jevmory
Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies.
How it uses Jev
Local, zero-dependency memory layer for coding agents. Every remembered fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence — and every number has a receipt.
Highlights
- 🎯 Verbatim facts, zero generation — no LLM generation anywhere.
- 🔌 Agent-agnostic — a one-command Claude Code plugin, an MCP
- 🛡️ Local by architecture — Python 3 stdlib only, per-project
- 📄 Receipts for everything — raw judgments and usage are stored
Getting started
Requires Python ≥3.10 and nothing else — stdlib only, no pip deps.
- Languages
- Python 100% · Shell 1%
- License
- MIT
- Latest release
- v0.3.0 — plug-and-play: Claude Code plugin, MCP server, session-start recall
- Last activity
- Sep 2026
- Added
- 2026-09-22
- Stars at snapshot
- 9
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.