A plugin that gives coding agents persistent memory across Claude Code sessions. It can remember decisions, coding conventions, and debugging lessons locally or through a team server.

Use it when configuring or using Cortex to retain development knowledge between sessions, either for one developer or a team.

It prevents useful project knowledge from disappearing when a session ends. The available configuration includes an optional server URL and a sensitive team-server API key.

cortex — Plugin by AdityaVG13

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.

Claude Code

/plugin marketplace add AdityaVG13/cortex

agentmods

npx agentmods add plugins/adityavg13/cortex/cortex-plugin

Clone the repo

git clone --depth 1 https://github.com/AdityaVG13/cortex

Made for: Claude Code.

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. Scan, not verified.

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 yesterday.

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.

plugins/cortex-plugin/.claude-plugin/plugin.json · 23 lines

What it actually says

{
  "name": "cortex",
  "version": "0.6.0",
  "description": "Remembers your decisions, coding conventions, and debugging lessons across every Claude Code session. Persistent local memory for AI coding agents.",
  "homepage": "https://github.com/AdityaVG13/cortex",
  "repository": "https://github.com/AdityaVG13/cortex",
  "license": "MIT",
  "userConfig": {
    "cortex_url": {
      "title": "Cortex Server URL",
      "type": "string",
      "description": "Cortex server URL (leave blank for local solo mode, or enter your team server URL e.g. https://cortex.myteam.com:7437)",
      "sensitive": false
    },
    "cortex_api_key": {
      "title": "Cortex API Key",
      "type": "string",
      "description": "API key for team server authentication (leave blank for local solo mode)",
      "sensitive": true
    }
  }
}

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.

yesterday First seen · 23 lines scan A 4cdfa8d3b469

Subscribe to this mod's changes

cortex is a plugin published in the GitHub repository AdityaVG13/cortex (9 stars, last pushed 2d ago), 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 2026-08-31.

Debugging Learning and teaching Memory and context agent ai developer-tools local-first mcp

piia-engram

Local-first personal AI identity layer for MCP-compatible coding tools. Stores your lessons, decisions, playbooks, and project context as local JSON. AI proposes; high-risk items wait for your review, and everything stays visible and reversible. Local-first, no cloud, no account.

Patdolitse/piia-engram · not measured

screenshotting-gui

Capture clean, repeatable screenshots of a GUI desktop app (Cursor, IDEs, browsers) on an isolated Xvfb display: drive it with python-Xlib (XTEST), capture with ImageMagick, annotate with a highlight box, crop or arrow. For docs, courses and bug reports; never touches the operator's live :0 desktop.

EvilFreelancer/screenshotting-gui · not measured

forkmind

Local-first LLM branching, debugging & context offloading. Treat AI context windows like a Git repo — capture, branch, regression-test LLM calls as a DAG, and archive context as encrypted, restorable capsules. Teaches Claude when and how to drive ForkMind.

Medhovarsh/forkmind · not measured

tencentdb-agent-memory

Four-layer long-term memory (L0→L1→L2→L3 Persona) with hybrid FTS5+vector recall + L2 scene-navigation. CLI: tmem (status, search, projects, migrate-fragments, recall, scene, scenes, changelog, persona, sync, config, daemon, atoms, sessions, write-l1, write-scene, write-persona, mark-done, init). Run /memory-init…

baodq97/tencentdb-agent-memory · not measured

clrun-skill

Teaches Claude Code how to use clrun for interactive terminal sessions — TUI prompts, select lists, checkboxes, confirms, long-running processes, and env persistence.

cybertheory/clrun · not measured

nextjs

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

vercel/next.js · not measured