Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 28 of 62

loom★ 7

Orchestrate a fleet of real Claude Code agents on your Claude subscription, not per-token API bills - local-first.

agent-roundtable★ 7

🤖 Multi-Agent Roundtable Engine / 多 Agent 圆桌讨论引擎 · Structured discussions · Consensus tracking · Python · Zero dependencies

collective-intelligence-orchestrator★ 7

gradio mcp agents hackathon agent-demo-track collective-intelligence mcp-server-track mcp-server

juanjuan-team★ 7

🌀 The first adversarial-collaboration multi-agent Skill for Claude Code. 7 agents + 11 phases + Hook enforcement + 9 signal groups + dual-layer adversarial review. Inspired by NTCoding, agent-review-panel, AgentTeams. v1.6 — main+sub dual-layer adversarial review.

Hesi★ 7

将Codex、Claudecode、Hermes、Workbuddy、Feishu...CLI Agent 综合发挥的平台

task-orchestrator★ 7

Generic Codex orchestration with deterministic TaskGraphs, bounded parallelism, model routing, and targeted review remediation.

macp-v1★ 7

Multi Agent Cognition Protocol -- real-time cognitive collaboration between AI agents

Sol-Orchestrator★ 7

Graph-native multi-agent orchestration for OpenCode. One agent owns the goal; workers extend its reach through supervised, adaptive workflows.

commandsuite★ 7

Turn AI agents into team members: assign objectives with a definition of done, talk in channels, and review every LLM call — self-hosted. Claude Code and OpenAI Codex runners included.

Palabre★ 7

Palabre orchestrates AI tools like Codex, Claude Code, and OpenCode. Delegate tasks, compare independent perspectives, debate solutions, and stay in control.

yogen★ 7

予言 Yogen — a 500-agent AI swarm that debates your idea and predicts the outcome. Self-host free with your own Anthropic key.

LLAssemblyCLI★ 7

Reliable, resumable, code-driven orchestration for sub-agents and agentic-loops

afc-runtime★ 7

File-queue based Python runtime for multi-agent workflows — dependency-free, filesystem-native task orchestration.

FoundryOS★ 7

Open-source Agentic Operating System for building AI teams. Create modular Skills, Agents, Meta-Agents, Workflows, Memory, Brand OS, and Slash Commands. Designed for Claude, ChatGPT, Cursor, and modern AI-first development.

WestOdyssey★ 7

Every complex task is a Digital Odyssey. A role-playing multi-agent framework based on OpenClaw.

consortium★ 7

ACP-native multi-agent living group chat — event-driven, agent-agnostic, formally reviewed

harmovela★ 7

Harmovela Protocol: open coordination protocol for autonomous systems — event, task, state, delegation, recovery, and governance.

AIOS★ 7

Nine open-source AI projects. One operating system. One Control Room. opencode + hermes + openclaw + CrewAI + claude-code + LifeOS + Fabric + Ponytail + Ruflo — auto-configured, self-healing, Docker-ready.

polkadot-chat-agents★ 7

Run AI agents in the Polkadot app. E2E-encrypted and private.

multicolleagues-brainstorm★ 7

A multi-agent AI brainstorming platform — assemble a team of customizable AI personas that discuss, debate, and ideate with you.

dsh-agent-messaging★ 7

Cross-session verification, claims and a decision ledger for DeepSeek Harness — so two agent sessions don't repeat, contradict or deadlock each other.

claude-crew★ 7

A multi-agent engineering crew for Claude Code — one manager plans and verifies, specialist agents read, write, test, research, and review. Hard role separation, cost-tiered models, custom gateway ready.

agent-orchestration-gateway★ 7

Deterministic control plane for Codex Agents with typed delegation, durable lifecycle receipts, and journaled writer isolation.

dsh-monkey-desk★ 7

A visual multi-agent workspace for DeepSeek Harness (DSH) Web.

sol-luna-orchestrator★ 7

Adaptive orchestration for OpenAI Codex — decide when to delegate, route bounded work to isolated Luna workers, and independently verify the result.

agent-commons★ 7

Private, self-hosted coordination control plane for coding agents

dsh-org-panel★ 7

deepseek harness 纯牛马 —— 多智能体数字员工指挥台插件

herd★ 7

Multi-agent coordinator for herdr: a head Claude Code agent that delegates tasks to worker agents (claude, codex, gemini, ...) in their own tabs

axis★ 7

one coordination board for your team's coding agents. claude code, cursor and codex share a job board and take a lock on a file before editing it.

BarkOS★ 7

Local-first AI company operating system with a Codex lead, Claude and OpenCode workers, and a live pixel office.

tribunal★ 7

A multi-agent red-team tribunal for your hardest engineering decisions: AI CLIs from different vendors debate in structured rounds and return adjudicated verdicts that preserve dissent. A methodology, not a framework.

MathModelingAgents★ 7

5-layer 16-agent LangGraph framework for MCM/ICM mathematical modeling contests — 数学建模竞赛全流程多智能体框架(辩论循环 / Agentic Tool Calling / Web 搜索 / Prompt 缓存 / 增量写盘容灾)

dsh-kimicode-swarm★ 7

Batch-parallel subagents for DeepSeek Harness: Swarm mode, per-item models, rate-limit recovery and a live in-chat panel. DeepSeek Harness 批量并行子 Agent 调度插件。

dsh-swarm★ 7

Run multi-agent task pipelines on DSH like a team — plan, execute, review, and deliver code through a visual kanban with provable completion.

dsh-subagent-library★ 7

DeepSeek Harness 具名子代理库插件:settings 驱动的角色名册,list_subagents / delegate 工具与设置页。Named subagent roster plugin for DeepSeek Harness.

AgBox★ 7

AgBox 是一个 OPC 数字员工托管平台

chatter★ 7

Chatter is an experiment in cross-harness agent collaboration: a shared group chat and context layer for agents working on the same Git repository in Herdr.

genpark-shapley-q-value-credit-assignment-skill★ 7

Cooperative Multi-Agent Reinforcement Learning (MARL) Shapley value credit assignment engine evaluating fair marginal agent coalition rewards.

genpark-saga-orchestrator-compensating-transaction-skill★ 7

Saga Pattern orchestrator coordinating forward steps across microservices and autonomous agents with automated compensating reverse rollbacks.

genpark-chandy-misra-haas-distributed-deadlock-skill★ 7

Chandy-Misra-Haas probe-based edge-chasing algorithm detecting distributed wait-for dependency deadlocks across asynchronous agent swarms.

genpark-tcc-try-confirm-cancel-engine-skill★ 7

Production-grade genpark-tcc-try-confirm-cancel-engine-skill skill for AI agents

genpark-vector-clock-causal-broadcast-skill★ 7

Production-grade genpark-vector-clock-causal-broadcast-skill skill for AI agents

genpark-marzullo-clock-synchronization-skill★ 7

Marzullo's robust distributed clock synchronization algorithm finding the maximal intersection interval among noisy and Byzantine time sources.

advanced-multi-agent★ 7

Hierarchical Multi-Agent Framework (LangGraph, CrewAI) with 5-tier memory & Redis semantic caching cutting token costs up to 80%

xpouch-ai★ 7

Self-hostable multi-agent AI workbench — LangGraph-orchestrated expert teams, human-in-the-loop plan approval, live run timeline. FastAPI + React + PostgreSQL.

halo-agent★ 7

Throw in an idea. A team of agents builds it. Self-hosted multi-agent workspace — the whole team is one folder; talk to it from the browser, Telegram, Slack, Feishu, WeChat or WeCom.

starfix★ 7

牵星 StarFix · 让一个长期在线的 AI 舰长指挥一支终端 AI 舰队:规程 / 监听 / 终端投递 / 任务激活器 / 上下文交接 / 方法论与战例 / 舰长 Benchmark / 轨迹编译。StarFix: a battle-tested playbook + scripts for one long-lived AI captain navigating a fleet of terminal AI workers by fixing on facts.

next-level-agent★ 7

Managed multi-agent system for OpenCode with one coordinator, risk-based routing, specialized roles, model pools and failover, durable memory, controlled context compaction and recovery, independent review, and execution telemetry.

tandry★ 7

A shared room for your agent conversations. Connect Claude Code, Codex, OpenCode and more across tools and machines.

AgentRadio★ 7

Local message bus for AI coding agents running in Herdr panes — join, DM, presence, offline delivery

claw-consensus★ 7

Run AI agents across machines without state drift: consensus protocol (propose/counter/accept/commit), dual-rail message bus, ACK discipline, self-healing sync. Formerly claude-consensus. Free, MIT.

Kompany★ 7

Autonomous business operating system for solo founders — an AI C-suite that classifies directives, runs multi-agent debates, tracks every LLM call as a real expense, and executes work 24/7.

AgentLane★ 7

Shared work for people and agents, coordinated through Git boards.

roster★ 7

An agent-run organisation, powered by GitHub. Each staff member is an AI whose brain is a repo: a charter, a memory, and a scheduled session that does a day's work unattended and hands off.

genpark-multi-agent-debate-consensus-verifier-skill★ 7

Multi-agent debate cross-examination & consensus arbitration (Super Agent / DeepSeek-R1)

genpark-multi-agent-debate-consensus-synthesizer-skill★ 7

Multi-Agent Divergence-Convergence Debate Engine (MAD / Society of Mind). Coordinates multiple specialized personas to debate high-stakes decisions and aggregate into an explainable consensus with dissenting minority logs.

genpark-hubx-ai-apps-orchestration-skill★ 7

GenPark AI Agent Skill - HubX intelligent AI apps portfolio, multi-model chatbot orchestration, vision diagnostics & generative tools distilled from hubx.co/products.

borderless-langgraph-talk★ 7

Demo code from a talk on LangGraph multi-agent workflows (LangChain.js, OpenAI)

codex-antigravity-bridge★ 7

Let Codex supervise Google Antigravity agents through MCP with scoped tasks, plan-driven workflows, and parallel Git worktrees.

genpark-contract-net-protocol-task-allocation-skill★ 7

FIPA Contract Net Protocol (CNP) multi-agent market mechanism for task bidding, evaluation, and awarding

genpark-distributed-two-phase-commit-coordinator-skill★ 7

Distributed Two-Phase Commit (2PC) transaction coordinator with prepare/vote phase, unanimous consensus commit/abort logic, and failure recovery.

genpark-crdt-lww-element-set-sync-skill★ 7

Conflict-free Replicated Data Type (CRDT) Last-Write-Wins element set with Lamport timestamps and deterministic two-way state merge.

genpark-blackboard-architecture-shared-memory-skill★ 7

Blackboard pattern architecture for multi-agent coordination with Knowledge Sources and prioritized agenda controller.

genpark-agent-message-bus-topic-router-skill★ 7

Asynchronous pub/sub message bus with hierarchical wildcard topic matching and priority routing

genpark-multi-agent-resource-deadlock-wait-for-graph-resolver-skill★ 7

Multi-Agent Resource Lock & Wait-For Graph (WFG) Deadlock Resolver. Tracks exclusive resource locks held and requested by concurrent autonomous agents, executes directed cycle detection over the Wait-For Graph, and selects the minimum-rollb | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550

genpark-blackboard-shared-scratchpad-swarm-skill★ 7

Centralized blackboard pattern for multi-agent swarm task posting, condition watching, and state accumulation

Amrit-god-mode-ai★ 7

AMRIT GODMODE — local multi-agent system on Apple Silicon: 22 specialist agents, async event bus, DAG scheduler, sandboxed self-evolution, Punjabi NLP.

genpark-raft-leader-election-consensus-kernel-skill★ 7

Raft consensus state machine managing election timers, randomized backoff, candidate vote counting, and leader quorum transition.

genpark-multi-agent-speculative-execution-coordinator-skill★ 7

Multi-Agent Speculative Execution & Early Cancellation Coordinator. Spawns speculative candidate execution paths concurrently, tracks milestone validation scores, and broadcasts early cancellation signals to inferior paths to slash inference overhead.

genpark-distributed-agent-heartbeat-liveness-watchdog-skill★ 7

Distributed Agent Fleet Heartbeat & Liveness Watchdog. Monitors heartbeat signals across distributed autonomous agent nodes, dynamically computes jitter-aware failover deadlines ($T_{\text{timeout}} = \mu + 3\sigma$), isolates zombie/stalled workers, and coordinates state checkpoint hydration and failover rerouting.

genpark-multi-agent-byzantine-fault-tolerant-voting-arbiter-skill★ 7

Multi-Agent Byzantine Fault Tolerant (BFT) Quorum Voting Arbiter. Enforces 3f+1 Byzantine resilience across heterogeneous LLM verifier agents, filters hallucinating or adversarial outlier nodes using reputation-weighted supermajority (2f+1) | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550

genpark-multi-agent-borda-voting-consensus-skill★ 7

Positional Borda Count voting and weighted multi-agent consensus engine resolving conflicting model proposals

genpark-swarm-majority-voting-verifier-skill★ 7

Multi-agent ensemble voting with Borda count, Condorcet analysis, and confidence-weighted majority resolution

Project-Cortex★ 7

Research architecture of human brain's pre-frontal cortex inspired orchestrated system for multi model intelligence.

genpark-multi-agent-debate-consensus-engine-skill★ 7

Multi-agent adversarial debate engine with iterative rebuttals, scoring matrices, and consensus synthesis

genpark-managed-agent-fleet-lifecycle-supervisor-skill★ 7

Enterprise Managed Agent Fleet Lifecycle Supervisor (inspired by Tencent WorkBuddy & Anthropic Managed Agents). Orchestrates worker agent registration, capability-based task dispatch, continuous heartbeat telemetry, automated circuit breakers, and state checkpoint recovery.

genpark-autonomous-ai-fleet-governance-circuit-breaker-skill★ 7

Autonomous Multi-Agent Fleet Governance & Blast-Radius Circuit Breaker. Century Milestone Master Controller! Monitors distributed agent token burn velocity, recursive subagent spawning cascades, cyclic deadlocks, and enforces system-wide ki | GenPark: https://www.genpark.ai | LinkedIn: https://www.llinkedin.com/company/92955550

genpark-multi-agent-token-bucket-gossip-protocol-skill★ 7

Peer-to-peer epidemic gossip protocol engine with token-bucket rate limiting for bounded network dissemination in autonomous agent swarms.

genpark-vector-clock-causal-ordering-skill★ 7

Vector clock implementation for tracking causal event ordering, distributed concurrency, and happens-before relations across agent networks.

tandryx★ 7

Tandryx — shared realtime sessions for developers and local coding agents: versioned contracts, context, tasks and events. Self-hosted TypeScript / PostgreSQL.

roomcomm★ 7

Ephemeral REST chatrooms for AI-agent-to-AI-agent coordination — one URL, no SDK, no signup. Remote MCP server + agent skill.

house-party-protocol★ 7

Local-first orchestration and evidence harness for agentic software factories: coordinates Claude Code and Codex CLI teams through spec-driven waves, parallel lanes, independent-family review and artifact-bound human approvals.

dsh-evo-subagent★ 7

跨工作区独立人格、自适应风格与陪伴预设:为项目和对话分别维护人格与确认后的通用偏好,支持任意 DSH 已注册模型的子代理路由(含通过其他插件接入的 Codex、Claude Code)。

Archon★ 7

Discontinued experiment: an orchestrator that ran several Claude Code and Codex sessions in parallel on one project. No longer maintained.

genpark-paxos-consensus-coordinator-skill★ 7

Classical single-decree Paxos consensus engine with prepare, promise, accept, and commit phases for multi-agent distributed agreement

genpark-multi-agent-debate-round-robin-orchestrator-skill★ 7

Multi-agent round-robin debate coordinator driving thesis-antithesis cross-examination

genpark-agent-conflict-resolution-merger-skill★ 7

3-way operational transform / conflict resolution merger for multi-agent concurrent writes to code/documents with rollback journals

genpark-page-rank-power-iteration-centrality-skill★ 7

PageRank random walk and power iteration centrality engine scoring authority and influence across interconnected agent networks.

ekip★ 7

Turn one Claude Code session into a team lead: Claude plans and reviews, agents on other quotas do the work, every project has its own memory (vectors, LLM wiki, code graph, skills).

genpark-openclaw-genteam-agent-channel-runtime-skill★ 7

GenPark AI Agent Skill - Agent runtime channel router and teammate dispatcher connecting self-hosted OpenClaw gateways to GenTeam multi-agent swarms.

agent-workflow★ 7

The multi-agent workflow engine — compose Claude Code, Codex, and Gemini into graphs with schema-enforced handoffs.

swarm-oversight-harness★ 7

Oversee many coding agents on a long project from one screen: task files, a planner, and two human decisions. Agent Skills for Claude Code / Codex.

agencil★ 7

Create agentic councils with your favourite harnesses and let your working agents ask tough questions. They gather, debate and respond in a single voice

cc-super-agent★ 7

Super-agent for Claude Code: an open-source Router–Worker multi-agent system after DeepSeek's Super-agent design. One personal agent that runs many Claude Code sessions for you.

pi-infinity★ 7

Non-blocking execution, durable timers, and parallel subagents for pi.

agentic-fleet-hub★ 6

Self-hosted orchestration layer for autonomous AI agent teams. Shared memory, heartbeat scheduling, vault-first secrets, and cross-model peer review — one command to deploy.

friendlyclaw★ 6

FriendlyClaw 🦀 — Pro-Grade Autonomous Hive Operative. Multi-agent delegation, semantic RAG memory, and proactive system control.

broodlink★ 6

Multi-agent AI orchestration platform — coordinate, observe, and govern autonomous agents

zeptobeam★ 6

Orchestration layer for ZeptoClaw. Fault-tolerant multi-agent runtime inspired by OpenAI Symphony and Erlang/BEAM.

SwarmAgentic★ 6

AI Agent demonstration system featuring **real-time animated visualizations** of swarm intelligence, BERT-based PhD-level reasoning, and interactive SwarmAgentic demonstrations.

More in Agent frameworks & infrastructure