LangGraph
A graph-based framework from the LangChain team for building stateful, controllable agent workflows. You define agents as graphs with explicit state, branching, and human-in-the-loop steps, which suits production systems that need audit trails and recovery points. Works with local models.
Strengths
- Explicit control over state, branching, and human-in-the-loop steps
- Production features like persistence, streaming, and recovery points
- Model-agnostic, so it works with local models through Ollama
Weaknesses
- More concepts to learn than simpler role-based frameworks
- Verbose for small, one-off agent tasks
- Sits within the larger LangChain ecosystem, which some find heavy
At a glance
- Licence
- MIT
- Pricing
- Open core
- Platforms
- macOS, Windows, Linux
- GPU required
- No
Links
Works with
Entry last verified 30 July 2026.