VibeServer

Prompt-driven backend framework. Replace REST endpoints with natural language.

Install

pip install vibeserver

Quick Start

from vibeserver import VibeServer

vs = VibeServer()

@vs.tool("greet", description="Greet a user by name")
def greet(name: str) -> dict:
    return {"message": f"Hello, {name}!"}

@vs.tool("calculate", description="Evaluate a math expression")
def calculate(expression: str) -> dict:
    result = eval(expression)
    return {"result": result}

@vs.tool("fetch_weather", description="Get weather for a city")
def fetch_weather(city: str) -> dict:
    return {"city": city, "temp": "22°C", "condition": "sunny"}

vs.run()  # http://localhost:8000

Then call it:

curl -X POST http://localhost:8000/ -H "Content-Type: application/json" -d '{"input": "greet Alice"}'
# → {"message": "Hello, Alice!"}

How It Works

1. Send natural language: POST / with {"input": "greet Alice"}
2. LLM plans execution: {steps: [{action: "greet", params: {name: "Alice"}}]}
3. Tool executes and returns structured JSON
4. Repeat calls match the Intent Graph — no LLM needed

Intent Graph

Persistent NL→plan cache with n-gram fingerprinting and cosine similarity. No embedding model needed. Repeat queries skip the LLM entirely with ~0ms latency.

Built-in Tools

Tool	Description
compute	Transform data (uppercase, lowercase, json_parse, sum, length)
create_record	Create a database record
search	Search records by type
update_record	Update a record
delete_record	Delete a record
get_user	Look up user by ID
auth	Verify API keys
list_users	List all users (admin)
stats	System statistics

Configuration

VIBESERVER_MODEL=openai/cmd/deepseek/deepseek-v4-pro
VIBESERVER_API_BASE=http://localhost:20128/v1
VIBESERVER_API_KEY=sk-xxx
VIBESERVER_DB_PATH=vibeserver.db
VIBESERVER_LOG_LEVEL=INFO

Docker

docker compose up

Links

• PyPI: https://pypi.org/project/vibeserver/0.3.0/
• GitHub: https://github.com/Ifarra/VibeServer
• Docs: https://github.com/Ifarra/VibeServer/tree/main/docs

License

MIT