Skip to content

Latest commit

 

History

History
43 lines (28 loc) · 1.76 KB

File metadata and controls

43 lines (28 loc) · 1.76 KB

ACCP — Elevator Pitch

Version 1.0

Core Pitch

ACCP gives agentic harness developers a drop-in compression layer for agent-to-agent communication that cuts token usage dramatically without forcing them to redesign their transport, routing, or tool stack.

Instead of sending verbose natural language or bloated JSON between agents, a harness can encode those messages into compact, structured ACCP frames, keep long history in tiered state, and inject only the minimum necessary context back into the model.

That means:

  • lower inference cost
  • longer multi-agent workflows before context windows fill up
  • more agents per workflow
  • less repeated prompt and state overhead
  • better control over what actually reaches the model

Why It Matters to Harness Developers

Harness developers already control the orchestration layer:

  • inter-agent message passing
  • state and memory management
  • tool response injection
  • adapter points for MCP, A2A, Semantic Kernel, LangGraph, and similar systems

ACCP fits directly into that layer. It does not replace transport, routing, or model APIs — it makes them cheaper and more efficient.

Short Spoken Version

“ACCP is a protocol layer for agentic frameworks that makes inter-agent communication token-efficient. It lets harnesses compress messages, checkpoint context, and reference shared state so developers can run deeper, cheaper, more scalable multi-agent workflows without changing their underlying transport.”

One-Line Tagline

“ACCP is semantic compression for multi-agent systems.”

Alternate Tagline

“ACCP is gzip for agent context — but semantic, structured, and built for multi-agent harnesses.”


Status: APPROVED
Document Owner: Project Lead / Architect
Created: April 2026