Explore the directory

A lightweight prompt file for GitHub Copilot that makes the agent respond in terse caveman-style speech, cutting a large share of output tokens while keeping technical accuracy, without installing the original package.

• Agent skills

An open-source CLI and GitHub Action that statically reviews what a pull request changed about an AI agent's tool permissions and capabilities, before that change merges.

• Security
• CI/CD

A Chinese-language interview-preparation knowledge base for AI agent engineering roles, organized around how interviews actually ask about LLM fundamentals, prompt and context engineering, RAG and tool use.

• Tutorials
• Books

A survey and curated paper list on audio-visual intelligence, covering how foundation models jointly perceive, generate and interact using both sound and vision.

• Curated lists
• Papers

An on-device speech infrastructure library in C++17 for Linux, Windows and Android, providing voice activity detection, streaming speech-to-text, speaker diarization, text-to-speech and a voice-agent pipeline.

• Speech
• Libraries

A governance layer for autonomous AI work where a single YAML file declares an agent's mission, spending limits and allowed capabilities, and every task is planned, budget-checked, audited and recorded.

• Agent frameworks
• AI evals

A monorepo for Maple, a confidential AI research and chat application with a desktop Agent Mode, its client SDKs, a local OpenAI-compatible proxy, and the OpenSecret backend behind it.

• Inference
• LLM gateways

An AST-powered code intelligence engine that indexes a codebase into a persistent knowledge graph with Cypher queries, cross-file call resolution and hybrid semantic search across 62 languages.

• Agent memory
• Databases

A Rust-native personal assistant and coding agent, packaged as a single stripped binary with no Python or Node.js runtime, running a ReAct tool loop across 16 LLM providers.

• Coding agents
• Terminals

The local connector for TODO for AI that gives your machine's shell, files and browser to AI-driven tasks, running commands, editing files and documents, and tracking git-aware file changes.

• Agent frameworks
• Workflow automation

Companion Colab notebooks for the Manning Publications book Domain-Specific Small Language Models, covering small-model training and optimization.

• Tutorials
• Books

A local desktop app for orchestrating and supervising multiple AI agents, letting a user drag a workflow onto a canvas and watch LangGraph run it against tools such as Claude Code, Codex, Ollama and MCP.

• Coding agents
• Agent frameworks

Reference architectures, code examples and practice scenarios for a four-hour O'Reilly live training that prepares learners for Anthropic's Claude Certified Architect: Foundations exam.

• Tutorials

A native streaming speech-recognition model that transcribes audio of unlimited length continuously, with a rolling key-value cache that keeps memory and latency bounded even in 24-hour operation.

• Speech

A CLI tool that transforms an OpenAPI 3.x specification into a Terraform Provider Code Specification, which can then be used to generate Terraform provider code.

• APIs
• Hosting

A tool that predicts whether a given GGUF language model will run on your hardware and how fast, then builds a quantized file customized to your machine and prints the exact llama.cpp command to run it.

• Models
• Inference

A cross-platform Electron desktop app that coordinates several computers on a local network to run distributed LLM inference together, using llama.cpp's RPC backend.

• Inference

A tool that automatically saves decisions, constraints, bugs and todos from Claude Code chats into a JEVMEM.md file, then feeds the relevant lines back into context in later sessions.

• Agent memory

An open-source workflow system that turns a raw OpenAI Codex agent harness into a repeatable engineering environment, with reusable skills, quality gates, session memory and cross-harness adapters.

• Coding agents
• Agent skills

A research method for adapting true 1-bit large language models after training, using sparse XOR bitmask patches that flip individual binary weights instead of requiring gradients or continuous weights.

• Models
• Papers

An open-source platform for building teams of AI agents that automate complex tasks, configured through a visual node editor rather than code, built on top of the AutoGen framework.

• Agent frameworks

A Ruby framework, made for Rails but usable in plain Ruby, for building observable, cost-controlled LLM pipelines with automatic model fallback, retries and consensus-based decisions.

• Agent frameworks
• Libraries

A Python SDK and CLI that exposes an existing AI agent, whether a CLI, a workflow engine or a Python framework, as an A2A protocol server in a few lines of code.

• Agent frameworks

A starter kit that deploys production-ready generative-AI infrastructure on Amazon EKS with a single CLI command, including LLM serving engines, an AI gateway, vector databases and observability.

• Containers
• Hosting