Apply 7 psychology frameworks to your chat history with a partner.
Local. Privacy-preserving. Open source. Chinese + English.
Most chat analyzers give you a word cloud, a sentiment line, and a heatmap. ChatRel does the opposite: it takes the signals you already generated β in months of texting your partner β and maps them onto frameworks that relationship scientists have actually studied for 40+ years.
Intimacy Γ Passion Γ Commitment as three separable axes, each tracked weekly.
10-stage model of relationship development, anchored by language milestones.
Anxiety Γ Avoidance dimensions mapped to Bartholomew 4-category types.
Positive-to-negative interaction ratio; criticism / contempt / defensiveness / stonewalling.
Self-disclosure layered shallow β core across time.
Rising variance + AR(1) as early-warning signals for regime shifts.
Function-word / cognitive / affective markers linked to relationship satisfaction.
All demo reports below are generated from a fully synthetic 90-day couple chat (sample_data/synthetic_couple.json). No real chat data.
Index of all analyses with key metrics at a glance.
β€οΈWeekly IDS, triad scores, phase timeline.
π§¬ECR-R dimensions, 12-week trajectory, Gottman 5:1, EWS.
π₯Event detection, who initiates, repair lag, monthly trend.
π‘οΈThreat exposure, trust density, composite RCI.
πAuto-curated highlights β firsts, sweetest, deepest moments.
Supports Telegram JSON exports, generic CSV, and (via external decryption tools) WeChat. See schema docs for the canonical input format β any platform can be adapted.
π Privacy is not a feature. It's the entire architecture.
Your chat never leaves your machine. No API calls, no telemetry, no account, no cloud. Plotly loads from a CDN at view time but reads zero data. .gitignore blocks every pattern that would leak chat content. Every signal, every score, every insight is computed and rendered locally.
ChatRel produces proxy signals, not diagnoses. Thresholds are heuristic. Forecasts are damped linear extrapolation with mean reversion β not probabilistic predictions. Never label a real person "anxious-preoccupied" based on one 2D scatter plot. Read the limitations doc before making strong claims.