Slipstream

Semantic quantization for multi-agent AI coordination.

Slipstream encodes coordination messages as compact Force+Object intents:

SLIP v3 <src> <dst> <Force> <Object> [payload...]

Typical JSON coordination messages (~40+ tokens) compress to ~6-8 wire tokens.

Start Here

• Quick adoption guide
• LangGraph integration guide
• SDK reference
• v3.0 -> v3.1 migration notes
• Protocol invariants
• Canonical paper source (v3.1 markdown)

Install

pip install slipcore

Quick Start

from slipcore import format_slip, parse_slip, quantize, render_human

# Direct formatting
wire = format_slip("alice", "bob", "Request", "Review", ["auth"])
assert wire == "SLIP v3 alice bob Request Review auth"

# Think -> Quantize -> Transmit helper
wire2 = quantize(
    "Please review the authentication code",
    src="dev",
    dst="reviewer",
)

msg = parse_slip(wire)
print(msg.force, msg.obj, msg.payload)
print(render_human(msg))

Strict Fallback Rules (v3.1.0)

Fallback messages are now strict:

• Fallback messages must include a ref token.
• Ref token must be alphanumeric and 1-16 chars.
• Use parse_slip_legacy() only for explicit migration of old permissive wires.

from slipcore import format_fallback, parse_slip_legacy

wire = format_fallback("qa", "planner", "ref7f3a")
legacy = parse_slip_legacy("SLIP v3 qa planner Fallback Generic")
assert legacy.fallback_ref == "reflegacy"

Force Vocabulary (Closed, 12)

Observe, Inform, Ask, Request, Propose, Commit, Eval, Meta, Accept, Reject, Error, Fallback

Ecosystem

• Model: anthonym21/slipstream-glm-z1-9b
• Dataset: anthonym21/slipstream-tqt
• A2A transport extension: extensions/a2a-slipstream/v1

Governance

• Contributing
• Code of Conduct
• Security Policy
• Project Governance
• Maintainers

Citation

@misc{maio2025slipstream,
  title={Slipstream: Semantic Quantization for Efficient Multi-Agent Coordination},
  author={Maio, Anthony},
  year={2025},
  url={https://github.com/anthony-maio/slipcore}
}

License

Apache 2.0.