Back to benchmarks & research
jevmory project preview
Benchmarks & research

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
agent-memorycalibrated-confidenceclicoding-agentpythonsqlite

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Listed in Jev Library

If this is your project, the badge below links back to this page. Paste it near the top of your README.

[![Listed in Jev Library](https://jevlibrary.dev/api/badge/romiluz13-jevmory)](https://jevlibrary.dev/projects/romiluz13-jevmory)

Something wrong on this page, or would you rather not be listed? Tell us and it will be changed.