agentmods.dev

deja

deja is a plugin for Gemini CLI from vshulcz/deja-vu. Its token cost is not measured, scanned A, original, MIT.

A memory tool for Gemini CLI that searches past coding sessions saved on your computer, including sessions from several other coding tools.

In plain words
What is it for?
Use it to search and recall previous coding conversations from Gemini CLI, Claude Code, Codex, Cursor, and other supported tools.
Why use it?
It helps you find earlier decisions, code discussions, and unfinished work without relying only on the current session.

Plugin for Gemini CLI

Written for Gemini CLI: a Gemini CLI extension manifest. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

not rated 1.3krepo +68 changed yesterday A scan tokens not measured original MIT

Good fit Use it to search and recall previous coding conversations from Gemini CLI, Claude Code, Codex, Cursor, and other supported tools.

Compare 6 plugins from other repositories ↓
Install with agentmods
npx agentmods add plugins/vshulcz/deja-vu/gemini-extension
View source ↗ vshulcz/deja-vu vshulcz.github.io
About the project

deja-vu is a local memory system that indexes coding-agent session histories and makes relevant past work available to other agents. It helps users share fixes and context across Claude Code, Codex, Cursor, Copilot CLI, and other coding agents without using a language model or embeddings. The catalogue contains hooks, commands, MCP components, skills, plugins, and instructions for connecting agents to that memory.

vshulcz/deja-vu · 1,288 stars · on GitHub · vshulcz.github.io

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/vshulcz/deja-vu

Made for: Gemini CLI.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deja

README.md
[![agentmods](https://agentmods.dev/badge/plugins/vshulcz/deja-vu/gemini-extension/github.svg)](https://agentmods.dev/plugins/vshulcz/deja-vu/gemini-extension)
Your own site
<a href="https://agentmods.dev/plugins/vshulcz/deja-vu/gemini-extension"><img src="https://agentmods.dev/badge/plugins/vshulcz/deja-vu/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deja

Your own site · 80×15
<a href="https://agentmods.dev/plugins/vshulcz/deja-vu/gemini-extension"><img src="https://agentmods.dev/badge/plugins/vshulcz/deja-vu/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

deja scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads gemini-extension.json. This mod also ships 18 executable files (scripts/agent-smoke.sh, scripts/day0compare/agentmemory.py, scripts/day0compare/agentsview.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

gemini-extension.json · 15 lines

What it actually says

{
  "name": "deja",
  "version": "0.23.0",
  "description": "deja-vu memory for Gemini CLI: the coding sessions already on your disk — Gemini CLI, Claude Code, Codex, Cursor and thirty-eight more — searchable and recalled, including work from before it was installed.",
  "contextFileName": "GEMINI.md",
  "mcpServers": {
    "deja": {
      "command": "deja",
      "args": [
        "mcp"
      ]
    }
  }
}
Files

What ships with it

60 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday Changed 67b545c5497a
  2. 5d ago Changed 4b62ed8391eb
  3. 8d ago Changed 4760e89176a1
  4. 10d ago Changed 0d741f42f9fa
  5. 13d ago Changed 1d166a8b2a9c
  6. 14d ago Changed 8de483ea54a2
  7. 16d ago Changed 37c1288bb6aa
  8. 17d ago Changed ba34ae43df6f
  9. 18d ago Changed ea8b02a341de
  10. 20d ago First seen · 15 lines scan A b7f22fe64091

Subscribe to this mod's changes

deja is a plugin published in the GitHub repository vshulcz/deja-vu (1,288 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Claude CodeMemory and contextagent-memorycodexcoding-agentsmcpopencode
Related

Other plugins, from other repositories

infinity-context-agent-plugin-gemini-hooks

Infinity Context Gemini extension with lifecycle hooks for durable project memory.

777genius/infinity-context · not measured

palimem marketplace

Plugin marketplace listing 1 plugin: memory-service.

palimem/palimem · not measured

memory-service

Local-first governed memory for Claude Code via MCP and lifecycle hooks.

palimem/palimem · not measured

krimto

Open-source memory for AI coding agents you own in git — governed by a real user→team→org hierarchy, not a vendor database. Solo to team. Apache-2.0.

krimto-labs/krimto · not measured

github-stars-radar

Local-first GitHub stars memory MCP server and skill bundle for Claude Code.

NeoZhouCHN/github-stars-radar · not measured

repo-brain

Persistent repository memory for Claude Code.

lucianum7/repo-brain · not measured