Skip to main content

Kalibr SDK — Integrate your SaaS with every major AI model using a single SDK.

Project description

Kalibr SDK

Multi-Model AI Integration Framework

Write once. Deploy anywhere. Connect to any AI model.

Kalibr lets developers expose any Python function as a model-compatible API — instantly usable by GPT, Claude, Gemini, and beyond.


🚀 Quick Start

Install

pip install kalibr

Run the included demo

kalibr-connect serve examples/demo_app.py

Then open your browser to:

http://127.0.0.1:8000/docs

You’ll see automatically generated endpoints for your demo functions — all schema-normalized and model-ready.


⚙️ Core Features

Multi-Model Support — Works with GPT Actions, Claude MCP, Gemini, and Copilot
Automatic Schema Generation — Define once, serve everywhere
Fast Local Development — Instantly test endpoints with kalibr-connect serve
Lightweight Runtime — No dependencies beyond FastAPI + Uvicorn

🚧 Coming Soon:
• Auth & JWT user sessions
• Analytics & observability
• One-click deployment (Fly.io, AWS Lambda)


🧠 How It Works

Decorate your Python functions with @app.register():

from kalibr.kalibr_app import KalibrApp

app = KalibrApp()

@app.register()
def summarize(text: str) -> str:
    """Summarize text input."""
    return text[:100] + "..."

@app.register()
def sentiment(text: str) -> dict:
    """Return a basic sentiment classification."""
    return {"sentiment": "positive" if "love" in text.lower() else "neutral"}

kalibr_app = app.get_app()

Then run:

kalibr-connect serve demo_app.py

Your endpoints appear instantly at:

http://127.0.0.1:8000/docs

📁 Project Structure

kalibr/
  ├── __init__.py
  ├── __main__.py
  ├── kalibr_app.py
  ├── schema_generators.py
examples/
  ├── demo_app.py
  └── enhanced_kalibr_example.py

📘 Documentation

See KALIBR_SDK_COMPLETE.md for full developer documentation.


Kalibr — Transform how you build AI-integrated applications.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kalibr-1.0.10.tar.gz (14.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

kalibr-1.0.10-py3-none-any.whl (4.8 kB view details)

Uploaded Python 3

File details

Details for the file kalibr-1.0.10.tar.gz.

File metadata

  • Download URL: kalibr-1.0.10.tar.gz
  • Upload date:
  • Size: 14.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.1

File hashes

Hashes for kalibr-1.0.10.tar.gz
Algorithm Hash digest
SHA256 158ef8a24cb0bd4836ea724bec68829d4ae7d1fc1360b04794a49fef2841eb49
MD5 f4eaee8ec332f4b20af0803d6c9740e1
BLAKE2b-256 e1c80e27181f296b7f5456d24255a8ca0c056567a0a22f2676c16051e1d53405

See more details on using hashes here.

File details

Details for the file kalibr-1.0.10-py3-none-any.whl.

File metadata

  • Download URL: kalibr-1.0.10-py3-none-any.whl
  • Upload date:
  • Size: 4.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.1

File hashes

Hashes for kalibr-1.0.10-py3-none-any.whl
Algorithm Hash digest
SHA256 32038736cb45e76a172276762073bbeabcfb3f23bd6ab682d98a99896362290a
MD5 5294dfd11d8fbb8d002c2c25a240169a
BLAKE2b-256 af86935abae128e4e4cb54bcbdaf28513e987c8eac019cb29cf392f311864faa

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page