MCIR (Memory-Completion Intent Resolution)
MCIR is the intent-resolution pipeline that combines fast regex routing, a small reasoning model, behavioral patterns, and memory context to decide which Theo mode and tools should handle each message.
In depth
MCIR (Memory-Completion Intent Resolution) is OpenCharts’ replacement for naïve mode toggles. For every incoming user message, the pipeline runs cheap heuristics first, then asks a fast model to score a multi-dimensional intent (action, output format, domain, complexity, framing) using your memory and recent project structure as context.
Output is a confidence-scored decision: route directly, ask a clarifying question, or pass through to the previous mode. Resolved intents are recorded so the system learns each user’s personal frequency distributions.
Examples
- Routes “build me a moodboard” to image canvas without a mode switch
- Resolves “update it” to the last project you touched
Also known as
Want to put this concept to work in OpenCharts?
Learn about routingRelated terms
Theo Memory
Theo Memory is the personal knowledge graph that remembers your facts, preferences, and instructions across conversations — so Theo gets more useful the more you use it.
Intent Classifier
The Intent Classifier is the layer that decides which Theo mode a message belongs to — fast, think, code, image, video, social, learn, research, or others — using regex patterns plus a small AI scorer.
Theo Personality
Theo Personality is your per-account configuration — tone, persona, language, formatting preferences — that gets injected into every system prompt so Theo always sounds like the assistant you want.