agent-lsp: agent-lsp is a stateful runtime over real language servers. It indexes your workspace once, keeps the index warm, and adds a skill layer that encodes correct multi-step operations. It provides speculative execution, phase enforcement, and token savings for AI agents.; MCP-Chinese-Getting-Started-Guide: This guide provides a rapid introduction to the Model Context Protocol (MCP), an open-source protocol standardizing LLM interactions with external data and tools. It demonstrates building and debugging MCP servers, developing MCP clients for LLMs like DeepSeek, and integrating with Claude Desktop.
Multi-project sessions: work across projects without reconfiguring
Enhancing LLMs with real-time web search capabilities