agent-api-server

agent-api-server is a FastAPI-based API server for LangGraph agents. It exposes REST endpoints for thread, schema, graph, and runtime configuration management, and it serves a built-in web client from /site.

Features

• FastAPI application factory for embedding or standalone deployment
• LangGraph-oriented API routes under /api/v1
• Built-in static client assets bundled in both sdist and wheel artifacts
• Redis-backed thread storage and PostgreSQL checkpoint integration
• Optional integration with config center, SSO, MCP, and model management services

Requirements

• Python 3.11 to 3.13
• Redis
• PostgreSQL
• Access to all runtime dependencies declared in pyproject.toml

Installation

Install from a package index that provides all required dependencies:

pip install agent-api-server

This project depends on llm-sdk and model-manage-client. If those packages are hosted on a private index in your environment, configure pip or Poetry to use that index before installation.

Configuration

The server reads configuration from environment variables. Common settings include:

REDIS_URL=redis://localhost:6379/0
POSTGRES_URL=postgresql://postgres:postgres@localhost:5432/postgres
MODEL_MANAGER_SERVICE_URL=http://127.0.0.1:10053
SERVER_PORT=8080
SERVER_WORKER_AMOUNT=1
LOG_LEVEL=INFO
ENABLE_MCP_SERVER=False

See .env_example for a more complete example.

Running the server

Run the application with Uvicorn:

uvicorn agent_api_server.service:create_fastapi_app --factory --host 0.0.0.0 --port 8080

After startup:

• API root: http://127.0.0.1:8080/api/v1
• OpenAPI docs: http://127.0.0.1:8080/docs
• Built-in client: http://127.0.0.1:8080/site

Build

Build source and wheel distributions with Poetry:

poetry build

Repository

Source repository: https://gitlab.wise-paas.com/openai/agent_api_server