cortex

cortex is a plugin for Gemini CLI from cdeust/Cortex. Its token cost is not measured, scanned A, original, MIT.

A local-first memory service that stores and retrieves information in a local database. It also organizes memories as a knowledge graph and can build a browsable wiki; automatic capture through hooks is limited to Claude Code, while Gemini CLI requires manual use.

In plain words
What is it for?
It helps agents remember and recall project information, connect related knowledge, and maintain a local knowledge base. It requires uv or uvx to be available.
Why use it?
It lets an agent retain information between sessions without relying on a remote memory store, while making related facts easier to find.

Plugin for Gemini CLI

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

Good fit It helps agents remember and recall project information, connect related knowledge, and maintain a local knowledge base. It requires uv or uvx to be available.

Compare 6 plugins from other repositories ↓
Install with agentmods
npx agentmods add plugins/cdeust/cortex/gemini-extension
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/cdeust/Cortex

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 cortex

README.md
[![agentmods](https://agentmods.dev/badge/plugins/cdeust/cortex/gemini-extension/github.svg)](https://agentmods.dev/plugins/cdeust/cortex/gemini-extension)
Your own site
<a href="https://agentmods.dev/plugins/cdeust/cortex/gemini-extension"><img src="https://agentmods.dev/badge/plugins/cdeust/cortex/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 cortex

Your own site · 80×15
<a href="https://agentmods.dev/plugins/cdeust/cortex/gemini-extension"><img src="https://agentmods.dev/badge/plugins/cdeust/cortex/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

cortex 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 29d ago.

The scan reads gemini-extension.json. This mod also ships 51 executable files (scripts/aggregate_hook_timings.py, scripts/backfill_wiki_titles_2026_07_14.py, scripts/backfill_write_class.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 · 12 lines

What it actually says

{
  "name": "cortex",
  "version": "4.23.5",
  "description": "Persistent local-first memory MCP server: remember/recall with thermodynamic heat and decay, knowledge graph, autonomous wiki, local SQLite store by default. Requires uv (uvx) on PATH; hooks-based auto-capture is Claude Code-only — on Gemini CLI memory is manual-tool-driven.",
  "mcpServers": {
    "cortex": {
      "command": "uvx",
      "args": ["--from", "hypermnesia-mcp[sqlite]", "hypermnesia-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. 29d ago Changed c546128b8108
  2. 1mo ago Changed 64958270dc2d
  3. 1mo ago Changed 773dfdd1c9ce
  4. 1mo ago Changed ec1d46b52fb6
  5. 1mo ago Changed 385c4f269bdd
  6. 1mo ago Changed 3ae3974a2f71
  7. 1mo ago First seen · 12 lines scan A 25851dd9079b

Subscribe to this mod's changes

cortex is a plugin published in the GitHub repository cdeust/Cortex (75 stars, last pushed yesterday), 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.

Related

Other plugins, from other repositories

prism-coder

Your coding agent forgets everything between sessions. Prism gives it a memory that sticks: your decisions, open TODOs, and changed files, restored the moment you return. It goes past a notes store — associative recall surfaces related past work, drift detection catches a long session wandering off-goal, and an…

dcostenco/prism-coder · not measured

papi

Persistent project management inside your AI coding tool. PAPI plans what to build next, tracks every decision, and keeps projects coherent across sessions — so a new session starts where the last one left off instead of from nothing.

getpapi/papi · not measured

inspeximus

Self-correcting memory for Claude Code. Facts you correct stay corrected, deletions leave a signed receipt you can verify offline, and storing something never calls a model. Also ships the checks: erasureresidue asks whether the bytes actually went — on any store, not just this one.

DanceNitra/inspeximus · not measured

mnemo-mcp

Persistent AI memory — store, search, and recall knowledge across sessions.

n24q02m/mnemo-mcp · not measured

synapse-mcp

Persistent AST knowledge graph and safe writes for AI coding agents across 50+ languages. 100% local — no cloud indexing, no telemetry.

myelixlabs/synapse-mcp · not measured

stickies

A persistent sticky-note layer for Claude Code. Claude writes durable facts (decisions, blockers, preferences, context, todos) during a session; they survive resets and are injected back into context on the next start.

dumbspacecookie/stickies · not measured