Multiple agents, one source of truth: a Planner/Coder/Reviewer demo of how a shared Statewave subject prevents parallel-agent context collisions.
-
Updated
Jul 28, 2026 - Python
Multiple agents, one source of truth: a Planner/Coder/Reviewer demo of how a shared Statewave subject prevents parallel-agent context collisions.
MCP server for shared context caching — AI agents share computed results to reduce token cost and latency
This component is an rpc accessible service to a shared context inside of a distributed system
Shared context and memory coordination layer for swarms of parallel AI agents. Documented HTTP + WebSocket protocol, interoperable Python and Node CLIs, BM25 keyword memory search, built-in MCP server for agent tool calls.
Add a description, image, and links to the shared-context topic page so that developers can more easily learn about it.
To associate your repository with the shared-context topic, visit your repo's landing page and select "manage topics."