LangGraph
Build resilient, stateful agents as graphs -- explicit nodes and edges for control flow, rather than an implicit agent loop, for reliable long-running or multi-step workflows.
- Actively maintained
- Well documented
- Permissive license
Overview
LangGraph models an agent's control flow as an explicit graph (nodes for steps, edges for transitions) with built-in state persistence, so you can build agents that pause, resume, branch, and recover from failure predictably, rather than relying on an LLM to implicitly manage the whole flow. It's from the team behind LangChain (also in this catalog) but is architecturally distinct -- a state-machine approach rather than a chain/agent-loop abstraction.
LangGraph is a fit for teams building agents where reliability and explicit control over the workflow matter -- long-running processes, human-in-the-loop approval steps, or complex branching logic -- rather than a simple single-pass agent.
- Categories
- AI Agents & Agent Tools
- Languages
- Python, JavaScript
- License
- MIT
Related Projects
Letta
Apache-2.0A platform for building stateful agents with advanced memory that learns and self-improves over time, rather than resetting between conversations.
Actively maintained
- AI Agents & Agent Tools
Composio
MITPowers 1000+ toolkits, tool search, context management and authentication so AI agents can actually take action, not just plan it.
Actively maintained
- AI Agents & Agent Tools
MCP Servers
MITOfficial reference implementations of the Model Context Protocol -- the open standard now adopted across OpenAI, Google, Microsoft and Anthropic for connecting agents to tools and data.
Actively maintained
- AI Agents & Agent Tools
SWE-agent
MITTakes a GitHub issue and autonomously tries to fix it with your LLM of choice; also usable for offensive cybersecurity and competitive coding challenges (NeurIPS 2024).
Actively maintained
- AI Agents & Agent Tools
Spotted an error? Suggest an edit on GitHub.