the lab · open source · mit

stoprentingyourmind.

your ai's memory is either proven or it's prayed for. homestead-memory is a local, verifiable memory layer for ai agents: plain markdown you own, retrieval that works offline, and a gate that proves the memory hasn't rotted. every other memory tool asks you to hope it remembers. this one shows receipts.

get it on github → read the story
watch it catch its own rot

memory intact. until it isn't.

that's the real cli. hsm verify exits nonzero on rot, so it gates your ci and your cron like a test suite. run it yourself in 60 seconds: pip install homestead-memory

what it stands on

three commitments. zero black boxes.

markdown you own

the memory is plain files on your disk. open them, read them, git diff them, leave any time. indexes are derived and disposable. it's your folder.

verification over trust

memory rots quietly: notes contradict themselves, sources vanish, stale values shadow current ones. hsm verify scores integrity 0 to 100 and exits nonzero on rot. it gates ci like a test suite.

extraction you can audit

the optional distilled layer extracts facts with verbatim quotes, checked in code. a claim either cites a real source or gets dropped. contradictions append a changelog line, never a silent overwrite.

the culture is turning

we've been saying this for a month. now they are too.

the week we shipped this, the biggest podcast in tech spent thirty minutes on the same idea: stop handing your data and your edge to a frontier lab that can turn around and compete with you. all-in, ep 279.

"data retention is your treasure. transfer it at your own peril."
palantir manifesto, read on all-in #279
"why would you ever share proprietary data with them? you are mortgaging your future."
david sacks, all-in #279

they're describing the fortune-500 version: on-prem clusters, a server per employee, roll your own model. homestead-memory is the one you run on your laptop tonight. your memory, kept local, plain markdown you own, and it proves it hasn't rotted. free, and mit.

and the labs that host your model will happily ship the product that competes with you. ask figma. ask cursor. use claude code all you want. just don't hand it your memory.

honest numbers

benchmarked. receipts included.

cloud memory bills you per turn, forever. this is $0 to write, and it's a folder you already own.

85%
retrieval recall@k

did the memory surface the right evidence? measured on the full 500-question LongMemEval set, 48-session haystacks with distractors.

52.8%
qa accuracy

official per-type judge methodology. honest and mid: others self-report higher on harnesses you can't run. ours you can.

~5.2k
context tokens / query

the cost axis. verbatim memory with $0 write-time cost.

99.4 / 100
rotbench

the integrity score nobody else publishes. mechanical checks, no llm judging its own homework.

every number above comes from a harness you can run yourself, judged with the official LongMemEval methodology. we publish our failures too: a lab whose valuation depends on looking infallible structurally can't do that. we can, so we do. the full run history is public.

get it running

sixty seconds. your machine.

the cli

pip install homestead-memory

hsm init   ./my-vault
hsm ingest ./my-vault
hsm ask    "what did i decide about x?"
hsm verify ./my-vault

claude code · cursor · desktop

claude mcp add homestead-memory \
  -- hsm mcp ~/my-vault

six mcp tools: ask, search, verify, history, ingest, distill. your agent gets a memory it can prove.

break it. we dare you.

rotbench is an open spec

the integrity score is only credible if it survives adversaries. build a memory store that's obviously rotten but scores intact, or an intact one that false-positives, and we merge your fixture and fix the check. the scoreboard of merged breaks lives in the repo. trust you can inspect, and break, is the one thing a duopoly can't ship.

read the spec →