Explore the directory

A file-based, agents-first kanban board with a single-binary CLI and text interface, using atomic claim-and-move operations and installable agent skills so multiple AI agents can pick up tasks and work a shared board in parallel without clashing.

• CLI tools
• Workflow automation

A self-hosted MCP server that connects Claude Desktop and other MCP clients to Google Drive, Docs, Sheets, Slides, and Calendar, with 130 tools for file management, rich document editing, sharing, and multi-step workflows under the caller's own Google credentials.

• MCP servers
• APIs

A pre-release .NET terminal workspace for agentic coding that manages model-provider setup, project navigation, prompt attachments, and durable sessions, working across Codex, Copilot, Grok, OpenAI, Anthropic, and other providers behind one keyboard-first interface.

• Coding agents
• Terminals

Research code for two visual tokenization methods, BSQ-ViT and its successor L24SQ-ViT, that use spherical vector quantization instead of a learned codebook to tokenize images and video.

• Models

A running list of low-bit model quantization research papers from 2020 through 2026, organized by year, covering LLMs, vision-language-action models, and mixture-of-experts.

• Curated lists
• Papers

A Python framework for evaluating safety risks in multi-agent systems, wrapping an existing MAS to run structured checks across 20 risk types such as prompt injection, tool misuse, and sandbox escape, and producing evidence-backed safety reports.

• AI evals
• Security

A framework-agnostic Python implementation of the Agent2Agent protocol that turns any agent into an A2A server, with separate storage, broker, and worker components so the task-executing worker can run on its own machine or process.

• Agent frameworks

A free, open-source desktop AI coding workspace for microcontroller development that compiles and uploads Arduino, ESP32, and similar projects, and reads live serial output, all through an integrated AI coding agent.

• Coding agents
• Editors

A Graph Neural Network library built on Apple's MLX framework, designed to train and run GNNs on Apple Silicon's unified CPU and GPU memory, with reported speedups over other frameworks on large graphs.

• Models
• Libraries

A minimal template for building an OpenAI-powered AI agent that compiles to a contract and deploys to Phala Network's decentralized, TEE-secured serverless cloud rather than a conventional FaaS provider.

• Agent frameworks
• Hosting

A universal, model-agnostic operating harness that installs shared project rules, a definition of done, and evidence-recording checks into a repository so any AI coding agent runs the real checks, records proof of its work, and leaves a handoff another session can verify.

• Agent skills
• Code quality

A pure MLX reimplementation of the YOLO26 object detection model for Apple Silicon, with no PyTorch dependency at runtime, covering detection, tracking, segmentation, and pose.

• Models

An open-source realtime media server in Go that handles the WebRTC transport, barge-in, and streaming speech-to-text, LLM, and text-to-speech pipeline behind a voice agent, so a developer keeps their own prompts, tools, and models while StreamCore owns the latency-sensitive path.

• Speech
• Backend

A Rust and CUDA inference engine that streams a giant Mixture-of-Experts model's routed experts from NVMe storage per token, letting models far larger than available VRAM run on consumer GPUs by keeping only routing and attention resident in memory.

• Inference

A Kubernetes-based platform for deploying and routing GPU-accelerated inference, streaming, and batch workloads at scale, handling function lifecycle, invocation routing, GPU cluster integration, and observability.

• Inference
• Hosting

A local browser-based terminal grid that runs several coding-agent CLI sessions side by side, color-coding each cell as working, done, or needing you, with tmux persistence, git-worktree isolation per agent, and a phone push notification when a turn finishes.

• Coding agents
• Terminals

A curated guide of DeepSeek prompting techniques in Chinese, covering the V4 model's thinking-mode settings, official prompt libraries, and ready-to-use templates for analysis, math, coding, and deep-research tasks.

• Curated lists

A reference monitor for AI coding agents that intercepts every shell command, file operation, and web request through Rust hook binaries and Cedar policies, blocking exfiltration and destructive actions across Claude Code, Cursor, Copilot, and other agent tools.

• Agent skills
• Security

A speculative-decoding method for faster LLM inference that drafts a whole token tree in one parallel pass while preserving causal conditioning between branches, then verifies the entire tree against the target model in a single forward pass.

• Inference

A course and project collection of more than 15 autonomous AI agents built with frameworks such as Agno, Microsoft AutoGen, and OpenAI Swarm, covering reasoning, retrieval-augmented generation, multi-agent collaboration, vision, and persistent memory.

• Tutorials
• Curated lists

A 27-chapter, code-first Python tutorial that builds an autonomous AI agent from scratch, covering the agent loop, tools, memory, MCP, and a multi-platform chat gateway.

• Agent frameworks
• Tutorials

An open-source knowledge base of 301 coding-agent skills across 22 subject categories, from graduate-level theory frameworks and algorithms to Taiwan-specific business and tax knowledge, packaged as Claude Agent Skill Markdown files.

• Agent skills

An MCP server that lets an AI agent see and control a real iPhone through macOS iPhone Mirroring, describing on-screen elements with tap coordinates and executing taps, swipes, and typed text through dozens of tools.

• MCP servers

An open-source, self-hostable desktop AI agent that plans and self-corrects in a streaming think-act loop, designs and runs its own visual workflows, and streams generative UI such as KPI boards and slide decks into the chat.

• Agent frameworks