Connect any API to AI platforms in 10 lines of code
Project description
Kalibr SDK Docs
Kalibr makes your SaaS agent-ready.
Define your API once and Kalibr compiles connectors for ChatGPT, Claude, and more.
Our MVP works today with GPT and Claude. The universal proxy makes your API callable in minutes.
Quickstart (MVP)
Install
pip install kalibr-sdk
Your First Integration
from kalibr_sdk import Kalibr
# Connect your backend
k = Kalibr()
k.connect("https://api.airtable.com", api_key="key123")
# Register actions
k.register_tool("create_record", "/v0/base123/Table", "POST")
k.register_tool("search_records", "/v0/base123/Table", "GET")
# Deploy
k.deploy()
What Happens
• Kalibr spins up the universal proxy
• Exposes your API at public URLs via ngrok
• Generates platform configs (OpenAPI for GPT, MCP for Claude)
• You copy the configs into ChatGPT or Claude → your API works
⸻
Demo Experience
With 5–7 lines of code:
• Your API works with ChatGPT and Claude
• No platform-specific code
• Real requests hit your production backend
Example:
• ChatGPT → “Add a contact to my CRM”
• Claude → “Search for customers from Microsoft”
Both hit your Airtable API through Kalibr.
⸻
Current Status (MVP)
GPT Actions (OpenAPI) working
Claude MCP working
Universal proxy live (local + ngrok)
Register actions once, run on multiple models
⸻
What’s Next
With funding + partners, we’ll expand:
• Hosted proxy (multi-tenant, secure, SOC2)
• More platforms (Gemini, Azure Copilot, Assistants)
• Normalization layer (auth, error codes, schema drift)
• Drift detection (auto-patch when providers change)
• Auto-registration (where platforms support it)
⸻
Roadmap
MVP (today)
• Local proxy + SDK
• GPT + Claude connectors
• Design partner pilots
Phase 2 (3–6 months)
• Hosted proxy (AWS/GCP/Azure)
• Multi-tenant infra
• OAuth + advanced auth handling
• Gemini + Azure Copilot support
Phase 3 (12–18 months)
• Auto-registration
• Normalization at scale
• Drift detection + monitoring
• Compliance, reliability, uptime SLAs
⸻
Design Partner Program
We’re onboarding a small group of SaaS design partners to shape Kalibr.
Design partners get:
• Early SDK access
• Forward-deployed engineering support
• Roadmap influence
• Preferred pricing
📩 Contact: hello@kalibr.systems
This is clean, Markdown-friendly, and looks normal to a developer.
Want me to also scaffold an **`examples/` folder with one Airtable example** so it looks even more real on GitHub, or do you want to keep it super minimal for now?
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-0.1.0.tar.gz
(6.6 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file kalibr-0.1.0.tar.gz.
File metadata
- Download URL: kalibr-0.1.0.tar.gz
- Upload date:
- Size: 6.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8c11f5d458ab91d82ada07f539dc1f88fd7920c1ac3f83bff9f1d5dbb03ad386
|
|
| MD5 |
6e8e3b9139e1324df73093ce2f6b0e29
|
|
| BLAKE2b-256 |
6070747ed039b4a0d78d588c07de27e7f5818d63279a0864b0f01a3507e19c47
|
File details
Details for the file kalibr-0.1.0-py3-none-any.whl.
File metadata
- Download URL: kalibr-0.1.0-py3-none-any.whl
- Upload date:
- Size: 8.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cae532310a1d9efd5c547c45d302207ae129a155f8176a895450e62adeb7b0b0
|
|
| MD5 |
dd70983dd0fb5a04ff0efa310748b155
|
|
| BLAKE2b-256 |
7916ba2d0ade13c42a89a4b1425aa76ddb22cdaf95bdfa8ccef9825ce06ff3e1
|