Persistent memory + self-improvement for AI coding agents. Gradient-gated disposition engine with formal stability proofs.

TITANS Disposition

Persistent memory + self-improvement for AI coding agents.

Your AI agents don't learn. Ours do. Here's how -- and the math proving why your current approach makes them worse.

pip install titans-disposition

The Problem (Two of Them)

Problem 1: Agents reset. Every AI coding agent -- Claude Code, Cursor, Cursor -- starts fresh each session. Session 500 feels the same as session 1. Context injection (system prompts, RAG) addresses knowledge. Nothing addresses disposition: the accumulated sense of how to work with you.

Problem 2: Naive self-improvement actively declines. If you try to fix Problem 1 by scoring agent output and nudging weights toward deficits, you get worse over time. We proved this mathematically: deficit-chasing on a quality simplex with nonuniform proxy bias produces monotonic decline. The fix requires structural protocols, not continuous optimization. (Full proof)

Three Pillars

1. Disposition Engine

A gradient-gated M-vector that gives agents persistent taste.

Based on Titans: Learning to Memorize at Test Time (Google, 2025), but applied as a disposition accumulation system. Every prompt is classified, gated, and deposited into a weight matrix that evolves with your collaboration:

from titans_disposition import DispositionEngine

engine = DispositionEngine(conversation_id="my-project")
engine.deposit("Add error handling to the auth module")   # routine: minimal weight
engine.deposit("No, use composition not inheritance")      # correction: punches through
engine.deposit("Redesign the pipeline as event-driven")    # architectural: carries momentum

metrics = engine.read()
print(f"M norm: {metrics['m_norm']:.4f}")  # The shape of your collaboration

T