Explore the directory

A companion tool that mirrors the DeepSeek Harness web interface from a desktop to a phone in real time over a QR code, working over the local network or a public tunnel.

• Coding agents

A library and set of command-line tools for high-speed approximate nearest neighbor search over large, high-dimensional vector data, using neighborhood graph and tree indexes.

• Databases

A code intelligence server built in Zig that gives AI coding agents a map of a repository through MCP: focused source context, symbols, callers, outlines, and dependencies, without editing files itself.

• MCP servers
• Agent memory

A self-hosted, multiplayer web workspace for running coding agents such as Claude Code, Codex, and Gemini on isolated git branches, each with its own development environment and conversation history.

• Coding agents

A seven-layer local memory system for Hermes Agent that stores structured facts, session history, and a self-curating wiki, and injects the right context back into conversations automatically.

• Agent memory

A repository of summaries, notes, prompts, and code files from DeepLearning.AI's short course on Agent Skills with Anthropic.

• Tutorials

A .NET library that compiles C# expression trees into delegates roughly ten to forty times faster than the built-in Expression.Compile, with a lightweight LightExpression alternative.

• Libraries

A self-hosting, educational optimizing C compiler that targets 32-bit Arm, AArch64, 32-bit RISC-V and x86-64, producing Linux ELF binaries.

• Languages

A self-hosted control plane that lets an engineering channel mention a coding agent from Slack, GitHub, GitLab, Linear, or Lark, and have it run Claude Code, Codex, Cursor, or another agent on a machine you control.

• Coding agents
• Workflow automation

A daily-updated list of research papers on autonomous LLM agents, each summarized in a few bullet points covering the paper's method, architecture, and evaluation.

• Papers

A curated list of tools, frameworks, techniques, and learning resources for building retrieval-augmented generation systems, organized by architecture patterns, frameworks, techniques, metrics, and production considerations.

• RAG
• Curated lists

A personal collection of Agent Skills for coding assistants such as Codex, including a pre-launch and pre-commit audit skill and a reliability overlay for safer, more focused coding work.

• Agent skills

An open-source general-purpose AI agent that keeps a persistent identity and memory across tasks and restarts, coordinates a swarm of specialist agents, and can rewrite its own code, prompts, and tools.

• Coding agents
• Agent frameworks

A collection of agent skills that generate single-file HTML animations, such as slideshow decks, flowcharts, network-protocol diagrams, and video storyboards, for AI coding agents like Claude Code and Cursor.

• Generative media
• Design tools

An AWS sample application, built on Bedrock, SageMaker and Lambda, that implements a set of ready-to-use generative AI business use cases such as chat, summarization, meeting minutes and translation.

• Tutorials

An agent skill that replaces fear-based prompting, such as threatening a poor performance review, with a respectful tone, reporting that a trust-based version of the same debugging methodology found twice as many hidden bugs in testing.

• Agent skills

An LLM knowledge-compilation engine that reads raw documents, such as PDFs, spreadsheets and transcripts, and synthesizes them into a persistent, cross-referenced wiki stored as local Markdown files, as an alternative to RAG.

• Agent memory
• RAG

A Model Context Protocol server that lets an AI application safely explore and query a MySQL database, listing tables as resources, reading their contents, and running SQL queries through a controlled interface.

• MCP servers
• Databases

A .NET client library for the Ollama API, recommended by Microsoft and used by Semantic Kernel, .NET Aspire and Microsoft.Extensions.AI, covering chat, embeddings, model management and tool calling.

• Inference
• Libraries

A collection of on-device AI primitives for React Native, compatible with the Vercel AI SDK, for running text generation, embeddings, transcription and speech synthesis directly on a user's phone.

• Mobile
• Libraries

A Neovim plugin that provides AI-powered, as-you-type code completion from LLM providers such as OpenAI, Gemini, Claude, Ollama, Llama.cpp and Codestral.

• Editors

A universal AI context generator that maps a codebase into a compact, AST-based summary, saving thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex and similar tools.

• Agent memory

A sponsored, structured learning path and set of guides for DevOps engineers adopting AI, covering an 18-month roadmap, building MCP servers and AI agents for DevOps, and enterprise frameworks for adopting AI safely.

• Tutorials

The official Python SDK for the Milvus vector database, giving Python applications a client library matched to specific Milvus server versions.

• Databases