fractera.ai

Register a new Fractera user and start the deployment of their server in one atomic call.

Read the current installation progress ONCE, on demand.

Return the final entry address of the server once installation is complete.

Retry a failed deployment using a server_token (from the failure email, the deploy-progress UI, or the dashboard).

Return a single recommended VPS provider for users who do not yet have a server.

Project reference / help desk about Fractera.

Architecture reference for Fractera AI Workspace: what it is made of and how it works (the admin drives it through Hermes — chat Web UI or Telegram — or directly through the five coding agents; a modal subscription sign-in layer + MCP keep work resilient when a subscription is limited; LightRAG is the central memory that slashes token use; Hermes is a light orchestrator while the coding agents do the heavy lifting; the result ships over HTTPS on a custom domain or plain HTTP on an IP).

Explains the Fractera development loop: how one admin request becomes tested, deployed, recorded code with no human writing it — Hermes orchestrates and loads its identity + project context, picks a ready coding agent (Claude Code, Codex, Gemini, Qwen, Kimi), the agent is enriched (SOUL.md / AGENTS.md / GLOSSARY.md / completed steps), generates a task then code, it is built and deployed, and the result branches (error feeds back; success updates the completed steps and the deployments tab) — all grounded by LightRAG memory at every step.