Collections
Tools from the directory grouped around one theme, such as MCP servers or Claude Code add-ons. Each collection lists what the tools do; none of them is a ranking.
Agent Safety & MCP Security
AI agents now run shell commands, call MCP tools and push code. These listings help you decide what an agent may do, check MCP servers before you install them, contain where agents run and what they spend, and keep an auditable record afterwards.
withHuman, MELRA, The MCP Census, CybeDefend, SIwithin, Lights-on Software Factory, Buddy Sandboxes, CoreSpeed, Tenbri, iFixAi
23 toolsClaude Code Tools
Claude Code does the work in your terminal. These are the tools people put around it to run more of it at once, keep it safe, give it memory and feed it better instructions. Each one works with Claude Code, and most also run with Codex or Cursor.
Farol, Corgi, pi-cowboy, Twine, CoIsland, SIwithin, agent-usage-guard, Lights-on Software Factory, CybeDefend, Sphinx, catnap, Skillsync, agent-archive, DocuMemory, Jotbus, Spotnote, Luke, Siteprint, Reticle, Opaline, XTrace, Opper, CoreSpeed
22 toolsMCP Servers & Tools
The Model Context Protocol (MCP) is how Claude Code, Codex, Cursor and other agents connect to outside tools and data. These listings either ship an MCP server you can connect today or help you build, test and run your own. For approval gates and policy checks, see the Agent Safety & MCP Security collection.
NitroStack, Pomerado, Bifrost, CATT, Gauge CLI, The MCP Census, Kerno, Reticle, Context.dev, Zernio, WhatsApp MCP, Etchv, DocuMemory, Glider, Skillstore, ADRs4AI, Statable, TablePro, Hatamoto, Vitals, ProvenMetal, Chiplab
30 toolsAI Coding Agents
Picking a coding agent is half the job. The other half is how you run it: one in your editor, a fleet in parallel worktrees, or a cloud agent that hands you a pull request. Every tool here is already in the directory, with one line on why it's worth a look. For a flat list in directory order, see the AI coding agents best-of list.
Cursor, Devin Desktop (formerly Windsurf), GitHub Copilot, Claude Code, OpenCode, Vani Code Agent, Dropstone, Hazzel, Reason, AutonomyAI, Opengeni, Solid, Farol, Halv, Frink, pi-cowboy, Twine, agent-relay, guilds.run, Agensh, Rinkata, Luke, Whiteboard, walkai-talkai, v0, Bolt.new, Lovable, Replit, Coderblock, Floot
27 toolsAI Agent Infrastructure
The model is the easy part. Shipping an agent means routing calls across providers, seeing what it did, giving it memory, feeding it clean data and giving it somewhere to run. These are the pieces, grouped by job, each with one line on what it does.
Hopscotch, Opper, Bifrost, Navige, RunInfra, Inferock, Lumabri, Latitude, Promptic, Cekura, Weir, Costura, Maximem Synap, Busabase, NOAN, Glider, KiviDB, Context.dev, Invofox, Sygal, Nace, Omnara, ZooWork, Durable Actors, ego lite, pw-repl, Braus
All tools A to Z · Best-of lists · Head-to-head comparisons · Categories
The 2 biggest AI stories, every morning.
One short email: the two stories that matter, and why.
You're in.
The Daily AI Brief will land in your inbox soon. If you don't see it, check Promotions or Spam and move it to your main inbox.