aimee aims to cut AI coding costs with a local model-switching layer
aimee is a local layer that sits underneath such as Claude Code, Codex, OpenCode, Gemini CLI, and Copilot. If a tool can use the OpenAI API or style, aimee can route its work to Claude, GPT, Gemini, Mistral, a local model, or another compatible model. The goal is to avoid being locked into one tool or one , while carrying memory and settings across tools and providers.
The cost idea is to stop the expensive main agent from reading all raw context for every step. Cheaper or free handle parts of the work, then send a compact result back to the main agent. Safety features include blocking sensitive files before a model sees them, locking file writes in planning mode, and isolating each session so parallel work does not overwrite itself.
aimee also uses 4-tier memory to reduce duplicates, catch contradictions, weaken old facts over time, and let new sessions start with what earlier sessions learned.
Key points
- aimee is a local layer for switching models under .
- It works with tools that speak the OpenAI API or style.
- It tries to cut costs by sending smaller tasks to cheaper .
- It adds for sensitive files, write access, and isolated sessions.
- Its 4-tier memory is meant to carry useful knowledge across sessions while reducing stale or conflicting information.