Teaches developers to guide and evaluate AI coding agents across the software lifecycle. Stanford's CS146S connects agent internals and context engineering with code review, security, and contributions to real projects.
AI Agent2025
Provides AI coding agents with practical guidance for Expo, React Native, and EAS workflows, from navigation and native UI to upgrades and releases. Maintained by the Expo team, it helps agents apply official documentation and CLI guidance accurately.
AI Infra2026
Compresses tool outputs, logs, files and RAG chunks locally before they reach the LLM to reduce token usage while caching originals for on-demand retrieval. Provides proxy/library/wrap modes, JSON- and code-aware compressors, and reversible compression.
AI Coding2026
Provides installable playbooks for AI coding agents, with local catalog search, agent-chosen skill stacks, and reviewable plans before changes. The core preview flow does not rank skills or apply them.
AI Coding2026
Provides a rule set and agent skill that lets AI coding assistants review and improve SwiftUI code for modern APIs, performance, accessibility, and maintainability. Packs checks for deprecated APIs, data flow, navigation, and accessibility tailored to mistakes LLMs commonly make.
AI Agent2026
Provides a local-first desktop workspace that runs and coordinates AI agents across your files, browser, and third-party tools with a shared, editable memory. Offers built-in models or bring-your-own-keys, one-click OAuth to 100+ integrations, and browser-driven agent automation.
MCP Client2026
Indexes a repository into a local, queryable index (graph, git, docs, decisions, code health) and exposes task-shaped MCP tools so coding agents and developers get cited answers, symbol-level blast radius, test impact, refactoring plans and dead-code detection; self-hosted (AGPL-3.0) and needs no API key for deterministic analysis.
AI Agent2026
A curated collection of Korea-focused AI agent skills that enable agents to perform local tasks — ticket booking, public-data lookups, e-commerce and messaging integrations — via prebuilt connectors and an optional hosted proxy for API keys and fallbacks.
AI Agent2026
Turns an Obsidian vault into durable, cross-session memory for coding agents, updating linked notes as conversations and sources arrive. Its optional shared logbook lets multiple agents record work in a plain folder.
AI Agent2026
Runs and manages persistent teams of coding agents (Claude Code, Codex, Pi) locally — boots named seats from a YAML topology and provides a daemon, CLI and TUI to monitor, snapshot, evolve and coordinate agent workspaces and terminals.
AI Agent2026
Turns image, video, and visual-brand work into workflows callable by AI coding agents, spanning character identity, product photography, brand systems, website building, and video analysis.
MCP Client2026
Connects coding agents to local reverse‑engineering tools so an agent can inspect binaries, apps, and websites and return traced code, evidence, and reconstruction workflows. Supports native (Ghidra/Hopper/IDA), JavaScript/Electron, .NET, APKs, firmware and network captures via an MCP server and CLI.