Explore the directory

A native KiCAD 10 plugin, built as a single Rust binary, that exposes schematic capture, PCB layout, routing and manufacturing-export tools to Claude and other AI assistants through the Model Context Protocol.

• MCP servers
• Design tools

A package manager that installs and keeps up to date the official AI agent skills that a Python or JavaScript library ships alongside its own releases, so a coding agent uses current APIs instead of outdated training data.

• Agent skills

A collection of sample projects and code artifacts for building with Microsoft Copilot Studio and the M365 Agents SDK, covering authoring, contact-center integration, single sign-on, testing, and custom chat UIs.

• Agent frameworks
• Tutorials

A self-hosted platform that runs a fleet of coding agents, each in its own GPU-accelerated sandbox desktop, coordinated through a spec-driven Kanban board so a team can review and merge their pull requests.

• Coding agents
• Containers

A command-line tool that uses code-embedding models to find near-duplicate implementations across a codebase, catching similar-but-not-identical logic that coding agents and reviewers tend to miss.

• Code quality

A browser-hosted, fully programmable Android simulator for training and evaluating mobile GUI agents, with many parallel instances, deterministic task judges, and results that carry over to real devices.

• AI evals
• Mobile

A long-term memory service for AI assistants that combines a graph database of typed relationships with a vector index, so an assistant can recall the reasoning behind a decision rather than only similar past text.

• Agent memory
• Databases

A single local file that gives Claude, Codex, Cursor and other agents a shared, searchable memory of text, photos and video on Apple Silicon, with no server, account or hosted database.

• Agent memory

A methodology and cross-platform CLI that turns AI coding prompts into structured design contracts with explicit constraints and dependencies, kept in sync with the implementation through reverse synchronization.

• Agent skills
• CLI tools

A tool that generates Go data types and unmarshalling code directly from JSON Schema definitions, validating input JSON against the schema's rules as it decodes.

• CLI tools

A code-intelligence engine that indexes a codebase into a structural knowledge graph of dependencies, call chains and clusters, browsable in an interactive dashboard or queried by an AI agent through MCP tools.

• Agent memory
• Code quality

A free, offline coding environment for local LLM agents, pairing Ollama-served open models with an OpenCode-based terminal interface for classrooms and workshops without a network connection or subscription.

• Coding agents
• Tutorials

A daily-checked catalog of more than 10,000 open-source LLM, agent and local-inference repositories, sorted by how quickly each one is gaining attention rather than by total popularity.

• Curated lists

A C++ library and tutorial for running GPU inference of CNN models with NVIDIA TensorRT, wrapping engine building, caching, and execution behind a small API with no exceptions.

• Inference

BossConsole is a native desktop console for running AI coding agents such as Claude Code, Codex, Gemini or OpenCode, giving them a shared browser, terminal, editor and secrets manager, and exposing the console itself as MCP tools the agent can call.

• Coding agents
• MCP servers

A C++ and CUDA toolkit that trains and serves large language models on NVIDIA GPUs, combining pretraining, LoRA or QLoRA fine-tuning, GRPO or DPO optimization and HTTP-based serving in one system.

• Models
• Inference

A local-first, shared project memory layer for coding agents, accessible through MCP, that keeps session summaries, git history and design decisions searchable across tools and sessions.

• MCP servers
• Agent memory

A multimodal AI agent framework for Go, supporting custom models, tools, memory and middleware for multi-turn conversation, chain-of-thought reasoning and structured output.

• Agent frameworks

A lightweight, real-time debugging tool for AI agents that traces every model and tool call through an OpenAI-compatible proxy, with a local UI for inspecting and analyzing interactions.

• AI evals
• Debugging

A 15-chapter Chinese and English handbook for DeepSeek Harness (dsh), covering installation, plugin development, performance tuning and a comparison of several coding-agent runtimes.

• Books

An orchestration tool for Claude Code that routes tasks across more than 80 specialized agents, using self-learning hooks and hundreds of MCP coordination tools to improve routing over time.

• Coding agents
• Agent frameworks

A multilingual, zero-shot text-to-speech system that clones a voice from a short reference clip and speaks any of fourteen supported languages in that voice, without needing a matching transcript.

• Speech

An enterprise AI gateway that proxies OpenAI, Anthropic, Gemini and self-hosted LLM APIs plus MCP tool calls behind one control plane, with RBAC, audit logs, rate limiting and cost tracking.

• LLM gateways

An AI coding agent, built on opencode, that adjusts its own tactics from session outcomes through a dual-speed self-evolution system, with recursive subagents and a long-running task engine.

• Coding agents