Knowledge Share
Technical articles, tutorials, and insights
One Open Source Project a Day (No. 238): Impeccable — Teaching Every AI Coding Tool to Have Taste
Impeccable is a design language tool for AI coding assistants, offering 24 commands and 59 deterministic detection rules covering the full design workflow — from product-context gathering and visual system construction to accessibility/performance audits. Supports Claude Code, Cursor, Codex, Gemini CLI, and a dozen other tools. The core engine is a standalone binary that runs detection without needing an LLM. Apache-2.0 License, 81.3k Stars.
One Open Source Project a Day (No. 237): DeepSeek Bot — Turning DeepSeek Harness Into a Team of Bots With Memory, Group Chat, and Task Handoff
DeepSeek Bot (DS Bot) is a bot plugin for DeepSeek Harness (DSH) that turns DSH into a team of long-lived bots — each bot is really an independent DSH session with persistent cross-session memory, supporting group chat collaboration, @-mention task handoff, and a Main Bot that oversees everything. Its design explicitly credits ideas (not code) from OpenAI Codex, OpenCode, Hermes Agent, and others. Apache-2.0 License, 1.9k Stars.
One Open Source Project a Day (No. 234): CC Switch — One App to Manage Providers, MCP, Skills, and Prompts Across Ten AI Coding Tools
CC Switch is a cross-platform desktop app that unifies API provider configuration across ten AI coding tools — Claude Code, Codex, Gemini CLI, Grok Build, OpenCode, and more. It supports one-click switching, local request routing with format conversion, multi-provider aggregation, and centralized management of MCP, Skills, and Prompts — ending the era of hand-editing JSON/TOML/YAML config files. Built with Tauri 2 + Rust + React 18. MIT License, 142.8k Stars.
One Open Source Project a Day (No. 232): DSH Desktop — Even the Desktop Shell Itself Is a Plugin, 30k+ Stars for the DeepSeek Harness Desktop Client
DSH Desktop is a community-built desktop client for DeepSeek Harness (DSH), targeting Windows/macOS. Its core philosophy is "everything is a plugin, including the desktop shell itself" — window, tray, terminal, and updater are all wired in as DSH plugins rather than patching upstream source. Ships a built-in plugin marketplace, mobile remote control, and a first-run setup wizard. MIT License, 30.3k Stars.
One Open Source Project a Day (No. 231): MiniMind — Train a 64M-Parameter LLM From Scratch in 2 Hours for About $0.43
MiniMind is a fully from-scratch, native-PyTorch LLM training project whose core claim is "train a 64-million-parameter language model from scratch in 2 hours for about ¥3." It covers the complete modern training pipeline — pretraining, SFT, LoRA, DPO, RLAIF (PPO/GRPO/CISPO), Agentic RL, and knowledge distillation — and spawns sibling projects for vision, multimodal, diffusion, and linear attention. 63.4k Stars, Apache-2.0 License.
One Open Source Project a Day (No. 230): HandRaw-Style — Numbering 327 Hand-Drawn Styles, 165 Layouts, and 36 Color Palettes So AI Art Stops Drifting Every Time
HandRaw-Style is a "numbered gallery of hand-drawn art styles paired with a bilingual AI-prompt-generation skill." It catalogs 327 hand-drawn illustration styles, 165 layout templates, and 36 classic monochrome color themes, all numbered — users just say a code plus a topic and get tested bilingual prompts, solving the "vague style description, every generation drifts" problem. It supports smart recommendation, precise selection, poster design, article illustration, photography planning, and more modes. 4.7k Stars.
One Open Source Project a Day (No. 228): AX — Google's Open-Source 'Kubernetes for Agents,' Orchestrating Billions of Agent Tasks with Declarative YAML
AX (google/ax) is Google's open-source, high-throughput, declarative agent orchestration runtime, built to run billions of autonomous agent workloads in a single cluster. It borrows Kubernetes' mental model, describing agent tasks with three core primitives — Task, Workspace, and Model — running on top of the Agent Substrate sandbox, with a kubectl-shaped CLI (apply/get/watch/ssh/suspend/resume). 11,600+ Stars, Apache-2.0 License, still in Alpha.
One Open Source Project a Day (No. 227): Strands Agents Harness SDK — From Hand-Rolled Agent Loops to a Production-Ready Agent in One Call
Strands Agents (strands-agents/harness-sdk) is an open-source agent SDK from the AWS team, shipping both Python and TypeScript implementations. Its standout feature is Strands Harness — a fully assembled, production-grade agent you get from a single create_harness() call, with built-in context management, session persistence, long-term memory, skill loading, and multi-model support, while still returning a fully customizable native Agent object. 8,300+ Stars, Apache-2.0 License.
One Open Source Project a Day (No. 223): TeamAI-CLI — Tencent's Team-Level AI Agent Middleware, Turning Individual AI Skills Into Shared Team Assets
TeamAI-CLI is Tencent's open-source team collaboration middleware. It isn't another AI coding assistant — it's a meta-management system that lets already-installed tools like Claude Code, Codex, and Cursor share skills, rules, and knowledge bases across a team. It syncs team standards through a push/pull workflow, builds a codebase knowledge graph, and uses friction-driven signals to capture and share hard-won experience automatically. 4.8k Stars, MIT License.
One Open Source Project a Day (No. 224): ARTEMIS — Google's Open-Source Mobile AI Automation Framework, Letting AI Assistants Operate Phones Like a Human
ARTEMIS is Google's open-source Android automation framework that turns natural-language instructions into reliable mobile automation. It offers two execution modes — Flash (fast reactive) and Pro (multi-agent planning and verification) — and integrates natively with Claude Code, Antigravity, Codex, and other AI IDEs via MCP, achieving 99%+ task completion on the AndroidWorld benchmark. 8.1k Stars, Apache-2.0.
One Open Source Project a Day (No. 225): NanoJev — A 0.6B Parallel Decision Model That Outputs Probability Distributions Instead of Generating Tokens
NanoJev is a lightweight recreation of the "Jev" parallel decision model system. Built on a Qwen3-0.6B backbone with dedicated decision heads, it takes states and questions as input and outputs complete probability distributions directly — with zero output-token decoding. It supports three decision head types (dynamic choice, boolean, ordered score) and has been validated on maze navigation and Snake game benchmarks. 954 Stars, MIT License.
One Open Source Project a Day (No. 226): AIO Sandbox — Browser, Shell, File, MCP, and VSCode Server in One Docker Container
AIO Sandbox (agent-infra/sandbox) is an all-in-one AI agent sandbox environment that unifies browser automation, a shell terminal, file operations, MCP servers, and VSCode Server in a single Docker container. Its core design is a unified filesystem shared across all tools. It ships official Python/TypeScript/Go SDKs, four built-in ready-to-use MCP servers, and has verified integrations with Browser Use, LangChain, and OpenAI Assistants. 6.0k Stars, Apache-2.0 License.