tools.simonwillison.net
GitHub - tobi/qmd: mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local - tobi/qmd
GitHub - ComposioHQ/awesome-claude-skills: A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows - ComposioHQ/awesome-claude-skills
AI Can't Read Your Docs
Designing software that today's AI coding agents can actually use.
Fission-AI/OpenSpec: Spec-driven development for AI coding assistants.
Spec-driven development for AI coding assistants. Contribute to Fission-AI/OpenSpec development by creating an account on GitHub.
Deta Surf
Agent
Code Mode: the better way to use MCP
It turns out we've all been using MCP wrong. Most agents today use MCP by exposing the "tools" directly to the LLM. We tried something different: Convert the MCP tools into a TypeScript API, and then ask an LLM to write code that calls that API. The results are striking.
advanced-context-engineering-for-coding-agents/ace-fca.md at main · humanlayer/advanced-context-engineering-for-coding-agents
Contribute to humanlayer/advanced-context-engineering-for-coding-agents development by creating an account on GitHub.
AI SDK Tools
NPM tooling
GPT-5 Thinking in ChatGPT (aka Research Goblin) is shockingly good at search
“Don’t use chatbots as search engines” was great advice for several years... until it wasn’t. I wrote about how good OpenAI’s o3 was at using its Bing-backed search tool back …
Spec-driven development with AI: Get started with a new open source toolkit
Developers can use their AI tool of choice for spec-driven development with this open source toolkit.
Cline + LM Studio: the local coding stack with Qwen3 Coder 30B
An autonomous AI coding assistant for VS Code with Plan/Act modes, terminal execution, file editing, and Model Context Protocol for custom tools
What makes Claude Code so damn good (and how to recreate that magic in your agent)!?
Claude Code is the most delightful AI agent/workflow I have used so far. Not only does it make targeted edits or vibe coding throwaway tools less annoying, ...
too many model context protocol servers and LLM allocations on the dance floor
This blog post intends to be a definitive guide to context engineering fundamentals from the perspective of an engineer who builds commercial coding assistants and harnesses for a living.
Just two weeks ago, I was back over in San Francisco, and there was a big event on Model Context Protocol
too many model context protocol servers and LLM allocations on the dance floor
Useful reminder from Geoffrey Huntley of the infrequently discussed significant token cost of using MCP. Geoffrey estimate estimates that the usable context window something like Amp or Cursor is around …
GitHub - tobi/try: fresh directories for every vibe
fresh directories for every vibe. Contribute to tobi/try development by creating an account on GitHub.
MindMap AI: Create AI-Powered Mind Maps Instantly
Create instant AI-powered mind maps with MindMap AI. Featuring Copilot Chat, co-creation, multi-format input, and easy sharing. Revolutionize your brainstorming process today!
Claudia
Transform your AI coding workflow with a beautiful GUI that makes managing Claude sessions, creating custom agents, and tracking usage effortless.
LL3M: Large Language 3D Modelers
aicodeprep-gui: The Fast Context Maker
Effortlessly generate a context block to quickly paste into any AI chat. Works on any OS, from any editor. Removing the friction between your project/repo and AI. This is not meant to replace Agent software.
When a Jira Ticket Can Steal Your Secrets
Zenity Labs describe a classic lethal trifecta attack, this time against Cursor, MCP, Jira and Zendesk. They also have a short video demonstrating the issue. Zendesk support emails are often …
How Kimi 2 Became One of the Best Tool-Using Models
The Moonshot AI team synthesized thousands of tools, agents, users, and sessions to build a library of training data.
Working Effectively with AI Coding Tools like Claude Code
A practical guide to working effectively with AI coding tools like Claude Code, covering mindset shifts, quality control strategies, and team collaboration workflows for modern software development.
Announcing Toad - a universal UI for agentic coding in the terminal
I’m a little salty that neither Anthropic nor Google reached out to me before they released their terminal-based AI coding agents.
DSPy: Build and Optimize Agentic Apps - DeepLearning.AI
Build, debug, and optimize AI agents using DSPy and MLflow.
My favorite use-case for AI is writing logs
One of my favorite AI dev products today is Full Line Code Completion in PyCharm (bundled with the IDE since late 2023). It’s extremely well-thought out,...
Become a command-line superhero with Simon Willison’s llm tool
Christopher Smith ran a mini hackathon in Albany New York at the weekend around uses of my LLM - the first in-person event I'm aware of dedicated to that project! …
Copilot VS Code Customizations
VS Code AI Customization: Learn to use custom instructions, prompt files, and custom chat modes to personalize AI code generation, reviews, and chat responses.
Tools: Code Is All You Need
The solution to agentic flows was code all along.
Hooks - Anthropic
Customize and extend Claude Code's behavior by registering shell commands