The index of AI agent tooling,
curated by people who use it.
Every coding agent, framework, and eval tool, checked against its docs and repo, with insights from the best field sources ranked by how much new ground they cover. Browse by tag, filter by what matters, and compare like for like.
102 tools tracked · 70 open source · 11 curated insights · refreshed weekly
The wrong agent stack costs you later
Pick the wrong tools and it catches up with you: a tangled stack you tear out and rebuild at real cost, a tool that doesn't do what it promised, a rogue agent in production, and trust lost with your team or your clients. Most lists make this worse, not better. Here's how we keep it from happening.
From the source, not the marketing
Most directories scrape marketing pages, so the specs are wrong before you read them. Specs here are pulled from each tool's own documentation and source repo, not its marketing page, and every entry is stamped with the date it was last refreshed.
What people actually say
Most directories just echo the marketing. We scrape where people actually write about these tools (transcripts, blogs, docs), pull out the strongest claims, and tie each one to the person who made it, so you can weigh it by who said it and where they're coming from.
Tagged, not bucketed
Shove a tool into one bucket and it never matches how you actually think. Tools here carry many tags, so you can combine them to filter the way you choose.
Weekly freshness
Agent tooling shifts every week, and a stale list quietly sends you to dead projects, old pricing, or features that got deprecated. A scheduled job refreshes stars, activity, and the index so nothing rots unnoticed.
How to use this index
Here's the short path to a stack you won't regret. No expertise required.
- Start with who you are, or what you want to build. Pick a role or a goal below and we'll show you a stack that fits.
- Narrow by what matters to you. Open the decision guide to filter by the things you care about, like running it on your own machine, paying nothing, or using your own API key.
- Compare your shortlist. Got two or three candidates? Put them side by side to see how they differ.
- Read before you commit. Check the wiki to see what people who use the tools actually say, beyond the marketing.
Who are you?
Already know your role? Jump to the tools that tend to be in that stack.
What do you want to build?
Pick a goal and we'll show you a stack — the tools that fit together to do the job — with a picture of how they connect.
Write code with AI
I want an AI that writes and edits code with me.
Build my own agent
I want to put an AI agent into my app.
See what my agents do
I want to watch what my AI agents actually do once they're running.
Test and score my agents
I want to test how well my AI behaves before I ship it.
What's a stack? It's the handful of tools that fit together to do a job — like your editor, the AI inside it, and the model behind it. Pick a goal above and we'll draw yours.
Field notes, not just a list
We pull transcripts from the best field videos, lift out the claims that matter, and score each one by how much new ground it covers. The result is a connected map that links tools to the concepts and tradeoffs that define them.
"Persistent memory is the biggest multiplier: a directory that logs corrections, read at session start, means every fix compounds."
fresh take · sourced from field notes