# AI Agent Tools With Multi-Agent Support

> Source: https://theagentsindex.com/collections/ai-agent-tools-with-multi-agent-support (curated, quality-gated, re-verified)

A framework wiring multiple agents into a graph, a voice agent transferring a call to a specialist mid-conversation, and a coding agent running a fleet of parallel copies of itself are all tagged `multi-agent` on this site, and none of them do the same job. Our own census, [What 'Multi-Agent' Actually Means](/blog/what-multi-agent-actually-means-2026/), read the sourced facts behind the tagged listings and sorted them into six shapes; this collection is that finding turned into a browsable set. Membership is re-derived from each listing's own text every time this page is re-read, never from the tag alone.

Five shapes have members this round. The sixth — *multi-vendor agent hosting*, where the product's pitch is running *other vendors' competing* coding agents side by side — currently has no Published listing whose own sourced text clears the bar, so the shape is recorded here with zero members rather than dropped from the methodology.

**Composable frameworks (9 of 14 [frameworks](/category/frameworks))** — you design and wire the multi-agent system yourself: LangChain, LangGraph, CrewAI, Microsoft AutoGen, Microsoft Agent Framework, Google ADK, Agno, Claude Agent SDK and LlamaIndex. LlamaIndex is the member a reader is least likely to expect, since it is known as a retrieval framework: it earns its place on AgentWorkflow, which hands control between a declared set of agents automatically, or exposes sub-agents to an orchestrator agent as tools. The frameworks in the index with no shape here are excluded on their own published text: Letta and Mastra name no agent-to-agent coordination primitive, and AgentsKit mentions the A2A spec only as a portability format that keeps agent definitions readable across tools.

**No-code team builders (1 of 16 [agent platforms](/category/agent-platforms))** — a non-technical operator assembles named, role-specific agents instead of writing code: Lindy.

**Vendor-built agent teams (2 of 9 [support agents](/category/support-agents), plus one [coding agent](/category/coding-agents))** — the vendor ships multiple named, specialized agents as the product itself, with no assembly required: Crescendo, Cresta and Factory.

**Parallel fan-out** — one job runs across many agent instances at once instead of one agent working straight through: Devin, Antigravity CLI, Muse Code, Augment Code and Goose among the [coding agents](/category/coding-agents), and Manus, GPT Researcher and GC AI among the [research agents](/category/research-agents).

**Voice handoff mid-call (3 of 12 [voice agents](/category/voice-agents))** — a call starts with a triage agent and transfers to a specialist with context intact, all within one phone call: LiveKit Agents, Cartesia and Deepgram Voice Agent API.

Genspark is the sharpest exclusion on this page. Its Super Agent orchestrates nine specialized LLMs and cross-checks their output against each other, which is multi-model rather than multi-agent: one agent consulting several models is not several agents dividing a job.

Several tools sit close to the line and are deliberately out, and for two of them the distinction is worth stating plainly: being callable by an agent, or building one, is not coordinating several. Dify publishes an MCP tool that other agents can call. Replit Agent can build other agents and automations. OpenCode runs several agent sessions in parallel on the same project but names no mechanism for them to coordinate or to divide one job between them. Junie and Gemini Code Assist name no second agent anywhere in their listings.

| Name | What it is | Why it's here | Pricing | API |
| --- | --- | --- | --- | --- |
| [LangChain](https://theagentsindex.com/langchain.md) | The most widely-used framework for building LLM apps and agents, with LangGraph for stateful multi-agent control: open-source and free to self-host. | Ships LangGraph, the graph-runtime multi-agent control layer documented as a separate entry on this page, and bundles the wider LangChain surface (LangSmith, content blocks) used to wire coordinated agents in production. | — | Yes |
| [LangGraph](https://theagentsindex.com/langgraph.md) | Open-source, MIT-licensed framework for building stateful, multi-agent AI workflows on cyclical graphs. | The stateful, graph-runtime multi-agent control layer where you design and wire multi-agent workflows as a cyclical graph — the explicit runtime piece of the LangChain surface for coordinated agents in production. | — | Yes |
| [CrewAI](https://theagentsindex.com/crewai.md) | Open-source Python framework for role-based multi-agent crews, with a hosted build and runtime that adds enterprise governance, native SDKs for the major LLMs, and Ollama via LiteLLM. | Role-based multi-agent crews where you assign named agents a role, goal and backstory and let them collaborate on a shared task — the canonical Python example of a multi-agent framework. | — | Yes |
| [Microsoft Agent Framework](https://theagentsindex.com/microsoft-agent-framework.md) | Microsoft's unified, MIT-licensed agent SDK for .NET and Python: the supported successor to AutoGen and Semantic Kernel. | Microsoft's unified, MIT-licensed agent SDK for .NET and Python: the supported successor to AutoGen and Semantic Kernel, with multi-agent orchestration patterns including group chat, sequential and concurrent. | — | Yes |
| [Microsoft AutoGen](https://theagentsindex.com/microsoft-autogen.md) | Microsoft's open-source framework for orchestrating conversations between multiple AI agents. Now in maintenance mode. | Microsoft's original multi-agent framework built around GroupChat and UserProxy patterns where agents converse to solve a task — in maintenance mode, succeeded by Microsoft Agent Framework. | — | — |
| [Google Agent Development Kit](https://theagentsindex.com/google-adk.md) | Google's open-source, code-first agent SDK with five language runtimes (Python, TypeScript, Go, Java, Kotlin), native A2A and MCP support, and an optional managed runtime on Google Cloud. | Google's open-source, code-first agent SDK with five language runtimes and native A2A support — multi-agent orchestration via agents-as-tools or sub-agents handed off between agent contexts. | — | Yes |
| [Agno](https://theagentsindex.com/agno.md) | An Apache 2.0 Python agent SDK and AgentOS runtime, with a Control Plane you run in your own cloud. | Apache 2.0 Python agent SDK and AgentOS runtime with built-in multi-agent teams, handoffs and a Control Plane for routing messages between agents — runnable locally or hosted on a paid tier. | — | Yes |
| [Claude Agent SDK](https://theagentsindex.com/claude-agent-sdk.md) | Anthropic's own agent-building library: the same agent loop, tools and context management that power Claude Code, for Python and TypeScript. Claude-only, with no multi-provider escape hatch. | Anthropic's own agent-building library for Python and TypeScript with explicit multi-agent sub-agent primitives: agents can spawn and delegate to other agents that own their own context. | — | Yes |
| [LlamaIndex](https://theagentsindex.com/llamaindex.md) | Open-source data framework for LLM apps, with LlamaParse as the paid agentic OCR for messy documents and LlamaAgents for document workflows. | AgentWorkflow hands control between a declared set of agents automatically, and sub-agents can be exposed to an orchestrator agent as tools — multi-agent by design, beyond the retrieval framing the name suggests. | — | Yes |
| [Lindy](https://theagentsindex.com/lindy.md) | A Slack-native AI teammate with a no-code app builder bundled in. | A no-code builder where you assemble named, role-specific AI agents in plain English — Lindy ships the abstraction of a multi-agent team to a non-technical operator who never touches code. | — | No |
| [Crescendo](https://theagentsindex.com/crescendo.md) | Fully-managed, AI-native CX platform that replaces your entire support stack with agents, QA and human staffing, billed per resolved outcome. | Vendor ships multiple named, specialized AI agents as the product itself — fully-managed customer-experience AI, no user orchestration required, billed per resolved outcome. | — | No |
| [Cresta](https://theagentsindex.com/cresta.md) | Unifies an autonomous AI Agent, real-time human Agent Assist and Conversation Intelligence on one contact-center platform, enterprise, custom-quoted, no self-serve tier. | Vendor ships an autonomous AI Agent, real-time human Agent Assist and Conversation Intelligence on one contact-center platform — multi-agent by default on a single product. | — | Yes |
| [Factory](https://theagentsindex.com/factory-ai.md) | Agent-native coding platform that coordinates specialized Droids across the full software development lifecycle, from a $20/mo Pro CLI to sales-gated enterprise deployment. | Agent-native coding platform coordinating specialized Droids across the full software development lifecycle — the vendor ships a coordinated team of agents rather than one general coding agent. | — | Yes |
| [Devin](https://theagentsindex.com/devin.md) | Devin is Cognition's autonomous coding agent: assign a task through Slack, CLI, or the web app, and it plans, edits, tests, and opens a pull request inside its own sandbox. | Coding agent that fans out across multiple sandboxes in parallel to tackle sub-tasks of a single job — true multi-agent execution rather than just multi-session in one process. | — | Yes |
| [Antigravity CLI](https://theagentsindex.com/antigravity-cli.md) | Google's terminal-native coding agent that replaced the open-source Gemini CLI in June 2026. Same Antigravity 2.0 agent core, now closed-source and tied to a Google AI subscription. | Google's terminal coding agent that runs parallel agent sessions across a task — Google's own example of multi-agent coding execution on a single user-supplied job. | — | Yes |
| [Muse Code](https://theagentsindex.com/muse-code.md) | Meta's terminal coding agent — pay standard rate and it never trains on your code, or opt into Contributor pricing for a steep discount if you let it. | Meta's terminal coding agent that fans out parallel agents on the same problem and cross-checks their output — multi-model plus multi-agent execution pattern on a single task. | — | Yes |
| [Augment Code](https://theagentsindex.com/augment-code.md) | AI agent platform that automates code review, ticket-to-PR delivery, security remediation, and incident response for dev teams. | AI agent platform that runs multiple specialized agents in parallel across code review, ticket-to-PR delivery, security remediation and incident response — many specialized agents, one product. | — | Yes |
| [Goose](https://theagentsindex.com/goose.md) | Open source AI coding agent with a desktop app, CLI, and 70+ MCP extensions across 15+ LLM providers, backed by the Linux Foundation | Open-source AI coding agent that runs multiple parallel sessions, with 70+ MCP extensions to coordinate agents across a desktop, CLI or SDK — Linux Foundation project. | — | Yes |
| [Manus](https://theagentsindex.com/manus.md) | An autonomous general AI agent that plans and executes multi-step tasks end-to-end in its own cloud computer. | Autonomous general AI agent that plans a multi-step task and fans out across parallel sub-agents in its own cloud computer — multi-agent execution of a single user-supplied job. | — | Yes |
| [GPT Researcher](https://theagentsindex.com/gpt-researcher.md) | Open-source autonomous research agent that plans a question, fans out across many sources and writes a cited report. Bring your own LLM and search keys. | Open-source research agent that plans a question, fans out across many parallel agents to gather sources, and writes a cited report — multi-agent research, not just multi-source aggregation. | — | Yes |
| [GC AI](https://theagentsindex.com/gc-ai.md) | An AI platform for in-house legal teams whose Research Agent runs parallel, cross-checked research across a corpus of 13M+ US case-law opinions, statutes and regulations. | Legal research agent that runs parallel, cross-checked research across a corpus of 13M+ US case-law opinions, statutes and regulations — multi-agent research pipeline for in-house legal teams. | — | Yes |
| [LiveKit Agents](https://theagentsindex.com/livekit-agents.md) | The Apache 2.0 voice-agent framework. 13.1k GitHub stars, self-hostable, and the only open-source pick in this category with fully published pricing. | Apache 2.0 voice-agent framework with explicit handoff primitives: a call can transfer from a triage agent to a specialist agent with context intact, mid-call. | — | Yes |
| [Cartesia](https://theagentsindex.com/cartesia.md) | The Stanford SSM-research spinout behind Sonic (TTS) and Ink (STT) — Line, its open-source voice-agent SDK, connects to 100+ LLMs and starts at a genuine $0/month, but the agent layer itself isn't self-hostable. | Line, the voice-agent SDK, supports multi-agent handoffs via its session API — a call can transfer between specialized agents mid-conversation while preserving context. | — | Yes |
| [Deepgram Voice Agent API](https://theagentsindex.com/deepgram-voice-agent-api.md) | The speech-infrastructure vendor's own voice-agent API. Managed STT, LLM and TTS over a single WebSocket, $4.50/hr flat, with 6 LLM providers and self-hosted or VPC deployment on the same product. | The Voice Agent API runs over a single WebSocket but supports handoff between agent configurations (LLM plus functions) mid-call, with context preserved across the transfer. | — | Yes |

## How this list is built

A tool earns a place here only if its own Published, sourced listing documents a genuine multi-agent capability — composing multiple agents yourself, assembling named agents in a no-code builder, shipping several specialized agents as one product, fanning a single task out across parallel agent instances, or handing a live conversation off between agents mid-call — not a generic "agentic" or "automation" claim with no second agent named anywhere. Verified directly against each listing's own `whatIs`/`whatItDoes`/`keyFeatures` text, sorted into the shapes documented in [What 'Multi-Agent' Actually Means](/blog/what-multi-agent-actually-means-2026/) — not inferred from the `multi-agent` tag alone. Direction is part of the test: a tool that is merely callable BY an agent, or that builds agents for someone else to run, is not itself coordinating several, and neither earns a place here.