Show HN: DecisionNode – shared structured memory for all AI coding tools via MCP (github.com)

interesting but why not just use memory.md / CLAUDE.md?

Why only gemini embeddings?

[dead]

[flagged]

[dead]

How does this handle context that becomes stale? E.g., if one tool updates a deployment state and another tool's memory still has the old version. MCP gives you the pipe but not the consistency model.