Back to directory

jevmem

A tool that automatically saves decisions, constraints, bugs and todos from Claude Code chats into a JEVMEM.md file, then feeds the relevant lines back into context in later sessions.

jevmem

When a decision changes, jevmem marks the old line as superseded rather than deleting it, and a memory-poisoning check screens any line not written by jevmem on the local machine -- a teammate's edit, a pull request, or a hand edit -- before it enters Claude's context; in the project's own 44-line test set this blocked 20 of 22 planted bad lines with no false blocks on legitimate rules.

It installs as an opt-in Claude Code plugin that does nothing until enabled per project, saves in the background so Claude does not wait on it, and by default calls no external language model to write lines unless a separate writer model is explicitly configured. It can import an existing CLAUDE.md, AGENTS.md or Cursor rules file, also works with Cursor and Codex, and requires a TypeSafe AI key; it is licensed MIT and written in TypeScript.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.