Skip to content
Memoturn
private beta

Real-time AI memory your coding agents share.

Cross-tool memory for Claude Code, Cursor, Codex, and Copilot. Hybrid search + rolling summaries + symbol-aware lookup, on Cloudflare's edge.

SDK + CLI
Apache-2.0 SDK + CLI
Protocol
MCP-native
Runtime
Runs on Cloudflare's edge
works with
  • Claude Code
  • Cursor
  • Codex CLI
  • VS Code Copilot
via MCP

why memoturn

Your agents shouldn't be amnesiacs. Memory belongs to the project, not the tool.

Today each coding agent keeps its own private context, so the work resets every session and never crosses tools. Memoturn inverts that: one shared substrate per project, written and read over MCP — the same memory whether the next turn comes from Claude Code, Cursor, Codex, or the CLI.

what you get

Three legs. One substrate. Auditable end to end.

Each leg is named, instrumented, and inspectable. The page surfaces which leg matched and why — the search isn't a black box.

real-time

Every turn, captured live

Durable Objects fan turns out over WebSockets the moment they land. No polling, no batching, no replay gaps.

Durable ObjectsWebSocket

cross-tool

One memory, every IDE

MCP-native. Connect Claude Code, Cursor, Codex CLI, and VS Code Copilot to the same project — context follows the work, not the tool.

MCPstdio + http

hybrid search

Dense + lexical + hot

Vectorize embeddings, Postgres FTS, and a recency-biased hot leg, fused with RRF. See exactly which leg matched, every time.

VectorizePostgres FTSRRF

ready when you are

Stop re-explaining your codebase to every agent.

Hosted on Cloudflare's edge. Sign up at api.memoturn.ai in seconds.