Published protocol SDK
Slipstream
Give agent coordination a compact, explicit message format.
Encode bounded coordination intents with a shared vocabulary, parse them at the receiver, and fall back when an intent needs more context. The Python SDK makes the protocol available without loading a language model.
What you can do with it
Who it's for: Engineers building a controlled message channel between cooperating agents.
A formatted message that the receiver can parse into its sender, recipient, intent, and payload.
Your first useful result
Install in your development environment
pip install slipcore- 01
Format and parse one message
Save this as a Python script and run it with Python. It checks the SDK wire format without model inference.
from slipcore import format_slip, parse_slip wire = format_slip("planner", "executor", "Request", "Task", ["auth"]) msg = parse_slip(wire) assert msg.wire == wire assert msg.force == "Request" assert msg.obj == "Task" print(wire) - 02
Keep a fallback path
Run this in Python. Retain the full original message behind the reference when the shared vocabulary cannot express it safely.
from slipcore import format_fallback wire = format_fallback("qa", "planner", "ref7f3a") print(wire) - 03
Measure one real workflow
Compare the original and wire messages using your model tokenizer. Check task success and missing information alongside token counts before expanding usage.
Know the limits
- Compact intents do not preserve arbitrary prose automatically. Payload, routing, and fallback behavior remain application responsibilities.
- Token savings depend on your tokenizer, message mix, and retained context. A preset illustration is not a measured deployment result.