Forkpath: Change One Moment in History, Then Let the AI Do the Homework

Description and use

Forkpath enables rapid generation of branching alternate histories using local AI models, with realism checks and editable event nodes.

Problem

Writing alternate history requires extensive research, scenario planning, and consistency across multiple storylines.

Outcome

Forkpath enables rapid, local generation of detailed alternate-history timelines with branching probabilities, realism checks, and editable event nodes, reducing research time from days to minutes.

Workflow

• 1. Install Forkpath locally via npm.
• 2. Run the dev server and open http://localhost:5173.
• 3. Select an AI engine (Anthropic, OpenAI-compatible, or local Ollama/LM Studio).
• 4. Input a one-sentence alternate-history prompt.
• 5. Forkpath generates a tree of events with odds at each fork.
• 6. Review and edit events; regenerate or delete branches as needed.
• 7. Save timelines as plain JSON for sharing or version control.

Evidence

Forkpath runs locally, so here's a quick tour in screenshots.

Source

The model layer was designed to be swappable from day one: No SDKs. The server talks to models through two small adapters built on plain fetch: one for the Anthropic Messages API and one for any OpenAI-compatible endpoint.

Source

With an open-weight model behind it, Forkpath is fully local: Nothing leaves your machine. The app, the model and your timelines all live on your laptop.

Source