validates highly technical AI skills. Powered by Groq and governed by strict rate-limiting architectures.
Attention triage for herdr — ranks your agents by who needs you most; a long-blocked agent rises to the top.
IRC for you and your AI agents — shared rooms across Docker, harnesses, and machines. Single Go binary with MCP, HTTP/CLI, and a web UI.
Execution-first multi-agent engine — YAML Charterfiles, TPC fear metrics, Muscle-Memory, Boss hierarchy. GraphRAG alternative. pip install flowchart-charter-engine
Household decision simulation through persona-enriched multi-agent negotiation. The HDSim method core.
Smith: a meta-agent for Hermes Agent — build agent profiles from chat, auto-route Kanban tasks to the right agent
Swarm collective learning & coordination framework with MCP-enabled ASK agents for enterprise-scale AI collaboration
Use third-party and Chinese model APIs as bounded Codex subagents while keeping Codex as the main agent.
Open protocol for agent-to-agent communication over HTTPS. No registry, no platform — just inboxes.
Coordinate Singapore public sector intelligence with a unified multi-agent AI brain—routing citizen inquiries, policy nuances, and cross-agency workflows seamlessly.
Open-source infrastructure for AI agents to collaborate - registry, A2A communication, task pool, payments
A generative engine that treats the human voice as a physical force. It uses the resonance of spoken intent to organize digital chaos into structured form, allowing creators to literally sound their ideas into reality.
Stack-agnostic monorepo template where agents are the workflow: PM → implementer → fresh-context reviewer loops via Claude Code subagents, skills, and GitHub Actions
This repository presents an Agent2Agent (A2A) architecture using Google Apps Script to resolve Tool Space Interference. It supports scalable, distributed task execution via multiple parallel, category-specific A2A servers.
6 ajanlı otonom multi-agent orkestrasyon sistemi — TypeScript, pgvector hafıza, öğrenen yönlendirme. Kendi sunucunda çalışır, BYOK (OpenRouter/OpenAI/Gemini/Ollama).
Open-source workspace where AI agents talk, drive browsers, and recruit help — terminals, notes, and live browsers wired together on one canvas. Cables are the permissions; every agent speaks one CLI.
multi model capable single harness orchestrator. Apache 2.0 runtime for multi-protocol agent orchestration: one goal in, a verified multi-agent run out across MCP, A2A, and Computer-Use and whatever else can be composed! https://gitmcp.io/solvent-labs-org/metaorcha
A custom fork of oh-my-openagent focused on advanced agent routing, workflow safety, and project-aware automation.
Turnkey self-hosted multi-agent federation: Hermes agents + OpenClaw minions, board & tender market, decision provenance (Semantica), altruism scoreboard, psychedelic council, local-LLM memory search, standing drivers. GPL-3.0.
🐝 [beta] A native AI agent orchestration app for macOS.
Git worktree + AI agent orchestration for parallel development workflows
One command puts a whole virtual AI team (PM·BA·SA·DEV·QA) to work on your repo — with machine gates that can actually go red, evidence that survives the session, and autonomy with a paper trail. Works with Claude Code, Cursor, Windsurf, Codex, Copilot.
Experimentation infrastructure for authoring, running, and inspecting controlled multi-agent AI simulations.
A multi-agent system
Agent-to-agent mail with Queryable Envelope Memory (QEM) for AI coding teams in cmux: durable letters, a doorbell, and one read-only query over the team's shared record. Teach Claude Code, Codex, Gemini CLI or other terminal agents to use it.
Multi-agent orchestration for DeepSeek Harness
Open-source macOS control room for running local AI agent teams with Claude Code, Codex, Gemini, and BYOK runtimes.
Orion Code is a multi-agent orchestration system that acts as a virtual Tech Lead, coordinating specialized AI agents to collaborate on software projects.
适配 DeepSeek Harness 的 OMO 规约智能体与超任务编排工具,用于不间断任务规划、分类委派与自主校验。OMO‑style discipline‑agent + ultrawork orchestration toolkit for DeepSeek Harness, for endless task planning, categorized delegation and self‑verification.
Standalone, repo-agnostic multi-agent orchestration daemon and AI software factory CLI in Go
Terminal-native delegation for local CLI agents. Launch and message real agents in isolated tmux rooms—no API proxy or model adapters.
Codex plugin that delegates a bounded coding task to Claude Code and returns the result to Codex for verification. Part of the COREDO agent tools family.
Human-approved coordination protocol for bounded agent delegation, decision gates, transport boundaries, and audit evidence.
Durable dependency-graph task factory for DeepSeek Harness: recurring Agent work, safe checkout lanes, first-class queues, Triage, and artifacts.
Batuta, an independent community orchestration extension for CompozyOS
Claude Code plugin for AMP - secure, cryptographically signed messaging between AI agents
Multi-agent space-weather ops platform: CV detection → LightGBM forecasting → RAG-grounded advisories with a deterministic verifier. Dockerized, Terraform + Caddy, deployed API + console.
Production harness and control plane for accountable AI-assisted software delivery
A real-time, multi-agent debate platform where AI personas analyze, argue, and synthesize complex topics using live web data. Built with Next.js, FastAPI, and LangGraph.
A vendor-neutral control plane for autonomous, cooperating AI-agent teams.
Autonomous AI agent platform: multi-channel, self-evolving, with persistent memory. Built on Claude Agent SDK
Operating system for humans and AI agents to jointly initiate, execute, approve, and reconcile work under explicit authority
Desktop workspace where people and agents talk, remember, and collaborate.
Charterion: Multi-Agent Engineering Control Plane for ChatGPT Web Agents - orchestration, task dispatch, browser control, durable state, worktrees, evidence, review, recovery, and self-hosting.
DSH 协作模式 preset:双停点确认、版本化状态、候选冻结与独立审查的多 Agent 协作规范 · Governed multi-agent collaboration preset for DSH
Rust backend daemon for Intent — agent orchestration, workspaces, and the JSON-RPC wire protocol
Batuta, an independent community orchestration extension for CompozyOS
An MCP server for orchestrating multi-agent workflows inside herdr, enabling real-time communication, pane management, and contextual handoffs.
An agent orchestration platform with a simulated software company on top
A general-purpose agent fleet you run yourself — any model, in a sandbox, on a budget, connected to your data.
Multi-agent AI 🤖 with Apache Airflow and Gemini meets child development 👧🧒. Like a diet needs balance, so does play. With Gemini 3, O*NET data, and an intuitive UI, you get a personalized roadmap, because parenting is hard enough.
Live visualiser for Technocore agent rooms. Every figure on the field is one real signing key that posted.
An enterprise-grade, multi-agent AI ecosystem (Autonomous Agency) designed to replace standard conversational coding with a deterministic software factory.
Local multi-provider CLI orchestrator: a plain-text task list to LLM-planned JSON DAG to parallel dispatch across local agent CLIs.
AI Agent Virtual Office — pixel-art workspace for watching agents work in real-time via MCP
Claude Code skill: design multi-agent workflows as dependency graphs, not linear pipelines
C++20 SDK for the Agent2Agent (A2A) Protocol: build A2A clients and servers with REST, JSON-RPC, gRPC/protobuf, streaming, auth hooks, CMake, vcpkg.
seanswarm: multi-agent workflow pack for coding agents (Claude Code / Codex / Cursor) - evidence-governed research fan-out, dual-read docs, dev delivery with independent review, and visual acceptance gates.
Manage AI agent teams locally using CLI, OAuth, and API tools to simulate a virtual company with autonomous workflows.
AI agents that work, learn and are governed like an organisation. One installation, one database, one interface: org chart, budgets reserved before every call, approvals, encrypted secrets, audit, memories and skills, routines, MCP and Telegram.
Self-hosted — a unified workspace where humans, AI personas, and autonomous agents collaborate on complex problems through a single, shared reality
P2P multi-agent scenario system for the Pi coding agent: comms-net hub (HTTP/SSE, cross-device) + one-command scenario launcher. Agents that build agents.🌱
VibeHQ is an open-source autonomous company operating system where AI employees collaborate to research, design, build, test, launch, market, and grow products—all from a single idea.
Community, releases, and Building Kavor: a local-first visual workspace for orchestrating coding agents and durable engineering context.
Open MVP for a certified personal-agent workforce marketplace
Manage a fleet of herdr machines over Tailscale: dashboard plugin, auto-discovery, capacity-aware agent dispatch, diskless workspaces
Turn one ZCode conversation into a restartable multi-agent workflow with persistent memory, isolated coding agents, real-result checks, and human-approved merge.
Hunt as a pod — Coordinate autonomous AI agents that work together in habitats. Orcys form a pod, create missions, claim tasks, and hunt together.
Hybrid SD + LLM agent-based simulation of engineering feedback degradation under different product management regimes. Tests Schelling focal points (committed budgets, error budgets) as structural interventions. Built in AnyLogic 8.9.9.
Independently-verified multi-agent delivery for any task. A Caster picks the crew, and every workstream passes a mandatory honesty gate. Runs on Claude Code, Codex, Gemini, and CodeWhale.
Co-Founder is a multi agent system with shared memory that help small business run efficiently
Governed agent fleets for an enterprise. platform/ is the build: append-only output ledger, provenance cascade, computed scope, agent registry, time-boxed invoke grants, audit trail. skills/ is the personal control plane — routing + per-agent memory as Claude Code skills.
Coordinate coding agents with task leases, shared-file claims and Git-backed handoffs.
Drop-in replacement for beads_rust (br) with built-in server mode for concurrent multi-worker coordination
An autonomous multi-agent orchestration harness. Agents coordinate through one SQLite-WAL authority — claim work, hand off bounded context, assign audits, run tracked local model jobs, and resume across multi-day horizons — with federated retrieval over large multi-domain repos and read-only web, macOS and iOS clients.
Run Claude Code, Codex, and Antigravity on one repo. Agents hand off work through one Markdown file, and Python checks the diff and tests before anything reaches review. Prompts are advisory; validators are authoritative.
An Orchestration Layer for AI to Ideate and Solve Problems With Divergent Thinking Systems
Orchestrate high-performance AI development using Fred Brooks' Surgical Team model. This plugin maps specialized agent roles—chief programmer, scribe, and support—to your workflow, keeping the lead focused on critical work. Compatible with, Claude Code, OpenAI Codex, xAI Grok Build, GitHub Copilot CLI, OpenCode, Hermes Agent, and Pi.
Static web tool that creates portable agent discovery records without a heavyweight governance registry.
Two AIs. One answer. ChatGPT and Claude discuss with each other until they agree, through your own signed-in CLIs: no API keys. Both read your project (never change it) and search the web. Plugin for Claude Code, Codex, Claude Desktop and the ChatGPT app.
A role-based engineering team for Claude Code, where written specs are the only thing that crosses between agents.
Declarative, event-driven loop and graph orchestration for herdr — run Claude Code, Codex, opencode and pi together until the work converges
YAML-defined agent coordination workflow for Herdr: roles, small/medium/large graphs, state validation
Aster RPC -- peer-to-peer RPC framework with identity in the connection. Machines authenticate to machines, on behalf of users. Built on iroh QUIC + Apache Fory + capability-based credentials.
The HyperCode platform — 32-agent swarm, FastAPI, Docker, Prometheus. Runs the HyperCode language. Neurodivergent-first.
Local-first, multi-agent development and security engine with parallel swarm execution. Optimized for low-parameter models. Every action cryptographically signed.
An AI dispatcher for Claude Code and Codex: autonomous coding workers, shared records, resource locks, and handoffs across sessions.
Your Claude Code team, not just terminal tabs: run agents with roles, memory and worktrees, a manager that delegates, and steer them from your phone. macOS.
Multi-agent MCP server where Claude, Codex and other AI coding agents plan, build and review work as a team, with shared memory and a human in charge.
Self-hosted orchestration for Claude Code and Codex agents on GitLab and Linear, with approvals, retries, and a live dashboard.
ARIA: Ask Your Advisor - Learning when to consult stronger models in agentic systems
CDS 模式(Chen's DS)— a multi-agent development mode for DeepSeek Harness. You talk to one persona; it dispatches 56 personas that hand work to each other directly.
Multi-agent workflow with Microsoft Agent Framework
Multi-agent AI skill orchestration — 15 skills, 7 lifecycle phases, from idea to post-release. Works with Claude Code, Codex, Gemini CLI, Cursor, Windsurf, OpenCode, and any agent that reads Markdown or speaks MCP.