StackMap
Subscribe
Explore / deja-vu
vshulcz

deja-vu

Indexes the session histories your coding agents already wrote — 17 harnesses, months retroactive — and serves recall over MCP. 84.9% hit@1 on LongMemEval-S, no LLM, no embeddings. One Go binary.

556 40 Go MITupdated today
View on GitHubDispute this mapping →
Curator's take

The inversion is the insight: every memory tool starts empty and records forward; deja starts FULL from history already on disk, and the no-LLM/no-embedding design means ~1.5ms search, zero keys, zero cost. When NOT: it remembers what your agents did, not curated knowledge — there's no write path for distilled lessons; and its benchmark numbers are self-published, so the standing caution on this shelf applies: benchmark recall on your own corpus.

Mapped by ShipWithAI editors · links verified
README.md

deja-vu

Your agents already solved this. deja finds it.
Memory tools start empty and record forward. deja starts full: it indexes the sessions your coding agents already wrote to disk — months of history from before you installed it — searches 3.5 GB in ~1.5 ms, serves it back to any agent over MCP, and moves with you between machines over SSH. One zero-dependency binary, fully local.

84.9% hit@1 on LongMemEval-S retrieval — no LLM, no embeddings, no API key. Harness in-repo, run it yourself.

vshulcz.github.io/deja-vu · how deja compares

CI Release npm OpenSSF Scorecard MCP Toplist MIT License

The same question asked twice in Claude Code: without deja the agent has no record of it, with deja it answers with the decision from eight months earlier

Every line is quoted from two real Claude Code sessions — the same question, the same agent, once without memory and once with deja. Nobody searched anything: the agent called deja itself.

84.9% hit@1 on LongMemEval-S · 69.8% on LoCoMo · zero LLM calls, zero embeddings, zero API keys · ~1.5 ms median search over 3.5 GB
Both harnesses ship in this repo and run on the public datasets in minutes — check the numbers yourself.

Install

curl -fsSL https://raw.githubusercontent.com/vshulcz/deja-vu/main/install.sh | sh

or:

go install github.com/vshulcz/deja-vu/cmd/deja@latest   # Go
npx @vshulcz/deja-vu "query"                            # npm, no install
brew install vshulcz/tap/deja-vu                        # Homebrew

For desktop apps that install MCP servers as bundles, every release ships an .mcpb per platform — download it from the latest release and open it. The bundle carries the binary, so there is nothing else to install. Terminal agents use deja install below instead.

Shell completion

deja completion bash >> ~/.bashrc
deja completion zsh >> ~/.zshrc
deja completion fish > ~/.config/fish/completions/deja.fish

Wire it into the agents you use (edits config, keeps a .bak):

deja install --all     # MCP recall for every agent it finds on this machine
deja install --auto    # same, plus session-start auto-recall where supported

Install also builds the index from the histories it finds, so the first agent session after it is instant rather than paying for the build. --no-index skips that for scripted installs; running deja with nothing indexed builds it too.

Claude Code

Continue your stack

What teams reach for next — and why each earns a place beside deja-vu. Ranked by curator confidence.