Python + TypeScript framework for chaining prompts, tools, retrievers, and memory into LLM applications. Ubiquitous in the ecosystem; pairs with LangGraph for agent orchestration and LangSmith for tracing.
Orchestration · LangChain
LangChain
The default open-source framework for composing LLM apps.
OPEN SOURCEAPICLIVetted
Model support
Model-agnostic
Where it runs
- API
- CLI
Tags
- #framework
- #python
- #typescript
- #rag
- #open-source
Related in Orchestration
View Vercel AI SDK details OrchestrationOPEN SOURCEDeployedVercel AI SDK
Vercel
TypeScript SDK for streaming, tool-calling, and structured outputs.
Vercel's batteries-included TypeScript framework for LLM-powered apps. Streaming primitives, structured outputs, tool calling, and React hooks for chat UIs — works with every major provider out of the box.
- typescript
- streaming
- tool-use
- structured-output
View CrewAI details OrchestrationOPEN SOURCECrewAI
crewAIInc
Multi-agent framework with explicit roles and tasks.
Python framework for orchestrating crews of specialised agents — researcher, writer, reviewer — coordinated through shared context. Opinionated about roles, sequencing, and delegation; good fit for content-and-research pipelines.
- multi-agent
- roles
- python
- open-source
View Inngest details OrchestrationFREEMIUMInngest
Inngest
Durable workflow engine for AI background jobs.
Event-driven, durable execution engine — pause/resume, retries, fan-out, scheduling — designed for long-running AI jobs that can't sit in a request/response cycle. TypeScript-first; framework-agnostic.
- durable
- workflow
- background-jobs
- typescript
View LangGraph details OrchestrationOPEN SOURCELangGraph
LangChain
Graph-based agent orchestration. Stateful loops with checkpoints.
LangChain's agent layer. Model agents as nodes in a state graph with persistent checkpoints, human-in-the-loop steps, and durable execution. Strong when you need a long-running, debuggable agent rather than a one-shot chain.
- agents
- graph
- state
- open-source