mempalace

MemPalace (techempower-org fork)

TechEmpower's production fork of MemPalace/mempalace (transferred from jphein/mempalace in May 2026)

[!CAUTION]

🚨 CRITICAL SECURITY WARNING: BEWARE OF SCAMS (upstream notice)

MemPalace has NO other official websites.

The ONLY official sources are:

1. The upstream GitHub repository and this fork's GitHub repository
2. The PyPI package
3. The docs at mempalaceofficial.com

ANY other domain (including .tech, .net, or other .com variants) is an impostor and may distribute malware. Do not download executables from untrusted sites. Details and timeline: docs/HISTORY.md.

[!IMPORTANT] 🚨 Claude Code sessions expire in 30 days w/out auto-save hooks wired! Read this →

Need the shortest recovery/setup path? Use the Claude Code retention setup checklist.

What this is

A verbatim-first local AI memory system. This fork tracks upstream/develop through the post-v3.5.0 sync (2026-07-02, commit da5a48c) and runs in production on a 411K+ drawer Postgres + pgvector + Apache AGE palace behind palace-daemon. It carries fork-ahead commits that compose with — not replace — bensig's release direction; the v3.3.5 release (2026-05-10) includes our co-authored _get_collection retry-once via upstream #1377. 4929 tests pass on main.

The fork's architectural thinking — the four-layer memory model, the verbatim-vs-derivative thesis, design principles, and the two-memory-layer pairing with Auto Dream — lives in docs/ARCHITECTURE.md. The new things here are what we've learned, not just what we've fixed.

Why this fork exists

We surveyed the memory-system landscape in April 2026 and found no verbatim-first local system with MCP. The landscape has since fragmented — MCP memory servers proliferated in May 2026 — but the verbatim-vs-derivative axis remains the clearest architectural dividing line. Updated survey as of 2026-05-24:

Verbatim-first systems