GoKawiilJevmem launches as automatic memory tool for Claude Code, Cursor, Codex
Jevmem is a new npm package that captures decisions, constraints, bugs and todos discussed during AI coding sessions and writes them to a local JEVMEM.md file. Changed decisions are marked as superseded rather than erased, and the relevant entries are re-fed into the assistant's context in later sessions. It integrates automatically with Claude Code via hooks, while Cursor and Codex require agent-initiated calls through MCP or rule files.
GoKawiil's interpretation of the reporting above, not reported fact.
Persistent memory addresses a common pain point in AI-assisted coding: context loss between sessions, which forces developers to repeat project constraints and past decisions. By logging history with timestamps and confidence scores rather than deleting outdated entries, the tool could help teams audit how technical decisions evolved over time. Its varying levels of automation across tools suggests broader adoption may depend on how well each AI coding assistant supports hook-based or MCP-based integrations.
- Jevmem automatically saves project decisions, constraints and bugs to a JEVMEM.md file during Claude Code sessions.
- Superseded decisions are marked rather than deleted, preserving a history of changed reasoning.
- Support varies by tool: Claude Code offers full automation, while Cursor and Codex rely more on agent-initiated memory calls.
Source: github.com, 2026-09-25
Published there as: “Jevmem – automatic project memory for Claude Code, built on Jev”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.