A visual canary that detects context rot and silent model degradation in long agent conversations by embedding externally verified checkpoints and self-reported status into each response.
Persistent decision memory and contradiction detection for AI coding agents. Enforces architectural consistency across sessions — the agent cannot code until it loads prior decisions. Human resolves conflicts on a dashboard or in chat.
Context Forge is a vendor-neutral continuity layer for AI tools. It stores project context in Markdown and JSON, retrieves task-scoped context, and leaves structured handoffs so another model can continue without being taught the project again.
A session memory consolidation and architectural oversight system that uses Gemini and SQLite to manage agent context and detect technical contradictions. It enables automated session summarization, long-term context evolution, and background refactor planning for AI agents.