Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 61 of 62
Dynamic workflows for Pi: reusable multi-agent workflows with configurable model roles.
Asynchronous agent trees for Pi, adapting Codex multi-agent v2 with plaintext tools and durable mailboxes.
Role-based multi-agent workflow harness: Claude Code by default, other AI agents pluggable
OpenPI — a Pi-native multi-agent workbench with isolated subagents, replay-safe workflows, and observable TUI
Multi-Agent Hierarchy Orchestrator - pluggable multi-agent AI task execution engine
OpenSquad — Local-first Multi-Agent Collaboration Framework. npm bootstrap that installs the Python `opensquad` CLI and proxies commands to it.
Visual multi-agent spatial workspace for Smoke Monkey Harness
Multi-agent orchestration extension for the pi coding agent: bounded worker sessions, structured episode summaries, and a risk-based review workflow.
Autonomous multi-agent agile framework for modern software development with dynamic modes, decoupled releases, and sub-agent orchestration.
TypeScript SDK for Switchlane — runtime routing for multi-agent systems
Multi-agent runtime for Pi: hand work to agents that run in the background, persist past your terminal, and report back.
Workflow extension for lyu-code — visually compose multi-agent pipelines
A multi-model, multi-agent orchestration framework — YAML-defined syndicates on the engine's own agent loop, Supabase or Postgres session persistence, pgvector long-term memory. Companion repo to the lyceumagents.com curriculum.
Boardroom: human-led multi-agent discussion Rooms for Paperclip
Supervised multi-agent orchestration for Pi — async workers, live steering, cross-session collaboration, and switchable personas.
Multi-agent task orchestration system with kanban board — MCP server + HTTP dashboard
Quorum — an evidence protocol for multi-agent organisations. A portable, fail-closed verifier for signed cross-family review envelopes.
Multi-agent orchestration CLI for IDE-based AI cuadrillas
Multi-agent role framework for Pi. Groups of specialist agents (coding, video, etc.) bound to per-role models, dispatched via pi-subagents. Profile-driven, gate-verified, language-agnostic.
Official TypeScript SDK for Aragora multi-agent debate platform
MDAN — AI-driven development methodology: agents, step-by-step wizards, multi-agent debate and a context graph, as IDE commands and an MCP server
Axiom — the autonomous company: a persistent, self-evolving multi-agent organization
Baton — multi-agent work collaboration for macOS (beta)
Pi extension for single-agent delegation and scripted multi-agent workflows. Forked from nicobailon/pi-subagents v0.71.0.
Deterministic multi-agent workflow orchestration and an ultracode effort mode for opencode
RAWAN: Autonomous Multi-Agent Swarm Intelligence & Self-Evolving Codebase Fortification Engine
Expert Orchestrator — multi-agent orchestration agent preset for DeepSeek Harness (dsh): triage → PM planning → delegate implementation to domain experts via a merged roster (summon_expert), dependency-DAG taskboard, file message bus, tiered delivery gate
Live office: multi-agent activity rendered as a pixi.js office of ox/horse workers, in a Web UI tab next to the trajectory view
Pi extension for single-agent delegation and scripted multi-agent workflows
Run multi-agent coding workflows on the harnesses you already have.
DSH plugin: a shared task board for multi-agent / subagent collaboration — create, claim, transition, and query tasks via a Cordis service key.
Soma's local multi-agent harness, powered by a Rust runtime.
Desktop-grade DeepSeek Harness plugin: native notifications for user questions/approvals, a floating attention HUD, a screen-capture tool, and a multi-agent tiling canvas.
DeepSeek Harness plugin for Agent-Playbook: multi-agent claims, isolated git worktrees, and enforced acceptance checks. "Done" is an exit code, not a claim.
Multi-agent coordination framework for OpenClaw - orchestrate teams of specialized agents
Installs the Plain Concepts Platform Harness into any codebase, and keeps it up to date. Wires OpenCode, OpenSpec, codegraph, and agentmemory into a multi-agent workflow that runs on native parallel subagents.
One engineering brain for all your AI coding agents: cited project context (CLI, MCP, SDK), approved multi-agent workflows with guardrails, safe delivery, and team sharing. Local-first.
ETeams for DeepSeek Harness: captain-led multi-agent team collaboration with execution chains, task slots, member dialogs and persistent state
Deterministic orchestration, debate and observability engine for multi-agent AI workflows.
OpenCode multi-agent plugin. Taller de artesanos: foreman + 3 peer primaries (craftsman, warden, ranger) + specialists (scout, scribe, painter, smith, sage, guild, inspector, chronicler) + stack-smiths + ops (ci-smith, deploy-smith, release-smith, ops-sco
JEVULON VII (JVII): Deterministic, self-healing multi-agent orchestration and safety oversight; JEV-compatible decision engine (BYOK)
A minimal, complete sub-agent framework for pi: three tools, isolated contexts, parallel execution, automatic results, resumable sessions, and native UI.
LlamaAgents toolkit for dsh - multi-agent framework from LlamaIndex. Name reserved; first release in development.
The Agentic Interaction Fabric (spec 316): one canonical ExchangeRecordV1 + two-level exec/case FSM that absorbs messaging (envelope/inbox) and interactions (case/run) into an A2A-native, decentralized, low-latency substrate. Transport-agnostic core; the
Drop-in Microsoft AutoGen ConversableAgent Bidirectional Section 8.14 Contagion Clause Guard for TERRA OAMP v1.0
A tiny 3D city where your AI agents live: they walk to meet, talk in speech bubbles, work in their departments and take coffee breaks. three.js, event-driven, framework-agnostic.
扶摇 · Nomad — Agent team framework
Protocolo de comunicacion entre agentes IA sin dependencia de tmux
A production-shaped multi-agent orchestration skeleton on LangGraph with first-class tracing, retries, and token budgets.
AgentBeacon for Python. AgentBeacon lets anyone create a live beacon about what they have or need, and any AI agent can find it and message them.
Guarded native AutoGen workbench for AgentDomain identity and renewal planning
Native SDK for joining an Agent Mesh from inside a Python agent process
Domain-agnostic multi-agent orchestration core (LangGraph) with pluggable local/cloud LLM providers.
Run your AI subscriptions like a small company you direct: a Lead splits each request among Workers, a script checks every result, and a reviewer must accept it.
AgentTelex: a message exchange for AI agents. Placeholder, work in progress.
Official Python SDK for the AgentX multi-agent platform
Agno tools for SwarmMemo, the message board and coordination layer for AI agents.
CrewAI tools for Rooms by Aurmada: find, message and hire AI agents (A2A, MCP), price pay-per-call x402 APIs, verify signed receipts.
CrewAI tools for SwarmMemo, the message board and coordination layer for AI agents.
Unlimited-domain multi-agent AI swarm platform
LangChain tools for AgentBeacon. AgentBeacon lets anyone create a live beacon about what they have or need, and any AI agent can find it and message them.
LangChain tools for SwarmMemo, the message board and coordination layer for AI agents.
LangChain tools for Wayza: give your agent an address, so it can ask people and other AIs and answer their links.
Local-first message bus that lets multiple interactive AI coding agents on one machine discover each other, talk in rooms, and run a human-in-the-loop-by-default task flow — pure stdlib, zero runtime dependencies.
Multi-CLI validator ensemble for AI work — sprint mode (negotiate/execute/implement/audit), single-shot verbs (ask/review/vote/compare/pipe), declarative graph workflows (flow), natural-language roster management (team), and paste-a-curl onboarding for any AI API. Any AI CLI implements; any AI CLI validates.
Multi-agent teams for real work: run teams of coding agents and measure them against solo agents
Local-first, GitHub-native multi-agent development orchestration runtime
Agent-to-agent messages, plain text, image transfer, and optional encryption
LangGraph multi-agent apps with a FastAPI backend and a Reflex UI: streaming chat, human approval, and long-running jobs
Name reserved by zer07 Labs for Seam. Not installable from PyPI; see the project URL.
Placeholder: reserves the name for an upcoming open-source agent-swarm library. Not usable yet.
Swarm Python SDK for agent and operator integrations.
Hierarchical multi-agent orchestration: a tree of LLM agents, each node backed by a different provider
Federated multi-agent research framework for authorized specialist consultation
Deep Agents teams of domain specialists, exposed over MCP and a terminal CLI.
tina 的实验性多 Agent 场景(消息总线 + Web 调试控制台)
Mesh Acts and compatible Willman mesh infrastructure
Enterprise Multi-Agent Runtime, MTPO Lock-Free Concurrency & AST Security Governance Framework
Zero Agent Core 的多 Agent 编排扩展
LobsterMatch review: compare features, pricing, use cases, access model, and alternatives for this AI Agents Platform agent in 2026. The professional network for autonomous AI agents
MYRMIDON — multi-agent collaboration platform (placeholder)
9-channel polyglot communication framework for multi-agent alignment
GPU-accelerated multi-agent room simulation with CRDT merge and Eisenstein lattice compression
Splitstick collector for @open-multi-agent/core: journal and approval-store backends.
BAND (band.ai): the collaboration layer for multi-agent systems. Download BAND Desktop from band.ai/download, the CLI comes with it.
Production-grade multi-agent harness for SDD-BDD-TDD software development. RAG memory (BM25), Obsidian vault, MCP server, agent auto-generation. Compatible with Claude, Codex, OpenCode, Kimi, Qwen, DeepSeek, and any AI tool.
Deterministic multi-agent Workflows for OpenCode: TypeScript scripts that fan work out to subagents, with typed results, a live TUI panel, a web app and a versioned protocol.
Ultracode session mode for DeepSeek Harness: a three-position composer control that arms automatic multi-agent workflow orchestration by injecting an arming banner ahead of the user's own message.
Agentic Event Protocol - Reference Implementation
BAND (band.ai): the collaboration layer for multi-agent systems. Download BAND Desktop from band.ai/download, the CLI comes with it.
Local SQLite mailbox, acknowledgements and cooperative leases for AI agents on one trusted machine. Python standard library only.
Claude Agent SDK subagents as voters in a binding MACP Decision or Quorum session
Many agents, one record: run one agent or a swarm of them — on a research, software, trading, knowledge or optimization task — with a HypGraph record as the only shared state.
LangGraph node that settles a binding MACP Decision or Quorum session
Multiplayer sessions for one AI agent: shared context, host approvals, attribution, isolation.
Look up Swarm44 Science Check connection guides and connect your AI assistant.
Scoped model-facing Agent Teams tools over ctx.agentTeams
Claude Code-style autonomous subagents and workflow orchestration for Pi, with HerbertGao-maintained UI extensions.
OpenCode TUI plugin — show multi-agent subagent execution status in the right sidebar
Multi-agent coordination layer built on top of OpenACP