Richard Ketelsen PRO
CRAFTFramework
AI & ML interests
CRAFT applies structured programming principles to AI conversations. Think recipes for your workflows.
Recent Activity
posted an update about 2 hours ago
CRAFT Framework: Structured AI Session Management for Claude Cowork — Free Public Beta
Overview
CRAFT (Configurable Reusable AI Framework Technology) is a structured communication framework that provides persistent session continuity, version control integration, and systematic quality assurance for AI-assisted workflows running on Claude's Cowork desktop platform.
Technical Architecture
CRAFT uses a recipe-based system — 188 standardized workflow definitions across 12 cookbooks — to manage the full lifecycle of AI project sessions. Key subsystems:
- **Session Handoff System (4 recipes):** Structured state serialization that captures project context, decision history, and persona calibration between sessions. Validated across 71 consecutive handoffs with zero information loss over 72 development sessions.
- **Version Control Integration (4 recipes):** Event-driven git checkpoints triggered by workflow completion rather than time intervals. Maintains over 500 files across 9 projects in a unified monorepo.
- **Quality Assurance Framework (6 recipes, 14-point plan):** Includes 4 verification gates — file pointability, read-vs-reconstructed detection, constraint conflict analysis, and untested assumption identification. Addresses the systematic overconfidence problem in LLM output.
- **Multi-Persona Collaboration (5 recipes):** Separate AI personas for content generation, validation, and operations management. The Creator/Validator pattern enforces independent review.
- **Cross-Project Transfer (4 recipes):** Knowledge packaging with provenance tracking, enabling verified intelligence sharing between project contexts.
Scale
The framework grew from ~60 pre-existing recipes to 188 (213% increase) during a 72-session adaptation project. Development produced 7 formal specifications, 64 documented lessons learned, and ~59,000 lines of recipe content. posted an update 8 days ago
Quick observation from working with Claude Cowork on multi-session projects.
**The constraint:** Cowork runs in a sandboxed VM that resets between sessions. No state persistence, no conversation carryover, no cross-session memory. Each session starts with zero context about prior work.
```
https://craftframework.ai/the-hidden-cost-of-session-amnesia-why-context-matters-more-than-you-think/
```
Within a single session, context compaction occurs as conversations approach the token limit — the system summarizes earlier exchanges, trading detail for capacity. Decisions made early in a session degrade to single-sentence summaries as the conversation grows.
**The cost:** For task-based work (summarize this, debug that), this is irrelevant. For cumulative work — projects that build over days or weeks — it creates significant overhead. Users spend meaningful time each session re-establishing context that the AI previously held.
**Common workarounds observed:**
- Manual context injection (copy-paste at session start)
- Single mega-sessions (avoids reset, but context degrades)
- External state documents (maintained alongside the AI)
Each trades one form of overhead for another.
**The architectural question:** Claude's chat interface (claude.ai) now has persistent memory — free for all users since March 2026. But the desktop environment still operates on a session-reset model. The gap between chat-based memory and desktop-based amnesia is growing.
This seems like a general problem for desktop AI tools, not just Cowork. How are others approaching session continuity in local AI environments?Organizations
