Skip to main content
Glama
vshulcz

vshulcz/deja-vu

Related Servers

Alternatives to vshulcz/deja-vu

  • A
    license
    B
    quality
    C
    maintenance
    A fully local persistent memory layer for LLM coding agents (Claude Code, Codex, Gemini CLI, OpenCode). A shell wrapper intercepts tool invocations, fires hooks on every tool call, then runs a 3-layer pipeline (extract → compress to ≤500-token digest → merge into project memory doc) at session end. The next session gets prior context injected automatically.
    6
    11 npm
    MIT

Related Servers

  • F
    license
    Not graded
    quality
    B
    maintenance
    Local semantic search over Claude Code sessions and shell command history, exposed to Claude Code as an MCP tool. Everything is indexed into one vector space and runs entirely on your machine.
    2
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Turns local Codex session transcripts into a searchable memory that MCP-compatible coding agents can query to retrieve relevant past sessions or exact commands and fixes.
    1
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Local-first memory for AI coding agents. Indexes your Claude Code, Codex, Cursor, Cline and Gemini CLI history by repo/branch/worktree and hands a context capsule (decisions, touched files, next steps) to the next agent over MCP.
    -
  • A
    license
    B
    quality
    C
    maintenance
    Provides local, agentic semantic recall over Claude Code session history, enabling the agent to search past discussions semantically, expand turns, and grep transcripts.
    5
    13
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Persistent local memory for Claude Code that indexes every session's JSONL file verbatim into SQLite + ChromaDB. Exposes 17 MCP tools for semantic recall, deterministic file replay, and fuzzy "do you remember when..." queries across your entire session history — no API calls, nothing leaves the machine.
    17
    115 PyPI
    14
    MIT

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