Unl, the open-source why agent for your coding agents.
Run one command in a project. Unl reads the rules you already gave your coding agent, shows you what it found. You choose what to keep as decisions with their reasons. Supported hooks give your agent relevant decisions before it acts.
npx unlimitless initRequires Node.js 20 or later. Hook support differs across Claude Code, Codex and Cursor. Read the compatibility table.
Sign in to use your hosted record with a supported AI. To use Unl locally in a project, run the command above.
Already using Unl locally? This connection does not yet share your local changes or transfer your history automatically.
You'll be asked to sign in to Unl the first time your tool uses it. In Claude Code, if nothing opens, run /mcp.
Tell your agent
Read unlimitless.ai/start.md, set up Unl, and show me the decisions you find.Coding surfaces
Same decisions, whichever model or tool you use. Also works with Claude Desktop, Cline, Kilo Code, opencode and any MCP client
Unl gives your AI what you decided, and why, when it matters, in every tool you use. See pricingWhat Unl keeps, and how to delete it
Turn on developer mode, add Unl's URL as a connector, sign in.
Whenever your own work comes up. The app calls Unl when a turn needs your decisions.
Settings, then Connectors: paste Unl's URL and sign in.
Whenever your own work comes up. The app calls Unl when a turn needs your decisions.
Ask the bot to add the MCP server at Unl's URL, named unl, then Authorize.
Your decisions and why. Available when your agent asks Unl.
Viktor reaches Unl through its API, with a personal key from your portal.
Your decisions and why. Available when your agent asks Unl.
npx unlimitless connect --codexAdds Unl, puts its tools in view and opens the sign-in. If it doesn't, run codex mcp login unl.
Whenever your agent reaches for your decisions. Point its rules file at unl.md, so it knows when to ask.
Full stepsnpx unlimitless connectAdds Unl, signs you in once and wires the hook that brings your decisions in before each action.
Every turn, automatically. A hook hands your agent what bears before it answers.
Full stepsMuse Code does the work. Unl carries your why into the work.
Your decisions and why. Available when your agent asks Unl.
Opens Cursor with Unl ready to add. Sign in when it asks.
Whenever your agent reaches for your decisions. In the Cursor CLI, npx unlimitless connect --cursor also brings them in as each session starts.
Full stepsAdd an MCP server named unl with Unl's URL, then authorize.
Your decisions and why. Available when your agent asks Unl.
Opens VS Code's install prompt. Sign in when it asks.
Whenever your agent reaches for your decisions. Copilot calls Unl in Agent mode when a turn needs them.
Full stepsSettings, then Connectors: paste Unl's URL, sign in and approve.
Whenever your own work comes up. The app calls Unl when a turn needs your decisions.
Add custom MCP in Devin Desktop; sign in on the first tool call.
Whenever your agent reaches for your decisions. Point its rules file at unl.md, so it knows when to ask.
Add Unl under Remote Servers, then approve the first tool call.
Whenever your agent reaches for your decisions. Point its rules file at unl.md, so it knows when to ask.
Add Unl to your Kilo config; the sign-in comes to you on reload.
Whenever your agent reaches for your decisions. Point its rules file at unl.md, so it knows when to ask.
Add Unl to your opencode config, then sign in from the shell.
Whenever your agent reaches for your decisions. Point its rules file at unl.md, so it knows when to ask.
Add Unl by file with serverUrl, restart, then authenticate.
Whenever your agent reaches for your decisions. Point its rules file at unl.md, so it knows when to ask.
https://api.unlimitless.ai/mcpAdd it as a remote MCP server. Your sign-in finds your world.
Whenever your agent reaches for your decisions. Point its rules file at unl.md, so it knows when to ask.
Start any new chat by saying connect to Unl.
You should not need this. It is here for the session where your AI does not bring Unl in on its own. The same block everywhere. Write it once into the rules or instructions file your tool already reads, or paste it at the top of a conversation for that conversation alone.
When my own work is in play, check with Unl first, and treat what it returns as my settled decisions.
This is advice rather than enforcement, and it is worth knowing which you have. A tool can skip an instruction and Unl has no way to insist. If a session ever answers against something you decided, ask it what you decided, and Unl brings it in.