skillmem.
by Liza Studio
Memory for AI agents

Self-improving skills for Claude Code.

Your agent learns, recalls, reinforces — and forgets what stops working.

01

Zero-cost writes

No LLM calls to store or retrieve a skill. Fully local — your memory never leaves the machine, and it costs $0 to use.

02

Bilingual hybrid search

Lexical FTS plus a local semantic layer. Write in one language, recall in another — it just finds the skill.

03

Ebbinghaus decay + reinforcement

Skills that help get stronger. Skills that sit unused fade out — the memory curates itself, like yours does.

04

Tamper-evident history

Every change is chained with SHA-256. You can prove what your agent learned, when, and that nobody rewrote it.

Open source soon — Apache-2.0

The full engine — learn, recall, reinforce, decay — ships as open source. Star it the day it lands.

github.com/liza-studio/skillmem →

skillmem cloud: sync your agent's skills across machines and share them with your team.

Join the waitlist — early access goes out in order of signup.

One email when cloud opens. No spam, no sharing.