context-mode: Every tool call in an MCP (Model-Controller-Program) environment dumps raw data into the context window, quickly consuming space and causing the agent to lose track of ongoing tasks. Context Mode is an MCP server that tackles this by sandboxing tool outputs to significantly reduce context usage, tracking session events in SQLite for continuity, and promoting 'think in code' to minimize data processing within the LLM.; subcog: Subcog is a persistent memory system for AI coding assistants that captures decisions, learnings, and context from coding sessions. It features a single-binary distribution, three-layer storage architecture (SQLite, FTS5, usearch HNSW), MCP server integration, and Claude Code hooks. It achieves high accuracy on factual recall benchmarks.
Deep repository research and analysis (e.g., architecture, contributors, issues)
Capturing and recalling technical decisions during development