ctx-memory
Rank #18894glama/GhadiSaab/ctx-memory
A fully local persistent memory layer for LLM coding agents (Claude Code, Codex, Gemini CLI, OpenCode). A shell wrapper intercepts tool invocations, fires hooks on every tool call, then runs a 3-layer pipeline (extract → compress to ≤500-token digest → merge into project memory doc) at session end. The next session gets prior context injected automatically.
ctx-memory is a Model Context Protocol (MCP) server published by GhadiSaab. It ranks #18894 of 58,832 servers tracked on MCP Toplist. ctx-memory is listed on Glama, and ships as a single rolling release with no explicit version metadata. It was first listed on Apr 27, 2026.
Ranks ahead of 39,938 of 58,832 servers on MCP Toplist.
Use ctx-memory
ctx-memory doesn’t publish a machine-readable install config. Follow the setup instructions in its repository ↗, or open one of its registry listings above.
Listed on 1 registry
GhadiSaab
Not versioned
This server is published through a registry that does not expose explicit version metadata. The listing tracks a single rolling release.
Frequently asked questions
- What is ctx-memory?
- A fully local persistent memory layer for LLM coding agents (Claude Code, Codex, Gemini CLI, OpenCode). A shell wrapper intercepts tool invocations, fires hooks on every tool call, then runs a 3-layer pipeline (extract → compress to ≤500-token digest → merge into project memory doc) at session end. The next session gets prior context injected automatically.
- Who maintains ctx-memory?
- ctx-memory is maintained by GhadiSaab, which publishes 1 MCP server (0 total versions) tracked on MCP Toplist.
- Is ctx-memory an official MCP server?
- ctx-memory is not on the Official MCP Registry. It is listed on Glama.
- How many versions does ctx-memory have?
- ctx-memory ships as a single rolling release with no explicit version metadata.
- Where can I find the source code for ctx-memory?
- The source code for ctx-memory is hosted at github.com/GhadiSaab/ctx-memory.