Engine docs
Everything a brain author needs from the engine — the same files omnislash upgrade syncs into your brain's docs/engine/, published here
on every engine release.
- Getting Started From an empty directory to a streamed answer from your own agent. Everything below runs on your machine; no server, no deploy, no CI.
- OMNISLASH: THE PHILOSOPHY The framework behind the self-evolving operator.
- Brain Runtime Contract Engine = framework runtime. Brain = a user project that consumes it (analog: an iOS app on top of system frameworks). This file defines the five things…
- Feature Inventory The exhaustive list of shipped engine features. Three levels: area (##) → feature → sub-feature. What a brain is and why it is shaped this way:…
- Brain Developer Guide: Registry Access and Engine Upgrades Omnislash engine npm packages (@omnislash-ai/) are published to GitHub Packages (private). The base Docker image (ghcr.io/omnislash-ai/engine) is public. A…
- Agent Observability: list → get → history → tail How a brain (or its agents) watches other agents: which read tool answers which question, how agent identity works across chats, and the cursor recipe for…
- Agent state — Postgres tables, views in context An agent that has to remember structured things — "paused until 14:00", a streak per direction, today's challenge and its status, the last seven reminders…
- Asking a Human The engine has exactly one human-in-the-loop pipeline: every question, approval card, and grant request goes through the same gateway, renders in Telegram…
- Automation Tiers Omnislash provides three tiers of business workflow automation. Each tier gives progressively more control and engineering precision. A business starts at…
- Boss Mode — the agent that works your HITL queue Boss mode is a time-boxed run you start from the dashboard (Run BOSS) or ask an agent to start. While it is active, HITL interactions your agents raise are…
- Brain Content Layout Brain behavior lives in features: one directory per feature under features/, holding everything that defines it — scenario, pipeline code, heartbeat, hooks,…
- Brain Operations: Deploy & Day-2 The deploy/ops reference for a brain: one-time server setup, secrets, CI/CD, runtime persistence, and day-2 operations. production-runbook.md is the linear…
- Business KPIs The overview already tells you how the operator is doing — runs, spend, grades, what it changed in itself. It cannot know how the business is doing:…
- Chat Access — who may use the bot, and how it behaves With no configuration at all, a bot serves only you. It answers every message in your DM with it and stays silent everywhere else. To let people use it, add…
- CLI Agents Setup Setup guide for the three CLI agents the engine spawns as subprocesses — Claude Code, Codex, OpenCode: what to install, authenticate, and (optionally)…
- Dashboard page map The dashboard is the operator's second surface. An owner mostly talks to the chief in Telegram; the dashboard is where they go when a chat answer is not…
- Database — your tables, your migrations One PostgreSQL database, two owners:
- Engagement — when the bot answers, and how Engagement is the third question of a bot's chat frame (chat-access.md): the frame first decides which role serves the chat and who the person is there…
- Evaluation & self-evolving Two opt-in blocks in an entity's frontmatter. evaluation: grades finished executions; loop: turns what the grades say into a pull request against your…
- Feature contexts — what a feature brings to a turn linked to it A role is the one place an agent's prompt used to come from. A feature could run entities as a role (a heartbeat, a hook, a scenario), but it could not add…
- Giving an agent a computer Some work has no API: a freelance exchange's cabinet, an internet bank, a desktop app. For it an agent needs what a person has: a desktop with a browser…
- Glossary — who is who One word for each thing. These docs, the engine's code and the dashboard use them the same way.
- Integrations Declarative bundle — the brain describes an integration as one object (tools + webhooks + token provider), and the engine automatically registers the tools…
- Memory: lines, authored sources & curation The engine gives your brain a searchable memory with two zones and, inside the machine-written one, as many separate lines as you declare. Knowing both…
- Money budgets A fleet of agents on metered API keys spends real money with nobody watching: a hook that fires on every inbound lead, a heartbeat every five minutes, a…
- Notification Channels Named delivery destinations your agents can notify without approval cards. You declare channels in omnislash.config.ts; the engine turns them into the…
- Pipelines (Tier 3) Pipelines are Tier 3 automation: you write the flow control in TypeScript on Restate, and the engine provides everything else — agents, tools, HITL,…
- Production Runbook Start here only once you already have a working local brain — scaffolded, started, and answering in the dashboard chat. If you do not, do getting-started.md…
- Publishing Artifacts Your agents can put a file on the web and hand back a link. They write to their artifacts directory, call artifactpublish, and get back a URL that renders…
- Reacting to your Telegram account Your agents can already act as your Telegram user account (the telegram tools, see features.md § Telegram MTProto). This page covers the other direction:…
- Role prompts — what to put in a role body, and what not to A role file (.agent.md, or a brain copy of role-.md) is frontmatter plus a body. The body is the role's own section of the system prompt. This page is about…
- Secretary Mode — your bot answers private chats on your behalf Mark a bot as a secretary and connect it to a Telegram Premium account's Telegram Business → Chatbots settings: the engine will answer messages in the…
- The Deliverable Every workflow run ends with one artifact you can hand a person: the deliverable. It is a file — written by an agent during the run, read off disk when the…
- Upgrading the engine An engine upgrade is an agent's job, never a person's: a coding agent working in the brain repo, on the strongest model available. It has two halves:
- Voice Two directions, one shape. Speech in (a voice message becomes text) and speech out (text becomes a voice message) are each a declared fallback chain: the…
- Widgets — interactive pages your agents open for a person A widget is a page an agent, a pipeline or a hook opens for a person: in Telegram, a message with a button that opens the page as a Mini App; on the…