Our take
Inactiveno commits in over a year- Activity
- 19
- Community
- 21
- Issues
- 21
- Pull requests
- 20
+0 stars in the last 30 days
LangCorn is a focused way to put a FastAPI interface around LangChain apps, but its inactive state and highly concentrated contributor activity make it a cautious choice for new production dependencies.
Good fit if
- You already use Python, LangChain, and FastAPI, and need a small API-serving layer.
- Your use is a prototype or an application where you can maintain the integration yourself.
- The MIT-licensed project meets your licensing needs.
Look elsewhere if
- You need a project with recent maintenance: there have been no commits in over a year and no release in over a year.
- Your adoption depends on active issue or pull-request handling; none were closed or merged in the measured recent period.
- You want a project whose maintenance is shared broadly, since most of the code comes from one person.
All health signals
| Last commit | 2024-07-15 (2.3 years ago) |
|---|---|
| Commits, last 90 days | 0 |
| Releases, last 12 months | 0 (latest 0.0.22, 2023-11-06) |
| Contributors | 4 (top contributor: 93% of commits) |
| Issues closed, last 90 days | 0 |
| Pull requests merged, last 90 days | 0 |
| Project age | 3 years |
Checked on 2026-10-16 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
940Forks
69Change since Nov 12, 2026: 0 stars·0 forks
Overview
LangCorn is a Python API server built on LangChain and FastAPI. It turns LangChain models, chains, pipelines, agents, and custom run functions into REST endpoints, so developers can serve them without building an API layer from scratch.
It is aimed at developers deploying LangChain applications who want FastAPI's request handling and automatically served API documentation. The project also describes support for static token authentication and per-request LLM settings.
Key Features
- Exposes LangChain chains and pipelines through generated REST endpoints.
- Serves multiple chains from one FastAPI application.
- Provides a command-line server and a
create_servicefunction for integration into an existing FastAPI app. - Generates FastAPI documentation for the served endpoints.
- Supports optional static API-token authentication.
- Accepts custom run functions, as well as chain objects.
- Documents passing conversation history and memory in requests.
- Supports request headers for custom LLM API keys and selected model parameters.
Use Cases
- A Python developer can expose an existing LangChain chain as an API without writing endpoint routing by hand.
- A team serving several LangChain pipelines can host them through a shared FastAPI service.
- Developers integrating a LangChain service into an existing FastAPI application can use
create_servicerather than the standalone command. - A prototype or internal tool can provide API documentation and optional token authentication for its LangChain endpoints.
What you need
Detected in the repository
- Python (from pyproject.toml)
- Automated checks on GitHub Actions
License in plain words
MITpermissive
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the copyright and license notice
- Share your changes: no
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
Install the package:
pip install langcorn
Then start a server with a Python module path to a chain, for example langcorn server examples.ex1:chain. See the README for app integration, authentication, and request examples.
Alternatives
- agent-service-toolkit: It provides a FastAPI service for LangGraph agents with a client and chat UI, rather than exposing LangChain chains, pipelines, and custom functions.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| langcorn | Python | MIT | 941 | Inactive |
| agent-service-toolkit | Python | MIT | 4.5k | Active |
Considerations
The repository is marked inactive, with no recent commits and no recent release; it also has no reported test suite. Contributor activity is concentrated in one person, and recent issue and pull-request handling is absent in the measured period. The project requires Python and is built around LangChain and FastAPI, so compatibility with the versions and APIs in your application should be checked before adoption. The README documents static token authentication, but does not describe a broader authentication system.
Found this useful?
Share it with someone who would like langcorn.