For Claude Code, Codex and Gemini CLI

Switch coding agents without starting over.

Junxion runs the agents you already use on your Mac, learns what matters in each project, and hands the next agent a short brief, so it picks up where the last one left off.

Try the live demo Mac app coming soon

How it works

Your agents keep their own logins.
Junxion keeps the memory.

  1. 01

    Run your agents through Junxion

    Start Claude Code, Codex or Gemini CLI in any project. They sign in with your own accounts and keep their settings, plugins and connectors.

  2. 02

    It learns as you work

    A local model reads each session and keeps the decisions, rules, preferences and open work, each with where it came from.

  3. 03

    The next agent gets a brief

    Switch agents, start fresh when the context fills up, or come back next week: the new agent starts with what it needs, and can ask Junxion for more.

Live demo

The real app, in your browser.

A sample to-do project with recorded Claude Code and Codex sessions. Start a session, answer the agent's question, hand the work to Codex, then see what Junxion learned. No sign-in.

junxion · demo

Measured, not guessed

A brief beats the transcript.

On our handoff benchmark (recorded sessions, a 600-token budget), Junxion's brief carried the key facts a new agent needed far better than the last 600 tokens of the conversation.

Junxion's brief0%
Transcript tail0%

Share of the key facts carried to the new agent, same budget.

What you get

Built for how you already work.

Handoffs in one click

Move a task from Claude Code to Codex, or start a fresh session when the context window fills up. Nothing gets explained twice.

Memory you can read

See everything Junxion knows about a project as a map, a list and a history. Correct anything, or add your own.

Your logins, your tools

Agents use their own sign-in (or an API key you add), with their own connectors and plugins. Nothing to set up again.

A live campus

Your agents and projects as a small city: see who's working where, and what's waiting on you.

Local first

Sessions and knowledge live on your Mac. Learning runs on a local model, so Junxion never sends your code anywhere.

Encrypted sync

Optional sync keeps your knowledge the same on all your Macs, sealed on your device so no one else can read it.

Questions

Good to know.

Which agents does it work with?

Claude Code, Codex and Gemini CLI today, through the open Agent Client Protocol. If you already use Claude Code or Codex in a terminal, Junxion uses that same setup.

Does Junxion see my code?

Junxion runs on your Mac and keeps everything there. Your agents talk to their own providers, as they always do. Junxion's servers only hold your account and, if you turn on sync, data that's encrypted on your device.

Do I need API keys?

No. Agents use the sign-in you already have (your Claude or ChatGPT account). You can add an API key instead if you prefer.

What does it need on my Mac?

macOS, the agents you want to use, and Node.js. Learning uses a local model through Ollama; without it, sessions are still saved and searchable.

Stop re-explaining your project.

Try the live demo Mac app coming soon