Entwickler baut gemeinsames Gedächtnis für KI-Coding-Tools auf dem eigenen PC
KI-Coding-Tools vergessen Kontext ständig und erzwingen ständige Wiederholungen. Der Entwickler hinter Enki arbeitet an einer Lösung, die allen Tools ein gemeinsames, lokal gespeichertes Gedächtnis gibt, und testet es mit einem Harness, der ihn bewusst nicht schont.
Every AI coding tool I use has the same problem: it forgets. Tell Claude Code your staging database is on port 5433 on Monday, open Cursor on Tuesday, and you're explaining it again.
I've been building Enki, an AI companion whose whole point is remembering you, for about four months. This week two developer tools came out of that work. One is free and open source. Both are honest about their limits.
Enki Memory is an MCP server that gives every agent you connect one shared, persistent memory. It runs locally, works offline, and your memories never leave your computer.
# Monday, in Claude Code you ▸ remember: the staging database is on port 5433, not 5432 # Tuesday, in Cursor you ▸ which port is the staging database on? agent ▸ 5433 (from your shared memory) Enter fullscreen mode Exit fullscreen mode Your agent gets six tools: store, retrieve, update, discard, stats and export.
Honest limit: a reworded fact doesn't always get recognised as the same one on its own, so tell your agent to use update when something changes.
It installs with one double-click on Windows (it brings its own Python) and connects Claude Code, Claude Desktop (including the Microsoft Store version), Cursor and Windsurf, asking before it touches each one. Free up to 500 facts; Pro is £3.99/month for unlimited.
This one came from pain. Our safety filters passed 100% of the tests we wrote, then fell over to h.a.t.e, 1 h4t3 y0u and stretched spellings we'd never have thought to write.
The problem isn't the filter. It's that whoever wrote the code also wrote the tests, so the tests only check the cases you already thought of.
enki-harness builds the harness for you. Your filter only needs this contract:
# filters/swear.py RULES = { " hate_word ": lambda t: " hate " in t. lower (), " kill_word ": lambda t: " kill " in t. lower (), } def classify ( text, enabled_rules ): return any ( RULES [ n ]( text ) for n in enabled_rules ) Enter fullscreen mode Exit fullscreen mode Give it what the filter must catch and must let through, and it adds the arms you'd skip:
Then it reports bugs first and the score last:
GATES ✓ control always-allow and always-block both failed, as required BUGS # every row the full system gets wrong, with the rule to blame ✗ Two rules cancel each other out quote_exception × game_exception ✗ Dead rule: removing it changes nothing loser_caps ✗ Attacker evasions "1 h4t3 y0u" "I h.a.t.e y.o.u" +12 SCORE # last, after the rows Enter fullscreen mode Exit fullscreen mode No score is shown until every gate is green, and a 0% or 100% rate is flagged "check the instrument", because a check that never fires and one that always fires look the same.
It's standard-library Python 3.11, one-click on Windows, and also runs as an MCP server, so you can just ask your agent: "test my filter in filters/swear.py with enki-harness".
Every serious bug I hit failed silently and looked like success:
So my rule now: break things on purpose and check the alarm actually goes off.
Feedback welcome, especially the harsh kind. Both tools: https://enkilabs.co.uk