MELlamaIndex AgentWorkflow
LlamaIndex workflow framework for multi-agent systems with explicit handoff and tool routing.
Best for
- •RAG-native agents that require structured workflow control.
Limitations
- •Complex retrieval-heavy flows need careful memory and context controls.
- •Reliability depends on external model/tool stack quality.
Use carefully when
- •Single-turn assistants with no retrieval/tool requirements.
Quickstart
- Start with one retriever + one planner agent before scaling to specialist agents.
Setup checklist
- • API key required: No
- • SDK quality: medium
- • Self-host difficulty: medium
Usage Notes
- • Validate model behavior on your own benchmark slices before rollout.
- • Pin version/provider routes for reproducible outputs.
- • Add logging + fallback routes for high-volume workloads.
Pricing (USD)
Input / 1M
-
Output / 1M
-
Monthly
$0
Capabilities
- agentHandoffsYes
- toolCallingYes
- retrievalIntegrationYes
- workflowStateYes
Benchmarks
github Stars
47155
github Forks
6862
active Maintainer Signal
89
Community reviews
0 reviews • avg —
No reviews yet.
Samples
codeWorkflow snippet
retrieve -> reason -> call tool -> verify -> respond
Compliance
- License: mit
- Commercial use: allowed
Provenance
- Last verified: 17/4/2026
- Source: https://docs.llamaindex.ai/en/stable/understanding/agent/multi_agent/