Skip to main content

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.

Get fleet-rlm running locally in under five minutes.

​
Prerequisites

  • Python 3.10 or later
  • uv package manager
  • Daytona API key — sandbox execution backend
  • An LLM API key — any LiteLLM-supported provider (OpenAI, Anthropic, Gemini, etc.)

​
1. Add fleet-rlm to a uv project

uv init my-fleet-app
cd my-fleet-app
uv add fleet-rlm
Published installs already include built frontend assets, so you do not need pnpm or a separate frontend build step.

​
2. Configure environment variables

Create a .env file in your working directory:
.env
# LLM provider (LiteLLM model identifier)
DSPY_LM_MODEL=openai/gpt-4o-mini
DSPY_LLM_API_KEY=sk-your-api-key

# Daytona sandbox runtime
DAYTONA_API_KEY=your-daytona-api-key
# Optional override:
# DAYTONA_API_URL=https://app.daytona.io/api
See the configuration reference for the full environment variable list, including auth, database, and MLflow settings.

​
3. Launch the Web UI

uv run fleet web
Open http://127.0.0.1:8000. You should see four product surfaces:
  • Workbench — adaptive chat and runtime execution
  • Volumes — runtime-backed file browsing
  • Optimization — DSPy evaluation and GEPA workflows
  • Settings — runtime configuration and diagnostics

​
4. Try a recursive task

In the Workbench, send a prompt that exceeds a single context window — for example, asking the agent to summarize a long document or analyze a repository. The agent will:
  1. Decide the task is too large for one ReAct context.
  2. Call delegate_to_rlm to spin up an isolated child Daytona sandbox.
  3. Run a bounded dspy.RLM inside the child, recursing further with sub_rlm if needed.
  4. Stream intermediate trace events back to the UI and bubble the final answer into the chat.

​
Other surfaces

Terminal chat

uv run fleet-rlm chat --trace-mode compact

API server only

uv run fleet-rlm serve-api --port 8000

​
Next steps

Installation guide

Install from PyPI or from source for contributors.

Core concepts

ReAct orchestration, recursive RLM, runtime surfaces.

Recursive RLM

How delegate_to_rlm and child sandbox isolation work.

Troubleshooting

Common installation and runtime issues.