# langchain-ai/langserve

LangServe 🦜️🏓

Repository: https://github.com/langchain-ai/langserve
Canonical: https://ross.abutalabs.com/products/langserve
Language: JavaScript
License: NOASSERTION
License Family: other
Topics: deployment, fastapi, langchain, langchain-python, llm, llms
Archived: true
Last push: 2026-05-05T19:49:07+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 80, release rhythm 52, longevity 76
- inputs: {"age_days": 1069, "days_push": 120, "days_rel": 320, "gap_med": 29, "n_releases_24m": 6}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2330, forks 272 (observed 2026-08-28T04:06:37.695571+00:00)

## What it is
LangServe is a Python library that deploys LangChain runnables and chains as REST APIs built on FastAPI, with automatic input/output schema validation, invoke/batch/stream endpoints, and a built-in playground UI. It also ships a client SDK (with a JavaScript client in LangChain.js) for calling remote runnables as if they were local, though the project is deprecated in favor of LangGraph Platform.

## Use cases
- deploy a langchain chain as a rest api
- serve an llm app with fastapi endpoints
- expose a langchain runnable over http
- stream llm responses and intermediate steps to a frontend
- test langchain chains in an interactive playground
- call a deployed langchain server from javascript

## When to choose
- you are maintaining an existing LangServe-based deployment and need community bug fixes
- you need to quickly expose simple LangChain runnables as invoke/batch/stream REST endpoints with automatic schemas
- you want a built-in playground and optional LangSmith tracing for a FastAPI-served chain

## When to avoid
- starting a new project, since LangServe is deprecated in favor of LangGraph Platform
- deploying LangGraph graphs or agents, which it is not designed for
- you need new features or long-term official support, as only community bug fixes are accepted

## Facets
- artifact type: library
- maturity: maintenance
- function: deployment, api-framework, http-server, sdk, llm-inference
- domain: large-language-models, artificial-intelligence, apis, backend, web-development, developer-tools
- platform: python
- tags: langchain, fastapi, pydantic, rest-api, streaming, playground, langsmith-tracing, runnables, deprecated, web-server

## Member repositories
- langchain-ai/langserve (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.695571+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:38:06.261971+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/langserve (fetched 2026-08-28T04:06:37.695571+00:00, sha e5d35a1547d0)
- Data as of 2026-08-30T08:39:29.467469+00:00.