hanzi-browse: Hanzi Browse provides 24 site playbooks as hints for LLM-based browsing agents, helping them handle complex real-world websites. It offers two modes: as a browser sub-agent for coding agents or as a REST API/SDK for product integration. The tool automatically configures MCP for multiple AI agents and requires only an npx command to set up.; 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.
Unsubscribe from marketing emails in Gmail
Deep repository research and analysis (e.g., architecture, contributors, issues)