{
  "listings": [
    {
      "slug": "agentos",
      "name": "AgentOS",
      "company": "Framers Lab, Inc.",
      "grade": "A",
      "fit": "caveat",
      "why": "agency() runs sequential, parallel, debate, review-loop, hierarchical and graph strategies across 13 providers, but the docs list spans for turns and tool results only, not per hand-off, and say nothing of sub-agent tool calls reaching the stream.",
      "source": "https://docs.agentos.sh/features/agency-collaboration",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/agentos"
    },
    {
      "slug": "agno",
      "name": "Agno",
      "company": "Agno Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Team modes coordinate, route, broadcast and tasks; members return results to the leader, and tracing records leader coordination and member runs. Member events stream with stream_events. Accounts: tool_call_limit leaves the loop running (agno #8304), and docs were hard to navigate (HN 47561818).",
      "source": "https://docs.agno.com/teams/delegation.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/agno"
    },
    {
      "slug": "boxlang-ai",
      "name": "BoxLang AI",
      "company": "Ortus Solutions, Corp.",
      "grade": "B",
      "fit": "caveat",
      "why": "Sub-agents are wrapped as delegate_to_\u003cname\u003e tools that return to the parent, across 15+ providers. The docs show no per-hand-off trace span or sub-agent tool calls in the stream, and no OpenTelemetry export.",
      "source": "https://ai.ortusbooks.com/main-components/agents/hierarchy.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/boxlang-ai"
    },
    {
      "slug": "claude-agent-sdk",
      "name": "Claude Agent SDK",
      "company": "Anthropic, PBC",
      "grade": "BB",
      "fit": "caveat",
      "why": "Subagents run in their own context, in parallel, return a report to the parent and take their own model and maxTurns. Claude models only, so the second-provider test can't be met; per-hand-off trace spans aren't described.",
      "source": "https://code.claude.com/docs/en/agent-sdk/subagents.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/claude-agent-sdk"
    },
    {
      "slug": "crewai",
      "name": "CrewAI",
      "company": "CrewAI, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "A hierarchical process puts a manager over specialist agents, but accounts report it failing on a local Ollama model where sequential worked (crewAI #1863) and stray backticks behind FastAPI (#2105). Built-in tracing needs a CrewAI AMP login.",
      "source": "https://docs.crewai.com/v1.15.41/en/observability/tracing.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/crewai"
    },
    {
      "slug": "cursor-agent-sdk",
      "name": "Cursor Agent SDK",
      "company": "Anysphere, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Subagents declare a description the parent reads to delegate and inherit the model; every model turn runs through Cursor's backend with Cursor models, and the docs read don't show hand-off spans or sub-agent tool calls in the stream.",
      "source": "https://cursor.com/docs/agent-sdk/reference/agent-config.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cursor-agent-sdk"
    },
    {
      "slug": "docker-agent",
      "name": "Docker Agent",
      "company": "Docker, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "sub_agents delegate through transfer_task and results flow back to the root; handoffs pass the conversation on. --otel spans cover sub-agent hand-offs and provider fallbacks, across many providers. Whether sub-agent tool calls reach the client stream wasn't confirmed.",
      "source": "https://docker.github.io/docker-agent/concepts/multi-agent/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/docker-agent"
    },
    {
      "slug": "google-adk",
      "name": "Agent Development Kit (ADK)",
      "company": "Google LLC",
      "grade": "BB",
      "fit": "caveat",
      "why": "Sub-agents, workflows and AgentTool, with invoke_agent and execute_tool OpenTelemetry spans. Accounts: control went into a sub-agent and never returned (adk-python #147), a built-in tool failed inside a sub-agent (#53), and some built-in tools exclude all others in one agent.",
      "source": "https://adk.dev/tools/limitations/index.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/google-adk"
    },
    {
      "slug": "guilds-run",
      "name": "guilds.run",
      "company": "Cigale AI",
      "grade": "C",
      "fit": "caveat",
      "why": "Guilds are standing teams sharing a group chat, and each run keeps the prompt and every tool call. The docs describe chat dispatch between agents rather than a router with a defined return to the caller, and no trace export.",
      "source": "https://docs.guilds.run/concepts/group-chat",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/guilds-run"
    },
    {
      "slug": "langgraph",
      "name": "LangGraph",
      "company": "LangChain, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Hand-offs are tools returning a Command, with subagent, router and subgraph patterns, on any LangChain model. Tracing is LangSmith, which needs an account, and subgraph hand-offs need careful context handling per the docs.",
      "source": "https://docs.langchain.com/oss/python/langchain/multi-agent/handoffs.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/langgraph"
    },
    {
      "slug": "llamaindex",
      "name": "LlamaIndex Framework",
      "company": "LlamaIndex, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "AgentWorkflow hands off through can_handoff_to and streams events; the orchestrator pattern exposes sub-agents as tools so control returns. The docs read don't show hand-offs as separate trace spans, and OpenAI is the default LLM unless Settings changes it.",
      "source": "https://developers.llamaindex.ai/python/framework/understanding/agent/multi_agent/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/llamaindex"
    },
    {
      "slug": "mastra",
      "name": "Mastra",
      "company": "Kepler Software, Inc.",
      "grade": "A",
      "fit": "caveat",
      "why": "Supervisor agents keep a lead in control and delegate to subagents; hand-off and council patterns are documented, tracing follows model and tool calls in one request, across AI SDK providers. Sub-agent spans per hand-off weren't confirmed; .network() is deprecated.",
      "source": "https://mastra.ai/docs/guides/multi-agent-systems.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mastra"
    },
    {
      "slug": "microsoft-agent-framework",
      "name": "Microsoft Agent Framework",
      "company": "Microsoft Corporation",
      "grade": "A",
      "fit": "caveat",
      "why": "Handoff orchestration passes control between agents with explicit rules (specialists can return to triage) and streams workflow events; OpenTelemetry follows GenAI conventions. An account saw checkpoint resume fail when per-request agent ids changed (agent-framework #4793).",
      "source": "https://learn.microsoft.com/en-us/agent-framework/workflows/orchestrations/handoff",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/microsoft-agent-framework"
    },
    {
      "slug": "openai-agents-sdk",
      "name": "OpenAI Agents SDK",
      "company": "OpenAI OpCo, LLC",
      "grade": "AA",
      "fit": "caveat",
      "why": "Hand-offs and manager-style Agent.as_tool, whose on_stream callback surfaces nested agent events, and approvals apply across hand-offs. Accounts: hand-offs were one-way (openai-agents-python #847) and routing worsened after a model swap (#1397).",
      "source": "https://openai.github.io/openai-agents-python/multi_agent/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/openai-agents-sdk"
    },
    {
      "slug": "pydantic-ai",
      "name": "Pydantic AI",
      "company": "Pydantic Services Inc.",
      "grade": "AA",
      "fit": "caveat",
      "why": "Delegation through tools returns control to the parent, with SubAgents in the Harness, programmatic hand-off and graphs, across 25+ providers, and OpenTelemetry spans via Logfire or any collector. Routing quality is left to the app; no account tested it.",
      "source": "https://pydantic.dev/docs/ai/guides/multi-agent-applications/index.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/pydantic-ai"
    },
    {
      "slug": "smolagents",
      "name": "smolagents",
      "company": "Hugging Face, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "A manager agent calls managed_agents as tools and gets their answers back, on any model through LiteLLM, Transformers or Inference Providers, with OpenTelemetry instrumentation. The secure-execution page says the Docker executor doesn't support multi-agents.",
      "source": "https://huggingface.co/docs/smolagents/v1.26.0/examples/multiagents.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/smolagents"
    },
    {
      "slug": "strands-agents",
      "name": "Strands Agents",
      "company": "Amazon Web Services, Inc.",
      "grade": "A",
      "fit": "caveat",
      "why": "Agents as tools (control returns to the orchestrator), Swarm hand-offs, Graph and Workflow patterns, with spans per model and tool invocation. Bedrock is the default provider; whether hand-offs get their own span wasn't confirmed.",
      "source": "https://strandsagents.com/docs/user-guide/sdk/multi-agent/multi-agent-patterns/index.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/strands-agents"
    },
    {
      "slug": "tradingagents",
      "name": "TradingAgents",
      "company": "Tauric Research",
      "grade": "B",
      "fit": "caveat",
      "why": "A fixed LangGraph pipeline of analysts, a bull and bear debate, a trader and risk reviewers, on many providers with a provider per model tier. Routing isn't configurable, and accounts report results changing every run (TradingAgents #178) and suspected training-data leakage in backtests (#33).",
      "source": "https://raw.githubusercontent.com/TauricResearch/TradingAgents/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/tradingagents"
    },
    {
      "slug": "vercel-ai-sdk",
      "name": "AI SDK",
      "company": "Vercel Inc.",
      "grade": "AA",
      "fit": "caveat",
      "why": "Subagents are invoked through a tool and return a result, optionally streaming progress to the UI, on any AI SDK provider. There is no hand-off primitive; a basic subagent blocks and hides its steps unless you stream it yourself, and spans per hand-off aren't described.",
      "source": "https://ai-sdk.dev/docs/agents/subagents",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/vercel-ai-sdk"
    },
    {
      "slug": "nitrostack",
      "name": "NitroStack",
      "company": "Nitrostack Inc.",
      "grade": "C",
      "fit": "no",
      "why": "No agents or hand-offs: a NitroStack project is an MCP server that AI clients connect to.",
      "source": "https://docs.nitrostack.ai/docs/getting-started/how-nitrostack-works.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/nitrostack"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 10,
    "after": [
      "agent-observability.debug-failed-run",
      "agent-observability.offline-eval-regression"
    ],
    "area": "frameworks",
    "asks": [
      "route support questions to the right specialist agent",
      "have a manager agent delegate to researchers",
      "build a team of agents for this analysis",
      "hand off to the billing agent and come back"
    ],
    "before": [
      "frameworks.tool-calling-agent"
    ],
    "blockers": [
      "hand-offs that are one-way, so the orchestrator never regains control",
      "sub-agent run as a tool hides its tool calls from the stream",
      "built-in tools refused inside sub-agents",
      "routing quality changes when the default or chosen model changes",
      "the same input gives different answers each run, so outputs cannot be backtested"
    ],
    "capabilities": [
      "agent.framework",
      "agent.multi-agent",
      "agent.handoff",
      "observability.traces"
    ],
    "category": "frameworks",
    "categoryName": "Agent frameworks \u0026 SDKs",
    "checked": "2026-11-15",
    "companies": {
      "fit": 0,
      "fitWithLimit": 19,
      "tagged": 80
    },
    "competition": "none",
    "fits": null,
    "fitsWithLimit": [
      "agentos",
      "agno",
      "boxlang-ai",
      "claude-agent-sdk",
      "crewai",
      "cursor-agent-sdk",
      "docker-agent",
      "google-adk",
      "guilds-run",
      "langgraph",
      "llamaindex",
      "mastra",
      "microsoft-agent-framework",
      "openai-agents-sdk",
      "pydantic-ai",
      "smolagents",
      "strands-agents",
      "tradingagents",
      "vercel-ai-sdk"
    ],
    "id": "frameworks.multi-agent-handoff",
    "listings": {
      "caveat": 19,
      "no": 1,
      "notRead": 0,
      "tagged": 87,
      "unchecked": 0,
      "yes": 0
    },
    "name": "Split a job across specialist agents with hand-offs",
    "status": "draft",
    "success": "The router sends each test request to the expected specialist, control returns to the caller where the design says it should, each hand-off and the context passed appear as separate steps in the trace, and sub-agent tool calls are visible in the stream. Runs on a second model provider without code changes. Measured: routing accuracy on a fixed set of 20 requests and the spread of answers across 5 repeats of the same request.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/frameworks.multi-agent-handoff.json",
    "weight": 16,
    "weightBasis": "10 of 61 accounts have this as their main job (share 16.4, rounded by largest remainder to sum 100); includes 2 TradingAgents accounts on its fixed research pipeline"
  }
}
