spb/tools-spboucher-ai

1{2  "slug": "langgraph",3  "name": "LangGraph",4  "aliases": ["langgraph (PyPI)", "LangGraph.js", "LangGraph Platform (former deployment name)"],5  "vendor": { "name": "LangChain, Inc.", "slug": "langchain-inc", "website": "https://www.langchain.com" },6  "homepage_url": "https://www.langchain.com/langgraph",7  "docs_url": "https://docs.langchain.com/oss/python/langgraph/overview",8  "repo_url": "https://github.com/langchain-ai/langgraph",9  "pricing_url": "https://www.langchain.com/pricing",10  "license_url": "https://github.com/langchain-ai/langgraph/blob/main/LICENSE",11  "product_type": "framework",12  "product_status": "active",13  "summary": "Low-level orchestration framework and runtime for stateful, long-running agents expressed as graphs, with durable execution, checkpointing, human-in-the-loop and streaming",14  "description": "LangGraph is an MIT-licensed framework and runtime from LangChain, Inc. for building long-running, stateful agents. Rather than hiding the agent loop behind a prompt abstraction, it asks the developer to define a `StateGraph`: typed state, nodes that are ordinary functions or LLM calls, and edges (fixed or conditional) that connect them to `START` and `END` before `compile()` produces a runnable. This lets deterministic steps and model-driven steps live in one graph, and it can be used with or without the LangChain library. Python and JavaScript implementations are maintained in parallel.\n\nThe runtime is where most of the value sits. Checkpointers persist state after every step, so a run can survive a crash and resume where it stopped; the same mechanism provides time travel for debugging, short-term memory within a thread and long-term memory stores across threads. Interrupts pause execution so a human can inspect or edit state before approving a tool call, and streaming surfaces tokens, state updates and events as they happen. LangSmith adds tracing and a visual studio, and the hosted path, now called LangSmith Deployment (previously LangGraph Platform), runs graphs as managed services with cron scheduling, MCP exposure and an Assistants API; self-hosted and hybrid variants exist on the Enterprise plan.\n\nLangGraph suits workflows where reliability matters more than convenience: multi-step research agents, approval-gated automations and anything that must pause for hours. The cost is verbosity and a learning curve around state schemas and reducers, and production-grade persistence requires a database-backed checkpointer rather than the in-memory default.",15  "capabilities": ["Graph definition with typed state, nodes, conditional edges and subgraphs", "Durable execution with checkpointers and resumable runs", "Human-in-the-loop interrupts to review or edit state", "Short- and long-term memory stores", "Token, update and event streaming", "Python and JavaScript libraries usable without LangChain", "LangSmith tracing and studio; hosted LangSmith Deployment with cron, MCP and Assistants API", "Prebuilt agent helpers and the Deep Agents SDK built on top"],16  "workflows": ["Model an approval-gated automation that pauses for a human before side effects", "Build a multi-step research agent with persistent memory across sessions", "Deploy a graph as a managed service with scheduled runs", "Debug a failed run by replaying from a checkpoint"],17  "advantages": ["Explicit control flow instead of hidden prompts", "Persistence and interrupts are first-class", "Framework-agnostic model and tool usage", "MIT license with optional commercial hosting"],18  "limitations": ["More code than high-level agent frameworks", "In-memory checkpointer is not production-grade; a database backend is needed", "Deployment product has been renamed, which dates older tutorials", "Hosted features beyond the free tier require LangSmith plans"],19  "prerequisites": ["Python 3.10+ or Node.js", "A model provider or local runtime; a Postgres or SQLite checkpointer for durable runs"],20  "audiences": ["Engineers building production agents with reliability requirements", "Teams needing human approval steps in automations", "Researchers prototyping multi-agent workflows"],21  "alternatives": ["langchain", "pydantic-ai", "openai-agents-sdk", "crewai", "autogen"],22  "comparison_notes": "LangChain's create_agent is a higher-level harness that runs on LangGraph; use LangGraph directly when you need custom control flow. Pydantic AI emphasizes typed outputs and dependency injection and offers durable execution through Temporal or DBOS rather than its own checkpointer. The OpenAI Agents SDK is lighter and tied to OpenAI's Responses API by default. CrewAI models work as role-based crews and flows. AutoGen is archived and points users to Microsoft Agent Framework.",23  "categories": [{ "slug": "agent-frameworks", "primary": true }],24  "tags": ["agents", "llm", "open-source", "python", "typescript", "orchestration", "state-machines"],25  "use_cases": ["build-agents"],26  "operating_systems": ["macos", "linux", "windows"],27  "execution_modes": ["local", "self-hosted", "cloud"],28  "interfaces": ["library", "api"],29  "deployment_models": ["embedded", "saas", "hybrid", "on-premises"],30  "integrations": ["LangChain", "LangSmith", "PostgreSQL (checkpointer)", "SQLite (checkpointer)", "Model Context Protocol", "OpenAI", "Anthropic"],31  "data_formats": ["JSON"],32  "languages": ["Python", "TypeScript", "JavaScript"],33  "source_model": "open-source",34  "license_spdx": "MIT",35  "pricing_model": ["open-source", "free", "freemium", "enterprise"],36  "pricing_checked_at": "2026-11-02",37  "self_hostable": true,38  "sources": [39    { "url": "https://www.langchain.com/langgraph", "type": "official_site", "title": "LangGraph", "supports": ["name", "summary"], "checked_at": "2026-11-02" },40    { "url": "https://docs.langchain.com/oss/python/langgraph/overview", "type": "official_docs", "title": "LangGraph overview", "supports": ["capabilities", "deployment_models"], "checked_at": "2026-11-02", "note": "Refers to hosted deployment as LangSmith Deployment" },41    { "url": "https://github.com/langchain-ai/langgraph/blob/main/LICENSE", "type": "license_page", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02" },42    { "url": "https://www.langchain.com/pricing", "type": "pricing_page", "supports": ["pricing_model"], "checked_at": "2026-11-02", "note": "Developer, Plus and Enterprise plans cover LangSmith Deployment" }43  ],44  "confidence": "high",45  "discovery_method": "editorial-research",46  "depth": "deep",47  "editorial_status": "reviewed",48  "visibility": "public",49  "featured": false,50  "author": "batch-A"51}52