Reading
A portable multi-agent engineering toolkit designed for the workflows of AI programming assistants like Codex, Cursor, and Claude Code.
Section 01
A portable multi-agent engineering toolkit designed for the workflows of AI programming assistants like Codex, Cursor, and Claude Code.
Section 02
Section 03
AI programming assistants are profoundly changing the way software development works. From OpenAI's Codex to Cursor IDE and Anthropic's Claude Code, these tools have greatly improved development efficiency. However, to fully unleash the potential of these AI assistants, developers need to master specific interaction patterns, prompt engineering techniques, and best practices.
The Agent General Staff project was born to provide developers with a unified multi-agent engineering suite, enabling different AI programming assistants to collaborate and leverage their respective strengths.
Section 04
Agent General Staff is a portable multi-agent engineering toolkit that supports mainstream AI programming assistants such as Codex, Cursor, and Claude Code. Through standardized interfaces and preconfigured workflows, this project allows multiple AI agents to collaborate on the same project to accomplish more complex development tasks.
Section 05
Section 06
Agent General Staff designs a unified agent abstraction layer to shield the underlying differences between different AI programming assistants:
Section 07
The project supports multiple agent collaboration modes:
Multiple agents process tasks in sequence, each completing a specific link:
Multiple agents analyze the same problem in parallel and synthesize opinions from all parties:
Multiple agents independently generate solutions and the best one is selected:
Section 08
The key to collaboration lies in maintaining context consistency:
Keep going with more reads from the same topic.
Nornir MCP Server is an enterprise-level server based on the Model Context Protocol (MCP). It seamlessly integrates large language models (such as Claude) with the Nornir network automation framework, supporting natural language orchestration for multi-vendor network devices (Cisco, Arista, Juniper, etc.), and providing production-grade features like a dual-engine architecture (NAPALM + Netmiko), intelligent filtering, and a secure sandbox.
Bibliothèque Française LLM is a structured indexing and annotation project for French public domain literature designed specifically for large language models (LLMs). It integrates multiple authoritative sources such as DraCor, Common Corpus, and Wikisource, providing metadata indexing categorized by genre, author, and era, as well as in-depth annotations for dramatic texts (including characters, lines, stage directions, etc.). Its aim is to enable LLMs to efficiently read and understand classic French literary works.
Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.
libmlxforge is an embeddable MLX large language model (LLM) inference engine designed specifically for Apple Silicon. It provides a unified C ABI interface, supports calls from Node.js, Swift, and Rust, and features continuous batching, streaming output, JSON-constrained structured output, and embedding vector generation.