SilentSwarm Documentation

SilentSwarm is a leader/fellow runtime for distributed transformer experiments with explicit control-plane orchestration, tensor data-plane transport, and cluster-backed experiment runs.

Start Here

• New to the project: getting-started.md
• System design: 01_architecture/index.md
• Run experiments: 02_experiments/README.md
• Operate clusters and bootstrap fellows: 03_operations/README.md
• CLI command reference: llm_swarm_cli.md
• Contributing workflow: 04_contributing/README.md

Reading Path

1. Start a local cluster and run one smoke sweep.
2. Read the architecture overview and runtime model.
3. Use the experiment and operations pages for day-to-day work.
4. Use Reference pages when you need exact commands, routes, or contracts.

Documentation Rules

• Document current behavior first.
• Keep navigation task-oriented and shallow.
• Prefer Mermaid diagrams for system flows and state machines.
• Keep historical planning separate from operator and developer docs.
• Keep links relative and verify with python -m mkdocs build --strict.

Build The Docs

source .venv/bin/activate
pip install mkdocs mkdocs-material pymdown-extensions
python -m mkdocs serve

Build static output:

source .venv/bin/activate
pip install mkdocs mkdocs-material pymdown-extensions
python -m mkdocs build --strict