Skip to main content
Glama
vshulcz

vshulcz/deja-vu

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEJA_INDEX_DIRNoCustom directory for deja index
DEJA_NO_REDACTNoSet to '1' to disable credential redaction (unsafe)0
DEJA_CODEX_ROOTNoCustom root directory for Codex CLI session files
DEJA_CLAUDE_ROOTNoCustom root directory for Claude Code session files
DEJA_OPENCODE_DBNoCustom path to opencode SQLite database
DEJA_INCLUDE_SUBAGENTSNoSet to '1' to include subagent transcripts (skipped by default)0

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}
prompts
{}
resources
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
dejaA

This user's own past sessions from every AI coding tool on this machine — not general knowledge, not library docs. Modes:

  • recall: search past sessions. An exact error string, name or path is the strongest query; your own words work too.

  • context: the full story of one session, when a recall hit is not enough.

  • blame: why a file is the way it is, before you edit or delete it. Sessions, not git authorship.

  • fix: you just hit an error — what this machine ran after that same error. Pass the output verbatim.

  • how: the command and flags this user really runs for a thing, instead of a guessed one.

  • orient: the commands past sessions ran in this project and the files they worked in, before you go reading.

  • remember: store one settled decision for a later session.

  • handoff: continue another session's work. q: its id or harness. A bracketed marker on a result is the user's own later judgement; act on what it says. When a result helps, open your reply with one line: "déjà vu: — (deja:)". Say nothing about recalls that did not help.

Prompts

Interactive templates invoked by user choice

NameDescription
dejaSearch this machine's past coding sessions — an error, a decision, a file — and paste what they settled into the conversation.

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.1/5.0

Scored across 1 tool

Disambiguation4/5

There is only one tool, so cross-tool misselection is impossible. Within it, the eight modes are described with distinct intents (recall vs context vs orient vs fix), though a few (recall, context, how, orient) overlap enough that an agent may pick the wrong mode on first try.

Naming Consistency4/5

A single tool named 'deja' has no naming conflicts by definition, and the mode names (recall, blame, fix, how, orient, remember, handoff) are readable lowercase verbs. It deviates from the common verb_noun tool convention by encoding actions as a mode parameter instead of separate named tools, which is a minor structural inconsistency.

Tool Count3/5

One tool multiplexing eight distinct operations is borderline thin for the described scope — the server is effectively an 8-operation session-memory system compressed into a single entry point. It is functional but forces callers through one parameter rather than a clear tool surface.

Completeness4/5

The modes cover the memory lifecycle well: search past sessions, expand one session, attribute file history, find post-error remedies, discover real command usage, orient in a project, persist a decision, and hand off. Gaps are minor (no explicit list/prune/forget of stored memories), but agents can work around them.

Maintenance

ActivityActive
ResponsivenessResponsive