Knowledge Share
Technical articles, tutorials, and insights
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. 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.
One Open Source Project a Day (No. 208): Kaneo — Minimal Self-Hosted Project Management
Kaneo is a minimal, self-hosted project management tool with a built-in MCP server for AI tool integration, native GitHub sync, and Board/List dual views sharing a single data source. Its design philosophy fits in one sentence — "All you need. Nothing you don't." 8.9k Stars, MIT license, an open-source alternative to Jira and Linear.
One Open Source Project a Day (No. 209): holaOS — An Agent-Native Local Workspace
holaOS is an open-source agent-native workspace where app interfaces and AI agents live side by side on the same screen. It connects 100+ integrations, MCP servers, Claude Code, Codex, and a shared local memory system. Supports IM context from Slack, Feishu, DingTalk, and WeChat. Local-first by architecture, data never leaves your device. 11.1k Stars, Modified Apache 2.0.
Code Agent Anatomy (23): Extending from Scratch — Connecting to the MCP External Tool Ecosystem
MCP (Model Context Protocol) is a protocol standard for connecting agents to external tool services. With it, the agent can call Tavily for web search, Context7 for documentation lookup, GitHub for repository operations — any service implementing the MCP protocol can be plugged in. This article explains how MCP is connected, covering the complete chain from configuration to model invocation of an external tool.
Code Agent Dissection (07): How Are External Tools Integrated? A Deep Dive into MCP
A deep dive into MyCodeAgent's MCP integration: optional dependencies, config discovery, stdio/HTTP transport, Adapter disguising remote tools as local Tools, and result normalization into a unified protocol. Understand how external capabilities enter the same tool pipeline, and why 'registered in the registry' and 'allowed to execute' are two separate concerns.
Open Source Project #188: AI Agents in Depth — Li Bojie's Complete Open-Source AI Agent Book, 10 Chapters, 95 Experiments, 35k Stars
Li Bojie's fully open-source book 'AI Agents in Depth: Design Principles and Engineering Practice.' Core formula: Agent = LLM + Context + Tools. 10 chapters building progressively: context engineering, user memory and knowledge bases, MCP tool protocol, coding agents, evaluation frameworks, model post-training (SFT/RL), continuous evolution, multimodal interaction, multi-agent collaboration. 95 hands-on experiments, 13 language versions, free PDF/EPUB download. Python, Apache-2.0, 35k Stars.
Open Source Project #186: Open Ontologies — Rust MCP Server for AI-Native Ontology Engineering, 70+ Tools, Single Binary, No JVM, Builds in 5 Minutes What Takes 4 Hours in Protégé
The Tesseract Academy's Rust MCP server that turns ontology engineering into AI-agent-callable capabilities. 70+ tools covering validation, reasoning, alignment, lifecycle governance, and RAG augmentation. Three-layer architecture: Dynamics (atomic ops + OWL-RL), Causal (causal identification), Planner (PDDL compilation). Tauri 2 + React 19 Studio desktop app with AI chat panel for building production OWL ontologies. Pizza ontology benchmark: 96% coverage in 5 minutes vs. 4 hours manual in Protégé. OAEI anatomy alignment precision 0.960 (3rd globally). Built-in marketplace of 33 standard ontologies including full IES support for UK National Digital Twin Programme. 341 Stars, MIT.
Open Source Project #182: Graphify — Turn Your Entire Codebase into a Queryable Knowledge Graph for AI Coding Assistants
YC-backed open-source tool that uses tree-sitter AST to parse code locally and an optional LLM backend to process docs, PDFs, images, and video — building everything into one queryable knowledge graph. AI assistants traverse the graph instead of grepping. Every edge is tagged EXTRACTED/INFERRED/AMBIGUOUS. Incremental updates patch only changed files in ~0.8 seconds. Supports Claude Code, Cursor, Codex, and 15+ other AI tools via MCP. Optional Neo4j/FalkorDB backends. 101k Stars, Apache-2.0 + MIT.
Open Source Project #166: worldmonitor — Real-Time Global Intelligence Dashboard with 73k Stars, AI-Powered Geopolitical Monitoring
AI-powered global real-time intelligence platform. 500+ curated news feeds, dual map engine (3D globe + WebGL flat map), 56 map layer types, cross-stream correlation, Country Instability Index (CII v8), finance radar (29 exchanges), local AI via Ollama, 6 site variants, Tauri 2 desktop app, MCP server. TypeScript + Rust, AGPL-3.0, 73k+ Stars.
Open Source Project #163: wigolo — Zero API Key, $0/Query Local-First Web Intelligence for AI Agents, Compared Against Tavily / Exa / Firecrawl
Local-first web intelligence layer for AI agents. 10 tools: search, fetch, crawl, extract, cache, find_similar, research, agent, diff, watch. 18 direct search engine adapters, ML reranking, byte-pinned source provenance, local semantic cache, no API keys required, $0/query. Comparison with Tavily, Exa, Firecrawl. 1.2k+ Stars, AGPL-3.0.
Open Source Project #162: code-review-graph — Build a Structural Map of Your Codebase to Cut AI Review Tokens by 82x
Local-first code intelligence graph. Tree-sitter parses the AST, SQLite persists the graph, 30 MCP tools surface precise context. Blast-radius analysis traces change impact chains, incremental updates complete in 2 seconds, 40+ languages supported. Benchmarked 82x median token reduction (528x max). 19.7k+ Stars, MIT.