https://github.com/user-attachments/assets/674a3e19-2e29-42fa-b062-6290ee9d0961
→ Your AI may remember what you told it, but remembering alone doesn't make sure it clearly recalls what's needed, or acts on it properly, so you end up repeating yourself and checking its work by hand.
→ For big jobs, you often either wire up a team of agents yourself, step by step, or hand the work to a team that runs out of sight, by its maker's rules. Across your windows and tools, keeping track of your sessions is still your job, which drains your attention and caps what you can actually do.
→ Much of what your assistant has learned about you lives inside one product. Moving it to another may take an import, with nothing to make sure it then works the same, and when you use both, keeping what they learn in step both ways is impossible without a shared memory setup.
We believe that once everyone has the same strongest models and the same harnesses, what will set you apart is the mind you build.
aiMyth (open-sourced as SecondSelf) builds your second self by giving your AI harness a "mind" of your own. The mind is made of your knowledge, rules and lessons, kept in interconnected files stored on your own computer, and it can learn, improve, do tasks and organise teams of agents just as you would have done yourself, from whatever harness you already use, such as Claude Code. Today it runs in Claude Code, and GPT models can join as subagents through the Codex CLI.

Why choose aiMyth
Memory tools help your AI remember. aiMyth makes sure it not only remembers, but also follows through. A harness gives an agent hands, and aiMyth gives those hands a mind of your own. We believe aiMyth is the complement to today's harnesses, and a path towards the intelligence that comes next:
- One mind behind every window. However many windows you open, with any agent in any tool, you always talk to the same mind. It looks after its own sessions and context, so you never have to manage them. Ask any window what you decided last week, and it knows.
- It strengthens you, never replaces you. It takes on the work and brings every real decision back to you. While you are away it carries on within your rules. In research, your ideas and your writing stay yours.
- Tell it once. It improves every day, by your rules, the way you would improve yourself. A correction you give today shapes every later job that needs it, including the work it hands to its teams.
- Big jobs get done even while you sleep. Hand over a job of any size, and aiMyth sets up the teams and workflows it needs, as you would yourself, and works through it within your rules. A report then sorts every item by what it needs from you.
- Your mind stays with you. When you change your harness or your personal agents, your knowledge, rules and lessons won't be lost.
- You can see why. Every answer shows its sources and how far to trust them, and every rule keeps its reason.
- Easy to start, in any harness. Clone it, run the set-up, open it in any harness you already use, and start talking. Each harness or personal agent you connect gains your mind.
- Every better model makes it stronger. The faster AI moves, the stronger your mind gets. Each better model, and each better Claude Code or Codex, is a free upgrade, and any part can be swapped for a better tool.
Some of these describe where aiMyth is going. What runs today lists what works now and where to check it.
No comments yet.