Install
Python 3.10+. Optional LangGraph extra maps runtime IDs for you.
pip install mycelium-runtime pip install 'mycelium-runtime[langgraph]' # optional
Path
Four commands.
Using a coding agent? Ask it to “Use
$mycelium-setup to protect this project.” The repository skill
discovers tools, fills the YAML, wires the runtime, and runs the checks.
You review effect classifications, identity, secrets, and provider access.
Using TypeScript, Go, or another language? The Mycelium engine remains Python, while your application connects through its local HTTP/JSON sidecar. Follow the language-neutral setup instead of rewriting the state machine.
See execution control in action
The feature tour demonstrates one lifecycle area: lease, hard-block, repair, reconcile, and operator release. Doctor inspects config. Verify exercises synthetic failures against the ledger backend only.
mycelium demo mycelium demo --redis # needs Redis + mycelium-runtime[redis] mycelium doctor --config mycelium.yaml mycelium verify --config mycelium.yaml
Scaffold one ledgered tool
Writes mycelium.yaml: transition + one mutating tool.
Fill in the callable path manually, or let $mycelium-setup
inspect and wire your application.
mycelium init # manual path: edit mycelium.yaml → tools.*.callable # agent path: use $mycelium-setup
Run your agent under Mycelium
Zero-touch wrap: configured callables are guarded before your app starts. Retries return stored results or hard-block; they do not double-fire.
mycelium run --config mycelium.yaml -- python -m my_app
What you just enabled: the default execution and recovery layer for one tool. Add validation, scope, secrets, authority, context, loop, budget, and completion controls when they apply. Together they make tool actions reliable before, during, and after execution.