memex: memex provides persistent memory for AI coding agents using atomic knowledge cards with bidirectional links. It stores insights from each session and recalls relevant cards before starting new tasks, enabling agents to build on previous knowledge. No vector database or embeddings needed—just markdown files.; 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.
AI coding agents maintaining context across sessions
Deep repository research and analysis (e.g., architecture, contributors, issues)