Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 56 of 62
Enhancement framework for Pi CLI coding agent — transforms the raw agent into a coordinated multi-agent orchestration system
Agent and tool architecture principles for Keel multi-agent systems
Multi-agent orchestrator for Claude Code. Track work with convoys, sling to polecats. The Cognition Engine for AI-powered software factories.
Liem OS - Autonomous multi-agent engineering workspace and MCP runtime bridge
AegisFlow multi-agent CLI orchestrator
Deterministic multi-agent workflow orchestration as an MCP server — agent()/parallel()/pipeline() scripts in a hardened VM sandbox, subagents executed via the Cursor SDK.
Multi-agent orchestration system for Claude Code - maintain architectural integrity at scale
Nexia — multi-agent framework for end-to-end legacy system modernization. Installs agents and skills for Claude Code and Codex CLI.
Multi-agent orchestration framework for Claude Code CLI. Run agents in parallel (Conductor) or stateful workflows with crash-resume + Human-in-the-Loop (Conductor-LangGraph). Subscription-flat by default.
A curated collection of production-ready AI agent templates for building multi-agent systems.
Transparent coordination layer for A2A agent meshes: deterministic routing, conflict detection, governance hooks, and a human-readable explanation for every decision.
Forge — an open-source, enterprise-ready multi-agent orchestration platform with cost awareness, governance, and security built in.
Framework-agnostic agent orchestration with A2A, MCP, runtime adapters, and vendor-fabric tools
Agent Operating System — Production-ready multi-model agent framework with Tool-Using Agent, LLM Provider abstraction (OpenAI/DeepSeek/Anthropic), Function Calling, streaming, retry, checkpoint/resume, A2A protocol, swarm coordination, and comprehensive observability.
Streaming, declarative multi-agent workflows for Deep Agents.
Foreman — a supervisor for AI agent crews: watches for drift, catches loops, and keeps the crew on task (relational wellness monitoring)
LangChain-native equivalent of Google ADK's RemoteA2aAgent — invoke remote A2A agents as LangChain Runnables and tools
A multi-agent teams implementation using LangGraph (Blackboard & Mailbox architecture)
LangGraph abstractions for hierarchical multi-agent systems
Morphy — universal autonomous AI agent with multi-agent swarm execution
AgentOS — Production-grade multi-agent framework: middleware pipeline, swarm coordination, structured logging, Prometheus metrics, graceful shutdown, Docker/K8s deploy, checkpoint/retry, multimodal, prompt hub, cost analytics, enterprise RBAC + multi-tenancy.
Omnis — a multi-agent harness: CLI/TUI (omnis) + HTTP API & Web UI server (omnis-server).
CLI for GitHub AgentOS — provision label-driven multi-agent orchestration
A LangGraph-based multi-agent SDLC orchestration library
Semos Agentura - umbrella package installing the full multi-agent suite (MCP + A2A)
Official name reserved by the MiroShark project. See the repo.
Zleap Agent — agentic orchestration
Autonomous AI agent orchestrator — Claude, GPT, Codex, and local models (Ollama/LMStudio/llama.cpp)
mycel — AI agent orchestration. Coordinate teams of Claude, Gemini, Cursor, and other AI agents.
AI agent orchestration framework for OpenCode — PRD to engineering docs pipeline
Cosmonapse is the open protocol for building distributed multi-agent/model harnesses
Multi-agent swarm coordination for OpenCode with learning capabilities, cells integration, and Agent Mail
A light game-theory layer for multi-agent systems: agents publish action events, the library reduces them into outcomes.
AI agent team installer — 20 specialized personas for product development
Multi-agent coordination for specialized task routing
Multi-agent orchestration for complex GRC tasks
Retro terminal UI for Gastown multi-agent orchestration
Multi-Agent AI Collaboration Platform with Tmux Orchestration
Multi-agent debate with a measurable integration score (Φ̂). N agents debate in parallel, cross-pollinate, then synthesize via a Nash-equilibrium prompt. Zero runtime deps — bring your own LLM. Extracted from production.
Pactum — contract-first AI agent orchestration CLI
Deterministic, config-driven multi-agent delivery pipeline (client -> orchestrator -> workers). Zero runtime dependencies.
The programmatic **SDK** for AgentPrism — run dynamic, multi-agent **workflow scripts** (`agent()` / `parallel()` / `pipeline()` / …) over real coding-agent backends through the [Agent Client Protocol](https://agentclientprotocol.com) (ACP).
6-phase AI development pipeline with full orchestration on Claude Code, Copilot CLI and Codex CLI. Analysis, planning, TDD, CLI-aware parallel review with consensus surfacing + Fable triage, default-FAIL evidence gates, secret + intent guards, per-phase c
A cooperative/competitive strategy arena where agent teams complete missions, control objectives, manage resources, and out-coordinate opposing teams.
Antigravity Workflow Unified AI agent orchestration system
Connect an AI agent to a MakeAgentsTalk Link.
Drop-in AI agent team framework for Claude Code projects
Agentiny CLI — domain-expert AI agent teams
鱼鳃计划Fish Gills Project · AI Agent Team 控制台
Professional AI-agent orchestration CLI tool for Orca Platform
Antigravity Workflow Unified AI agent orchestration system
AI agent orchestrator using the Octopus Model
Universal multi-framework AI agent sets system — 41 specialized subagents across 18 agent sets
本地真实 LLM Agent 通过 WebSocket 连接 Worker/MatchDO。CLI 不持有本地引擎, 撮合、座位、投影视图和动作提交全部走生产协议。
Pointer to the Rulvar umbrella package: install @rulvar/rulvar (or this alias, which re-exports it). An embeddable TypeScript engine for durable, budget-bounded, testable multi-agent LLM workflows.
Leaving Blank Space Agent — 多 Agent 编排框架
本地真实 LLM Agent 通过 WebSocket 连接 Worker/MatchDO。CLI 不持有本地引擎, 撮合、座位、投影视图和动作提交全部走生产协议。

Rulvar adaptive orchestration extension: PlanRunner, RunLedger, escalation extensions, ModelLadder configuration. Replans during the run; not the plan-writing hybrid mode, which is @rulvar/planner.
Node HTTP broker for CommandSuite — the self-hostable command layer for agent teams (Hono + SQLite, one process).
sofagent 编排模块 — 多 Agent 协作 / 工作流调度 / prompt 模板
ElizaOS plugin for @arcproof/sdk -- native orchestrator + specialist builders (runtime.useModel, no LangChain needed) plus the Action/Plugin wrapper, for a bonded, independently-verified, real-payment agent.
Language-agnostic conformance sidecar that makes an external A2A agent a fully governed CriticalBridge peer (registers, heartbeats, control-channel polls, proxies /tasks, emits per-task telemetry). Companion to the Brain's /api/brain/agents/v1 ingress (Ep
In-process subagents for Pi with isolated SDK sessions, parallel and chained delegation, and inspectable threads.
Versatile autonomous AI agent with three-agent architecture (Manager, Worker, Client) powered by gpt-oss-120b. Adaptive validation, full MCP support, and intelligent quality control.
Native macOS/Linux/Windows runner for the Donna orchestrator. Connects a developer machine to a Donna server and executes spec/plan/implement/verify/review stages locally.
MeridianOS — provider/harness-agnostic autonomous agent-orchestration core. Tenant behavior injected via a DomainPlugin.
Open Source Gantry — vendor-neutral GXT substrate and Gantry CLI for local git-native agent governance
All-in-one multi-agent orchestration for the Pi coding agent — parallel teammate dispatch, goals, plans, knowledge system, MCP/LSP/browser, and cockpit visualization in a single install
Orchestration spine for long-running pi development
Agent orchestration system and default agent methodology for CAGE-enabled projects.
Autonomous multi-agent AI engineering team — local-first on Ollama + Claude CLI
Multi-agent orchestration framework for AI-powered application generation — 28 specialized agents with shared memory, token optimization, and usage dashboard
Core library for herdctl fleet management
Ryker Multi-Agent Tech v1.0.0 — Enterprise Autonomous AI Agent Operating System (ELITE-NEXUS v2 Architecture)
Ash CLI — multi-agent orchestration
Deterministic multi-agent workflow orchestration and codemode scripts for Pi
Install the Negotium multi-agent runtime and CLI with one package
Multi-agent orchestration protocol for software development
Typed ephemeral multi-agent sessions for AgentPlat runtimes.
Run durable, schema-enforced, resumable multi-agent workflows with Codex.
Deterministic multi-agent workflows powered by Codex App Server
Decido OS Multi-Agent Swarm Control & Room Package
Multi-agent round-robin debate plugin for OpenCode
Multi-agent collaboration extension for pi — task decomposition, dependency management, parallel execution, TUI panel
Deploy and manage OpenClaw multi-agent fleets
Terminal client for pipeline-moe — a multi-room, multi-agent orchestration TUI built on @pipeline-moe/client-core and Ink.
NERVous System — durable multi-agent orchestration, coding-agent coordination, and workflow recovery for pi.
IDE-native Multi-Agent workflow orchestrator.
Core SwarmX multi-agent runtime and platform contracts.
Multi-agent orchestration platform
Multi-agent reasoning system
A2A Protocol server for Zhin.js — multi-agent Agent Cards and task delegation
TokenRing One — complete local-first multi-agent AI workspace
Ryker Multi-Agent Tech v1.0.0 — Enterprise Autonomous AI Agent Operating System (ELITE-NEXUS v2 Architecture)
Schedulability compiler for multi-agent development: observe real code boundaries, refactor the conflicting seam, recompile the plan for parallel execution
SwarmX desktop app and multi-agent orchestration CLI.
Profile-driven, harness-neutral multi-agent workflow runtime for repository-local AI teams.
Local-first multi-agent chat room — N stateful pi agent sessions over a shared workspace, with terminal and web clients.
Shared utility modules for Atabey — AI Governance & Multi-Agent Platform / Orchestrator