> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qredence.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Fleet Prime Agent

> A self-improving coding agent with persistent sessions, real subagents, and a streaming web UI. Run it from the CLI, a TUI, a background daemon, or the Qredence web app.

Fleet Prime Agent is a coding agent you run locally. It keeps a persistent Python kernel per session, spawns real subagents through `rlm(...)`, streams every turn as structured events, and improves itself over time from your feedback with `/refine`.

You can drive it from four surfaces that share the same runtime:

* **CLI** — one-shot or scripted runs (`text`, `json`, `rpc` modes).
* **TUI** — full interactive terminal.
* **Daemon** — long-lived background process that CLI, TUI, and web attach to.
* **Web app** — the Qredence UI for chat, tool cards, session branching.

## Start here

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/fleet-prime-agent/quickstart">
    Install, sign in a provider, and run your first agent turn in under five minutes.
  </Card>

  <Card title="Install" icon="download" href="/fleet-prime-agent/install">
    System requirements and install steps for the agent workspace and web UI.
  </Card>

  <Card title="Core concepts" icon="book" href="/fleet-prime-agent/concepts/architecture">
    Sessions, subagents, streaming events, refinement — the ideas the rest of the docs assume.
  </Card>

  <Card title="Feature guides" icon="sparkles" href="/fleet-prime-agent/guides/streaming-chat">
    Task-oriented walkthroughs for chat, tools, providers, sessions, MCP, and OAuth.
  </Card>
</CardGroup>

## What you can do with it

<CardGroup cols={2}>
  <Card title="Chat with a model that can run code" icon="terminal" href="/fleet-prime-agent/guides/streaming-chat">
    Every session gets its own persistent IPython kernel plus shell, edit, grep, and find tools.
  </Card>

  <Card title="Choose from 19 providers" icon="plug" href="/fleet-prime-agent/guides/providers-and-models">
    OpenAI, Anthropic, Bedrock, Gemini, and 15 more, with per-model cost and thinking-level metadata.
  </Card>

  <Card title="Branch and resume sessions" icon="code-branch" href="/fleet-prime-agent/guides/sessions-and-branching">
    Fork any point in a transcript. Compaction keeps long runs inside the model's context window.
  </Card>

  <Card title="Spawn subagents from Python" icon="sitemap" href="/fleet-prime-agent/concepts/rlm-subagents">
    Call `rlm(...)` inside an IPython cell to run a real child agent in parallel or in the background.
  </Card>

  <Card title="Add tools with MCP or extensions" icon="puzzle-piece" href="/fleet-prime-agent/guides/mcp">
    Register external tool servers over MCP, or ship your own extension package.
  </Card>

  <Card title="Teach it with skills" icon="graduation-cap" href="/fleet-prime-agent/guides/skills">
    Turn a recurring workflow into a personal or project skill loaded automatically.
  </Card>
</CardGroup>