deja-vu is a local-first agent-memory tool maintained by vshulcz (Vladislav Shulcz) under the MIT license; it is not an official project of any agent vendor. Its distinguishing claim is where memory comes from: it indexes the session histories already on disk, so it is useful immediately after install and can surface work done months before, rather than starting empty and recording forward. The README reports 85.3% hit@1 on LongMemEval-S, 69.6% on LoCoMo, and about 0.4 ms median in-process lookup over a 5.2 GB store of 1,551 sessions. On the MCP side it exposes one tool, deja, with a mode switching between six behaviors, and it also hooks into PreToolUse/PostToolUse for recall at the point of action. It suits developers running multiple coding agents who value local-only, LLM-free retrieval, and is a poor fit for those who need hosted shared memory or cannot accept the limits of pattern-based redaction.
Strongest · Documentation 18/20 Weakest · Reliability 11/20
Static review · not runListed 2026-09-10
Read the FMRS scoring method →Runtime：Node.js · Prebuilt binary · Go
DEJA_EMBED_KEY
Optional; explicit key for an authenticated third-party embeddings endpoint; takes precedence over OPENAI_API_KEY.
OPENAI_API_KEY
Optional; used automatically only for HTTPS api.openai.com endpoints, never sent implicitly to local or third-party endpoints.
DEJA_EMBED_URL
Optional; points at a local Ollama/LM Studio or OpenAI-compatible embeddings endpoint for semantic recall. Unset, deja probes localhost:11434 and localhost:1234.
DEJA_EMBED_MODEL
Optional; the embedding model name, e.g. text-embedding-3-small.
DEJA_EMBED_OFF
Optional; set to 1 to disable the local embeddings runtime probe.
1) Install: on macOS/Linux run curl -fsSL https://raw.githubusercontent.com/vshulcz/deja-vu/main/install.sh | sh; alternatives are brew install deja-vu or go install github.com/vshulcz/deja-vu/cmd/deja@latest; on Windows use scoop install deja-vu (the install script exits with 'unsupported OS' there). 2) Run deja install --auto to wire MCP into every agent it detects, enable session-start recall where supported, and build the first index; add --all to skip session-start recall, or --no-guidance to avoid writing per-harness guidance files. 3) To configure MCP by hand, use the stdio command npx @vshulcz/deja-vu mcp, or invoke deja mcp directly. 4) Verify with deja doctor [--deep].
{"mcpServers":{"deja-vu":{"command":"npx","args":["@vshulcz/deja-vu","mcp"]}}}
Shown for Claude Code. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"deja-vu": {
"command": "npx",
"args": [
"@vshulcz/deja-vu",
"mcp"
]
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add deja-vu -- npx @vshulcz/deja-vu mcp
Run it in a terminal; replace any <…> placeholders with your own values first.
After running `deja install --auto`, start a new agent session and check that the `deja` MCP tool appears in the client's tool list; then ask something you solved months ago — a correct answer quoted from a prior session proves recall works.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
deja-vu is a local-first memory layer that indexes the session histories coding agents on your machine have already written to disk (Claude Code, Codex, Cursor, Copilot CLI, OpenClaw and roughly twenty others in total) and hands the relevant memory back to whichever agent asks. Nothing leaves the machine by default: indexing and search are local, and credentials are redacted at index time. Per the project's README, lexical retrieval needs no LLM and no embedding key; semantic recall is optional and requires pointing deja embed at a local Ollama/LM Studio instance or an OpenAI-compatible endpoint. It serves MCP over stdio and exposes a single tool named deja whose mode argument selects behavior (recall, context, blame, fix, how, remember); six older tool names (recall, recall_context, blame, fix, how, remember) still answer for existing wiring. Install paths include the install script, Homebrew, go install, Scoop, and npx @vshulcz/deja-vu, and deja install wires MCP recall into the agents it detects.
Upstash's official server providing up-to-date third-party library docs for AI coding assistants
AI-powered NPM package analysis MCP server
An independent control layer that gives AI coding agents budgets, brakes, and receipts
GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
Source revision e89e3d9df4bd Data synced 2026-10-19 Read the FMRS scoring method