Locamem is local-first memory for AI agents. Your agent's whole memory is one SQLite file on your disk — no servers, no API keys, no context shipped to anyone. You own the file: read it, copy it, diff it, delete it. Retrieval runs on-device in under 10ms with zero network calls and zero per-recall cost.
Agents should remember without giving up control of what they remember. So we built memory as a single local file. SimHash (LSH) for candidate matching, FTS5 for full-text, optional on-device embeddingsfor meaning — all running against one SQLite database that lives on your machine. Every result returns a per-facet score breakdown, so a recall is something you can audit, not a black box you have to trust. Local-first isn't a deployment option for us. It's the design.
Agents are stateless. Every session starts from zero, so the obvious fix is to bolt on a memory layer. Today that almost always means a cloud service: your agent's context gets shipped to someone else's database, indexed on their hardware, and billed back to you per recall. You inherit their retention caps, their pricing tiers, their outages, and their answer to the only question that matters: who can read your agent's memory?For legal, healthcare, and finance teams, "it's in a vendor's cloud" isn't an answer they can ship.
Our betThe best memory is the one that never leaves the box. We're betting that two things win over opaque, metered vector stores: transparency and temporal truth. Transparency means every recall comes with its own scorecard — you see exactly why a result ranked where it did, per facet. Temporal truth means memory tracks validity over time and detects contradictions instead of silently overwriting; Locamem never deletes, so you can ask not just what the agent knows but what it knew, and when.
Locamem is built by Team Wilcoe — the team behind wilcoe.com. Our goal is to develop practical solutions in two directions at once: the tools and systems we run internally to do our own work, and the solutions we build and deploy for our clients. The best of those cross over — something we built to solve our own problem becomes something we can stand behind for everyone else.
Agent memory, automation, and tooling we depend on every day. The rule is simple: if we won't run it in our own stack, we won't ship it to anyone else.
The same systems, deployed into real client environments — often where sensitive data can't leave the building. Working under that constraint is exactly what shaped Locamem.
Locamem is that crossover. We needed AI agents that could remember across sessions withouthanding a client's context to a third party — so we built memory that never leaves the box, and we run it ourselves. For work that spans sensitive, regulated environments, "local-first" isn't a slogan; it's the only way to put agent memory into production responsibly.
So we open-sourced the engine under MIT and kept the model honest: we monetize support, optional self-hostable sync, and hands-on deployment — never your memory. The code is on GitHub at github.com/TeamWilcoe/locamem. Whether you want to run it yourself or have us deploy and support it for your team — team@wilcoe.com.