agentleFS
Marve10sMarve10s/Better-Fullstack/llms.txt

Better-Fullstack

llms.txt815 starsChanged 4 months agoMITView on GitHub

Better Fullstack scaffolds fullstack projects from a catalog of Stack Parts across TypeScript, React Native, Rust, Go, Python, Java, Kotlin, .NET, Elixir, PHP, Ruby, and Crystal. It ships as the create-better-fullstack CLI, a browser Stack Builder, and an MCP server for coding agents. Use it instead of hand-writing starter files. This file is for AI agents that want to use Better Fullstack. If you are changing this repository, read AGENTS.md instead. One command detects installed coding agents, registers the MCP…

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call bfs_get_guidance first.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# Better Fullstack

> Better Fullstack scaffolds fullstack projects from a catalog of Stack Parts across TypeScript, React Native, Rust, Go, Python, Java, Kotlin, .NET, Elixir, PHP, Ruby, and Crystal. It ships as the `create-better-fullstack` CLI, a browser Stack Builder, and an MCP server for coding agents. Use it instead of hand-writing starter files.

This file is for AI agents that want to use Better Fullstack. If you are changing this repository, read [AGENTS.md](AGENTS.md) instead.

## Read the docs

- [Docs index for agents](https://better-fullstack.dev/docs/llms.txt): every documentation page as Markdown.
- [Full documentation corpus](https://better-fullstack.dev/llms-full.txt): product docs, guides, and blog text in one file.
- [MCP server](https://better-fullstack.dev/docs/ai/mcp): client setup, resources, and every tool.
- [AI overview](https://better-fullstack.dev/docs/ai/overview): agent skills, plugin, and CLI rules for agents.
- [CLI create](https://better-fullstack.dev/docs/cli/create): flags, presets, dry runs, and defaults.

## Set up MCP

One command detects installed coding agents, registers the MCP server, and copies the `scaffold-project` and `add-to-project` skills:

```bash
npx create-better-fullstack@latest install
```

To register the stdio server by hand:

```bash
claude mcp add --scope user better-fullstack -- npx -y create-better-fullstack@latest mcp
codex mcp add better-fullstack -- npx -y create-better-fullstack@latest mcp
gemini mcp add --scope user better-fullstack npx -y create-better-fullstack@latest mcp
code --add-mcp '{"name":"better-fullstack","command":"npx","args":["-y","create-better-fullstack@latest","mcp"]}'
```

Cursor, Windsurf, Claude Desktop, and other clients that read `mcpServers`:

```json
{
  "mcpServers": {
    "better-fullstack": {
      "command": "npx",
      "args": ["-y", "create-better-fullstack@latest", "mcp"]
    }
  }
}
```

OpenCode, Zed, VS Code, and Codex TOML use other config shapes. The [MCP docs](https://better-fullstack.dev/docs/ai/mcp#manual-setup) list each one.

## Use the MCP tools

1. Call `bfs_get_guidance` first. It returns the current workflow rules and field meanings.
2. Find options with `bfs_get_schema`, `bfs_search_options`, or `bfs_recommend_stack`.
3. Validate the stack with `bfs_check_compatibility`.
4. Preview files with `bfs_plan_project`, then write them with `bfs_create_project`.

For an existing project, start with `bfs_get_project_status`. Changes follow a plan and apply pair, such as `bfs_plan_addition` then `bfs_add_feature`, and apply only with the token the plan returned.

## Use the CLI without MCP

```bash
npx create-better-fullstack@latest search laravel
npx create-better-fullstack@latest my-app --frontend tanstack-start --backend hono --database postgres --orm drizzle --auth better-auth --dry-run
```

`--yes` accepts the defaults and conflicts with core stack flags such as `--frontend` and `--backend`. Pass `none` for optional categories you want off. Add `--no-install --no-git` to avoid side effects.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.