memorylocalsearchsshcoding-agents
Local memory layer indexing coding agent session histories for fast recall and cross-machine sync over SSH.
Quick Install
Automated & IDE SetupCopy the AI prompt to install this server into Claude Code, Cursor, or another agent ā or use 1-click editor setup below.
We couldnāt automatically confirm this listing starts correctly
We ran the install command below but it didn't respond within our test window ā this can mean a slow first-time install rather than a real problem.
npx -y @vshulcz/deja-vuNo response to initialize.
This is an experimental automated check and can have false negatives ā missing environment variables, a slow cold install, etc. It doesnāt necessarily mean somethingās wrong. Last checked 1mo ago.
Manual Client & Custom JSON ConfigExpand JSON ā¾
Client Config & Setup
Choose your client or environment
Target File:
š” Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Overview
Use cases
Index past coding agent session histories for recall
Search large volumes of local session data in milliseconds
Enable session-start auto-recall in compatible agents
Synchronize memory data across multiple machines via SSH
Redact secrets automatically during indexing
Key features
Zero-dependency single binary, fully local operation
Search 3.5 GB of session history in ~1.5 ms
Supports multiple coding agents via MCP protocol
Cross-machine synchronization over SSH
Secret redaction at index time
No LLM calls, embeddings, or API keys required
Capabilities & Tool Schemas (1)
Inspect callable tools, capabilities, and parameters exposed to AI agents by Deja Vu.
dejaDepends on the mode, below.
Documentation Overview
The one memory your coding agents share, built from the history already on your disk.
Your agent is about to re-debug something you fixed in March ā in a different agent. 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 in whichever agent asks.
Nobody searched anything ā the agent called deja itself. Every line is quoted from two real sessions.
Every memory tool starts empty and records forward. deja starts full.
And nobody has to ask for it: recall arrives at session start, on every prompt, before a file is edited or a command runs, and after one fails. Keys and tokens are stripped as the index is built, so what reaches the model is safe to send.
85.3% hit@1 on LongMemEval-S Ā· 69.6% on LoCoMo Ā· millisecond lookups over 5Ā GB of history
Both harnesses ship in this repo and run on the public datasets in minutes Ā·
check the numbers yourself
English | äøę
Docs Ā· Benchmarks Ā· How it compares
Install
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 ā with auto-recall the agent already knows what you solved in that project when the session opens.
Other ways to install, and what to do if you want less than all of it
brew install deja-vu, go install github.com/vshulcz/deja-vu/cmd/deja@latest,
or npx @vshulcz/deja-vu "query" to try it without installing anything. Desktop apps that
take MCP servers as bundles can open the .mcpb from the
latest release; it carries the binary.
Claude Code, Codex, Cursor, Qwen, OpenClaw and Copilot can take the same plugin bundle from their own marketplaces instead:
On Windows the install script exits with unsupported OS ā it is a shell script. Use
Scoop instead, from the main bucket every Scoop install already has:
Or take deja-vu_<version>_windows_amd64.zip from the
latest release and put deja.exe on
your PATH, e.g. in %USERPROFILE%\.local\bin.
The binary alone is a complete install for searching: index, search, show, ctx, blame,
--json and redaction need nothing else. deja install is what wires MCP into your agents
and turns on session-start recall ā worth having, and optional. On a binary-only setup
deja doctor reports every MCP target as not-wired, which is that setup working as
intended. deja warmup also leaves a skill at ~/.agents/skills/deja-search/SKILL.md
that teaches an agent the CLI contract ā deja search --json, ctx, blame, how to read
tier and total ā so it knows history is searchable without MCP. The copy in the repo is
skills/deja-search/SKILL.md.
deja install --all is --auto without the session-start recall: agents answer from memory
when they decide to call it, rather than starting each session with it. The
agent setup guide covers what each
harness supports, aider's read-only context file, and the Windows cmd /c deja mcp wrapper.
What gets written into each agent's own guidance file
Install also writes user-level guidance for the harnesses it detects: Claude Code, Codex, opencode, Gemini CLI, Antigravity, Qwen, Kimi Code, pi, Copilot, VS Code Copilot Chat, Cursor, Goose, OpenClaw, Hermes, Roo Code, omp, Amp, prime-agent, DeepSeek Harness, Continue, Crush and Zed each get it in their own guidance file (or under the configured XDG_CONFIG_HOME). Re-run rewrites deja's skill or marked block without changing surrounding user content. Use deja install --all --no-guidance to opt out; Grok Build gets the shared skill in ~/.agents/skills, which is what it reads; the ~/.grok/GROK.md written beside it is for the unrelated community CLI that shares that directory. Cursor has no user-level instructions file, so it gets the shared skill in ~/.agents/skills ā one of the four places Cursor reads skills from ā read only when something looks relevant rather than every session.
What you get
Solve it in Codex. Claude remembers. Twenty-five coding agents write every conversation to local files, and deja turns those files into one memory layer all of them read.
| Retroactive search | deja "connection pool exhausted" over gigabytes, including everything from before you installed deja. Natural-language questions fall back to a relevance tier. Time is a hint, not a filter. |
| Cross-agent recall | The MCP recall tool answers "we fixed this three weeks ago" in whichever agent asks, whoever solved it originally. |
| It survives compaction | Measured over 43 compactions: the summary keeps 77% of the decisions and 0.2% of the commands you ran. deja hands back the other 99.8%. |
| Recall at the point of action | Before an agent edits a file or runs a command, deja names that file's prior decision or that command's working invocation, from a PreToolUse hook. When a command fails, a PostToolUse hook answers with what followed that same error here before ā the pair an agent never thinks to ask for. |
| It indexes the work, not just the talk | The files each turn opened, the commands that ran with their exit status, and the exact spans an edit replaced. That is the part every summary throws away. |
Four more: rejected decisions, staleness, sync and handoff, redaction
| It knows what held | deja promote <id> --state rejected --note "why" marks a decision you reverted. Every later hit for that session shows it was tried and rejected, with the reason. Nothing is deleted, and --state accepted takes the mark back. |
| It says when the ground moved | A hit reports 4 files this session touched have changed since, and says nothing when it cannot tell. It never claims anything is unchanged. |
| Sync and handoff | deja sync ssh laptop moves memory between machines, append-only, no cloud in the middle. deja handoff --to codex packages the live context so you can continue in another agent. |
| Redaction | Keys, tokens, JWTs and private key blocks are stripped at index time, so the cache is safe to keep. |
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. To post it anywhere else, turn it into a
PNG ā that page converts it in your own
browser.
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.
Related MCP Servers
Adoption & maintenance
Factual signals from GitHub, npm, and our automated checks ā not a rating.
GitHub stars
783
Stargazers on the source repository.
npm downloads
3.5k
Package downloads in the last 30 days.
Last commit
4d ago
Most recent push to the default branch.
Install check
Inconclusive
Didn't respond in our test window ā often a slow first install.
Tools exposed
1
Callable tools this server registers over MCP.
Directory activity
2 views
Config copies, upvotes, and views on AllMCPs.
Reviews
No reviews yet ā be the first to share how this listing worked for you.
Frequently Asked Questions about Deja Vu
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/vshulcz-deja-vu)HTML Embed
<a href="https://allmcps.com/mcp/vshulcz-deja-vu"><img src="https://allmcps.com/api/badge/vshulcz-deja-vu?style=directory" alt="Deja Vu on AllMCPs" /></a>