> Docs index for agents: https://webular.dev/llms.txt

# Docs

Every doc lives in the repo. Each link goes to the doc on GitHub. Pages on this site have a Markdown copy: add `.md` to the address.

## Start here

- [Install channels](https://github.com/srinitude/webular/blob/main/docs/install.md): every way to install webular besides npm.
- [How webular works](https://github.com/srinitude/webular/blob/main/docs/how-it-works.md): each building block and what it does for you.
- [Why webular](https://github.com/srinitude/webular/blob/main/docs/why-webular.md): where webular differs from hosted rivals, and where they do better.
- [Benchmarks](https://github.com/srinitude/webular/blob/main/docs/benchmarks.md): scores against other web research tools, losses included.
- [Benchmarks by peer](https://github.com/srinitude/webular/blob/main/docs/benchmarks-peers.md): webular against each peer on the tasks both answered.
- [How to read the benchmarks](https://github.com/srinitude/webular/blob/main/docs/benchmarks-guide.md): what was measured, why, and every term in plain words.
- [How the benchmarks are run](https://github.com/srinitude/webular/blob/main/docs/benchmarks-method.md): the method, how to run it again, the raw data rules, and outside scores.
- [Command parity](https://github.com/srinitude/webular/blob/main/docs/command-parity.md): each command's rival endpoints, whether the bench scores it, and the metric that fits.

## Use it

- [Command reference](https://github.com/srinitude/webular/blob/main/docs/commands.md): what each command does.
- [Agent contract](https://github.com/srinitude/webular/blob/main/docs/agent-contract.md): what an agent needs from the CLI, MCP server, plugin, and skills.
- [Browser mode (Cua)](https://github.com/srinitude/webular/blob/main/docs/cua-browser-mode.md): how webular drives a throwaway browser window.
- [Reliability](https://github.com/srinitude/webular/blob/main/docs/reliability.md): retries, dead pages, and sites that will not answer.
- [Research factors](https://github.com/srinitude/webular/blob/main/docs/research-factors.md): each factor that makes web research correct, fast, cheap, and repeatable, with its guard or its gap.

## Build on it

- [Architecture](https://github.com/srinitude/webular/blob/main/docs/architecture.md): how a command runs and which XState machines model it.
- [Development](https://github.com/srinitude/webular/blob/main/docs/development.md): read before you change webular or run its tests.
- [Build and run](https://github.com/srinitude/webular/blob/main/docs/build-and-run.md): run from source, use the bundles, or build the executable.
- [Bug classes](https://github.com/srinitude/webular/blob/main/docs/bug-classes.md): each kind of bug webular can hit, where it shows up, and what guards against it.
- [Mise tasks](https://github.com/srinitude/webular/blob/main/docs/tasks.md): every `mise` task, what it does, and what it runs first.
- [Best practices](https://github.com/srinitude/webular/blob/main/docs/best-practices.md): each practice webular follows, with its source and check.
- [Research ledger](https://github.com/srinitude/webular/blob/main/docs/research/README.md): the papers behind webular's design choices, and the ranked changes each topic suggests.
- [Research status](https://github.com/srinitude/webular/blob/main/docs/research.md): how many papers and repos were read, and which ranked changes are applied, rejected, or open.
- [Jev in webular](https://github.com/srinitude/webular/blob/main/docs/jev.md): how to set up the Jev key on any OS, and each route webular takes to Jev for its judgment calls.
- [Docs rules](https://github.com/srinitude/webular/blob/main/docs/AGENTS.md): the rules for writing these pages.