deja-vu

Memory for coding agents, starting with the history you already have.

Your agent is about to re-debug something you fixed in March. deja indexes the sessions Claude Code, Codex, Cursor and every other agent on this machine already wrote to disk, and hands the right one back when it is needed.

_{Nobody searched anything — the agent called deja itself. Every line is quoted from two real sessions.}

Every memory tool starts empty and records forward. deja starts full.

85.3% hit@1 on LongMemEval-S · 69.6% on LoCoMo · sub-millisecond lookups over 5 GB of history
_{Both harnesses ship in this repo and run on the public datasets in minutes · check the numbers yourself}

English | 中文

Docs · Benchmarks · How it compares

Install

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

Ten seconds to install, about ten to index, and it is useful. The second command wires MCP recall into every agent it finds, turns on session-start recall where the agent supports it, and builds the first index so the next session does not pay for it.

Start a new agent session and ask it something you worked on months ago:

have we dealt with jwt refresh rotation before? check your memory

It does not have to be asked, either — with auto-recall the agent already knows what you solved in that project when the session opens.

claude plugin marketplace add vshulcz/deja-vu && claude plugin install deja-vu@deja-vu

What you get

Solve it in Codex. Claude remembers. Twenty coding agents write every conversation to local files, and deja turns those files into one memory layer all of them read.

Your own work, wrapped

deja stats --card draws it in the terminal; give it a filename and it writes an SVG for a profile README.

The full feature reference lives in the docs.

Privacy

Indexing and search are local. The network is used only by deja update, deja sync ssh, and the version check in deja doctor.

Credentials are redacted at index time: AWS keys, api_key= and token= assignments, bearer tokens and raw JWTs, PEM private key blocks, provider tokens, scheme://user:pass@host URLs, and high-entropy values for shapes no pattern knows. The value becomes [redacted:<kind>] and the surrounding text stays searchable. deja share and deja sync export re-apply redaction on the way out.

deja forget removes sessions from a rebuilt index and writes tombstones, so a later deja index cannot restore them from the source history. --unforget lifts a tombstone. Project exclusions are one pattern per line in ~/.config/deja/exclude.

The security model documents data flows, redaction limits, trust assumptions and release verification.

CLI

$ deja "jwt refresh token"
[claude] api        · Jul 8 · 8f31c0a9 — 2 matches
  login started failing after refresh token rotation; jwt kid mismatch in tests
  fixed by reloading jwks cache after rotateKey and adding a clock-skew test
[codex]  web        · Jul 1 · b77d91e2 — 1 match
  refresh token cookie needed SameSite=Lax in local callback flow

Ask your history

Full reference: commands and JSON output.

MCP tools

The server exposes recall, recall_context, blame, fix, how and remember. deja install wires them in, so this is only needed to configure an agent by hand.

Supported harnesses

Claude Code · Cline · Codex CLI · opencode · aider · Gemini CLI · Cursor · Antigravity · Grok Build · Hermes · Goose · Qwen Code · Kimi Code · pi · omp (Oh My Pi) · OpenClaw · Copilot CLI · Roo Code · DeepSeek Harness · Zed.

Custom store locations go through DEJA_*_ROOT variables, and each agent's own relocation variable is honored too. The session format registry documents the observed paths, record schemas and role mapping per harness, with synthetic fixtures keeping those descriptions checked against the parsers.

Harnesses with a package of their own

deja install --auto wires all five of these like every other harness, and that stays the shortest path. They also have a package in their own ecosystem, for people who install extensions there rather than from a CLI:

Either path is enough on its own, and having both is not a problem: the opencode, dsh, Kimi and Codex packages read what deja install wrote and contribute only what is missing, and in Zed both halves use one server id, so there is nothing to have twice whichever order you install in.

Each uses the deja you already have; the copy it bundles is only the fallback.

Semantic recall (optional)

Point deja embed at a local Ollama, LM Studio or OpenAI-compatible endpoint with DEJA_EMBED_URL and rephrased queries still hit. Without a reachable runtime, lexical search and MCP recall continue unchanged.

Proof

deja bench recall     # ranking regression floor, CI fails if recall drops
deja bench context    # 30 seeded task chains plus five negative controls

The context experiment compares deja-recall against full-history, naive grep and cold context. With the default seed:

Same fact coverage as grepping the raw logs for about 200x fewer tokens, and about 60x fewer than replaying the matched sessions in full, while injecting nothing on the chains where no prior fact is relevant. The corpus generator and the relevance labels are ordinary reviewed Go. Audit what "relevant" means before trusting any figure, ours included.

Measured on a real store of 1,551 sessions and 143k messages — 5.2 GB across nine harnesses:

The index is incremental. When a session file grows, only that file is re-read.

How it works

Local inverted index in ~/.cache/deja: parse the JSONL and SQLite stores, redact credentials, write records.bin plus token buckets, and track per-file state in manifest.gob so repeat runs only ingest what changed. The MCP server, stats, share and sync all read that one index. Details in docs/ARCHITECTURE.md.

FAQ

Does anything leave my machine? No, unless you ask it to. See the data flows.

What about secrets already in my logs? They stay in the original harness files, which are your agent's data. They do not enter deja's index, digests, shares or sync exports.

Will it slow my agent down? A recall is a lexical lookup against a local index: ~0.4 ms median, and nothing waits on a model. A hook adds the process start and a freshness check over your stores on top of that — tens of milliseconds on a store of a few gigabytes.

Do I have to change how I work? No. The agent calls recall itself, and with auto-recall it already knows the project's prior decisions when the session opens.

How is this different from the other memory tools?

engram is the strongest of the record-forward tools and worth your time if that model fits you; it still starts empty and knows only what an agent chose to save. The full comparison covers eleven of them.

What about Windows? Builds exist and CI runs the suite there. macOS and Linux are the battle-tested paths. Field reports welcome in #9.

How do I wipe everything?

deja uninstall --all
rm -rf ~/.cache/deja

Try it on your own history

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

Ten seconds to install, about ten to index. The next session your agent opens, it already knows what you solved in that project — including everything from before you installed this.

Contributing

make build test lint, then CONTRIBUTING.md. Adding a harness starts in the parser registry. Priorities and non-goals are in ROADMAP.md. Good first issues are labeled.

License

MIT © Vladislav Shulcz