# AI Agents · Tech watch [Canonical source]() Systems using models to choose actions, call tools and perform tasks. ## [Discover and install agent skills with Skills.sh]() Skills.sh catalogs reusable skills and simplifies installation for supported coding assistants. Its directory lets developers review use cases before adding capabilities to their workflow. 2026-02-26 · [Markdown]() · [Original resource]() ## [NullClaw: a compact autonomous assistant in Zig]() NullClaw aims to provide compact infrastructure for an autonomous assistant, written in Zig. Its repository makes the project and implementation choices easy to explore. 2026-02-22 · [Markdown]() · [Original resource]() ## [Guide an agent’s interface design with UI UX Pro Max]() This skill gives an agent design guidance and interface choices for multiple platforms. The repository includes style, typography, and color-pairing recommendations to shape an implementation. 2026-02-15 · [Markdown]() · [Original resource]() ## [Rowboat: an AI coworker with persistent context]() Rowboat presents itself as a collaborative assistant with memory and tool integrations. Its repository makes the architecture and integrations available for inspection beyond the product overview. 2026-02-15 · [Markdown]() · [Original resource]() ## [Monty: sandbox AI-generated Python code]() Monty is a Rust-written Python sandbox for running code produced by models. The repository focuses on controlled execution and a runtime designed for agents. 2026-02-11 · [Markdown]() · [Original resource]() ## [Expose Storybook to an agent through MCP]() This article shows how to expose a Storybook-documented React library through a local MCP server. Component manifests let an agent consult design-system rules before generating code. 2026-02-06 · [Markdown]() · [Original resource]() ## [Connect a UI element to its source with React Grab]() React Grab lets you select a visible element in an app and pass its context to a coding agent. It helps locate the corresponding component in the codebase. 2026-02-06 · [Markdown]() · [Original resource]() ## [Claude-Mem carries context across agent sessions]() Claude-Mem captures session activity, compresses it, and brings relevant details into later sessions. Its repository describes persistent memory for several coding agents. 2026-02-04 · [Markdown]() · [Original resource]() ## [Run durable TypeScript workflows with Trigger.dev]() Trigger.dev runs long-lived tasks and agents with retries and concurrency controls. Its TypeScript SDK keeps those workflows close to application code. 2026-01-30 · [Markdown]() · [Original resource]() ## [Vercel’s React best practices organized for agents]() Vercel organizes guidance around major sources of slowness: waterfalls, bundles and unnecessary renders. Prioritization helps agents address costly problems before micro-optimizations. 2026-01-25 · [Markdown]() · [Original resource]() ## [Vibium: give agents browser verification tools]() Vibium exposes navigation, forms, clicks and screenshots through CLI, MCP or client libraries. It uses WebDriver BiDi so agents can verify changes in a real interface. 2025-12-28 · [Markdown]() · [Original resource]() ## [Firecrawl: turn web pages into data for agents]() Firecrawl offers search, scraping and crawling with Markdown, JSON and screenshot outputs. Its API provides an extraction layer for workflows and agents using web content. 2025-08-26 · [Markdown]() · [Original resource]() ## [Mastra: build and observe agents in TypeScript]() Mastra combines tools, workflows, traces and evaluations for building TypeScript agents. The framework supports observing execution and improving behavior through experiments. 2025-07-18 · [Markdown]() · [Original resource]() ## [Mastra 101: learn to build agents inside your editor]() This practical course guides the creation and deployment of Mastra agents. Tools, memory and MCP are introduced through a guided workflow inside the code editor. 2025-06-11 · [Markdown]() · [Original resource]() ## [React Agent Hooks: expose interface state to agents]() This library derives LLM tools from React hooks. Human and agent interfaces can share the same state, with a developer-defined schema controlling state changes. 2025-04-20 · [Markdown]() · [Original resource]() ## [Codex CLI: work on a repository from the terminal]() The repository introduces the Codex CLI coding agent and installation procedures. It provides an entry point to a code-assistance workflow running locally on the machine. 2025-04-17 · [Markdown]() · [Original resource]() ## [An MCP server for debugging Node.js at runtime]() This server exposes the Node.js debugger to assistants such as Cursor and Claude Code. It adds runtime information to the context available for diagnosing problems. 2025-03-29 · [Markdown]() · [Original resource]() ## [Discover and manage MCP servers and skills in VS Code]() This extension combines discovery, installation and management of MCP servers and skills. It makes those resources available to coding agents used alongside the editor. 2025-03-11 · [Markdown]() · [Original resource]() ## [Midscene: describe interface tests in natural language]() Midscene uses a visual agent to perform actions and verify interface results. Tests can be described in YAML or integrated into an existing framework through its APIs. 2025-02-11 · [Markdown]() · [Original resource]() ## [PR-Agent: open-source AI assistance for code reviews]() PR-Agent provides a community-maintained agent for reviewing pull requests. The repository documents setup and distinguishes this open-source project from Qodo’s commercial offering. 2023-07-15 · [Markdown]() · [Original resource]() Page 3 / 3 [Previous]()