tools
LangGraph
LangGraph is an open-source framework for building stateful, controllable agents and multi-step workflows.
In inglese
LangGraph lets developers define agent workflows as graphs with state, memory, persistence, streaming, and human approval steps. It supports deterministic and agentic components, multi-agent systems, and custom execution flows.
It is used by teams building long-running agents, business-process automation, conversational applications, and other LLM systems requiring control. The core library is free and MIT-licensed; hosted deployment, observability, and execution services are billed through LangSmith.
Features
- Build stateful, multi-step agent workflows as graphs
- Add human-in-the-loop approval and moderation steps
- Persist conversation history, checkpoints, and long-term memory
- Stream tokens, agent actions, and workflow events
- Compose single-agent, multi-agent, and hierarchical workflows
- Deploy through LangSmith Deployment or self-hosted infrastructure
- MIT-licensed open-source library
Use cases
- Build long-running business-process automation
- Create conversational agents with persistent memory
- Orchestrate workflows combining deterministic and agentic steps
- Add human approval to sensitive agent actions
- Deploy custom multi-agent applications
- Stream agent progress and actions to an application interface
Pros
Cons
Latest updates
- The completed items list in an annotation queue now offers Add to Dataset for selected thread items, importing each thread as a multi-turn example.
The completed items list offers Add to Dataset for selected thread items, importing each thread as a multi-turn example.
- Edit and delete in the experiments table now check project permission, to match BE.
Edit and delete in the experiments table now check project permission.
- Charts now show shape-aware loading skeletons instead of temporary zero values while data loads. Evaluator spend charts use bar and metric placeholders that preserve the final layout.
Charts show loading skeletons instead of temporary zero values while data loads.
- Downloading experiment results with “Include annotator name and comment per row” now keeps automated evaluator scores in every feedback column, alongside human annotations.
Downloading experiment results now keeps automated evaluator scores in every feedback column, alongside human annotations.
- The evaluators list API accepts an agent_id filter to return evaluators attached to the agent’s environments or tagged datasets.
The evaluators list API accepts an agent_id filter.
Capabilities
- Builds agents and workflows — “Design agents that reliably handle complex tasks with LangGraph, an agent runtime and low-level orchestration framework.” source
Get it
Security
- SOC 2 Type II — “we've just received our annual SOC 2 Type II report” source
- SOC 2 — “we've just received our annual SOC 2 Type II report” source
- ISO 27001 — “We're glad to share that LangChain has achieved ISO/IEC 27001:2022 certification for our Information Security Management System (ISMS).” source
- GDPR — “Compliance SOC 2 Type II ISO 27001:2022 GDPR HIPAA” source
- HIPAA — “Compliance SOC 2 Type II ISO 27001:2022 GDPR HIPAA” source
- Data kept in the EU — “USA or Netherlands” source
Pricing
- Starting price
- $39/user/mo
- Prices checked
- 2026-09-25
Developer
Free
- Up to 5k base traces / mo, then pay-as-you-go
- Community support
- 1 seat
Plus
- $39 / seat per month
- Up to 10k base traces / mo, then pay-as-you-go
- Access to Deployment, Engine, and more
- Add unlimited seats
Enterprise
Price on request
- Self-hosted and hybrid deployment options
- Custom SSO, ABAC, and RBAC
- Support SLA
- Custom seats and workspaces