Getting started
Overview
How tentaflake turns a NixOS host into a reproducible platform for isolated AI agents.
tentaflake is a generic NixOS flake template for running isolated AI agents on one machine. It provides reusable modules, agent builders, an installer, and operational checks for Hermes and ZeroClaw.
Agent adapters
Section titled “Agent adapters”The adapter API exposes mkAgent alongside the compatible Hermes and ZeroClaw builders. The registered openclaw adapter is a stopped refusal scaffold: it creates no OCI container, and an explicit start fails. A reviewed image and actual model, Research, execution, and lifecycle acceptance are still pending.
The same API accepts generic digest-pinned OCI definitions with explicit commands, ownership, workspace, and resources. These workloads remain stopped pending capability admission; generic model and Research hooks are not accepted, and the generic contract requires balanced.
Use tentaflake runtimes --json to discover presets. Installed-host onboarding offers agent template and agent validate|plan|import for stopped additions. Import does not track files in Git, rebuild, activate, or start services; review and track the definitions before an explicit host update.
The LLM broker offers bounded Chat Completions and Responses streaming when explicitly enabled per agent; streaming remains disabled by default and does not establish vendor compatibility.
Infrastructure and evidence
Section titled “Infrastructure and evidence”The system is designed around three properties:
- Isolation: each agent runs in a hardened container with explicit resources, workspace ownership, and networking.
- Controlled access: a per-agent model broker, the pinned web research relay, and disposable workers narrow the paths from an agent to external services and host tools.
- Recovery: declarative configuration, quotas, backups, and testable NixOS generations make failure modes observable and reversible.
The dev security profile preserves compatibility and is not a security boundary for untrusted, continuously running agents. Review security profiles and the threat model before production use.