Explore the directory

A local Rust daemon that replaces plain-text cat and grep for AI coding agents, exposing symbol-aware code reading and hybrid search over MCP to cut the tokens an agent spends reading code.

• MCP servers

A self-hosted AI workspace that orchestrates local and OpenAI-compatible models, agents, MCP tools and deep research through one installer, aimed at coordinating work rather than just chatting with a model.

• Agent frameworks

An AI chat backend written in Go that answers questions from an imported knowledge base, with built-in MCP tools, OAuth login and adapters for WeCom and Feishu.

• MCP servers
• Backend

A pure-Rust inference engine for transformer models on Apple Silicon, paired with a native macOS app for training, quantizing and chatting with local models.

• Inference

A two-part course introducing how large language models work, how they can be trained, and how to use them for scientific research, with slides and hands-on notebooks.

• Tutorials

A tool for defining an AI agent's role in a single YAML file and running it as a CLI chat, an API server, or an autonomous daemon reacting to schedules, file changes and webhooks.

• Agent frameworks

An LLM inference engine built from scratch in C++ and CUDA for a single GPU model, the NVIDIA RTX 5090, serving models over both OpenAI and Anthropic-style APIs.

• Inference

An AWS reference guidance showing how to build and deploy a multi-agent customer-support system using Amazon Bedrock AgentCore and the Strands Agents SDK.

• Agent frameworks
• Hosting

An open protocol and reference runtime that lets an AI agent generate an interactive user interface on demand over MCP, instead of the agent describing options in text.

• Agent frameworks
• MCP servers

A self-hosted proxy that sits between an application and any LLM provider, redacting personal data and secrets and blocking prompt-injection attempts before a request reaches the model.

• LLM gateways
• Security

A desktop IDE for working with several AI coding agents at once, showing multiple chats, a file explorer, git workflows and a browser preview panel side by side.

• Coding agents

A templating language and CLI tool for building structured prompts for large language models by pulling in content from local files and web pages.

• CLI tools

A tool that runs several AI coding-agent sessions in parallel, each in its own Git worktree under a contract, with gates deciding what counts as done before a pull request is created.

• Coding agents

A Claude Code plugin for people who describe what they want and let Claude handle how, covering brand-identity building, project planning as an approved dependency graph, and a creator toolkit.

• Agent skills

A 13-phase automated pipeline that turns a task description into reviewed, tested and committed code, using Claude Code or Codex with adversarial design and security review gates between each phase.

• Coding agents

A Claude Code plugin that indexes a codebase and answers searches by meaning using local embeddings and BM25 keyword matching, instead of plain text grep.

• Agent skills
• RAG

A curated collection of compact behavioral skills that change how AI coding agents plan, verify their own work and avoid repeating mistakes, installable across more than 35 agent harnesses.

• Agent skills

A curated table of AI agent use-case examples across industries such as healthcare, finance and education, each row linking to a related open-source implementation repository and, where available, a written article.

• Curated lists

An MCP server that gives AI coding agents typed, persistent memory plus document and repository search, aimed at DevOps and platform engineers who need an agent to recall past decisions, runbooks and incidents rather than only chat history.

• MCP servers
• Agent memory

An open wire specification letting a separate Guardian Agent inspect what an AI coding agent is about to do and permit, deny or modify that action before it happens over an authenticated channel, with an audit trail that can be reconstructed afterward.

• Agent frameworks
• Security

A toolkit that generates realistic multi-speaker meeting audio from room-impulse-response simulation and HMM-based turn-taking models, producing per-speaker reference signals for training speech separation, enhancement and diarization systems.

• Speech

A command-line security scanner for web applications that combines static analysis, dynamic testing against a running app, and LLM-based code review in one scan, aimed at developers who are not security specialists.

• Security

A vector database library written in C with Python bindings, covering twelve indexing algorithms, five distance metrics, and search features such as hybrid, filtered, geo-spatial and grouped search.

• Databases

An unofficial command-line tool and MCP server that lets a developer or an AI assistant browse, search and ask questions about a GitHub project's documentation through the Zread.ai service, instead of reading the raw source by hand.

• MCP servers
• Documentation tools