AgentOS Core documentation
Run your agent locally,
then make it yours.
Task-oriented guides for installing AgentOS, wiring up providers, and driving it from the terminal, Web UI, desktop app, or chat.
Start here
QuickstartThis guide gets AgentOS installed, configured, and running locally. It assumes you want the standard product experience: terminal commands, local Web UI…Use Cases and RecipesUse this page when you know what you want AgentOS to do, but you are not sure which feature guide to read first.ConfigurationAgentOS can be configured from the onboarding wizard, the Web UI setup flow, CLI commands, environment variables, and TOML files.CLI ReferenceThe agentos CLI is the fastest way to configure, run, inspect, and automate AgentOS.
Getting started9
QuickstartThis guide gets AgentOS installed, configured, and running locally. It assumes you want the standard product experience: terminal commands, local Web UI…Use Cases and RecipesUse this page when you know what you want AgentOS to do, but you are not sure which feature guide to read first.GatewayThe AgentOS gateway is the local server behind the Web UI, channels, RPC clients, sessions, approvals, diagnostics, and usage views.ConfigurationAgentOS can be configured from the onboarding wizard, the Web UI setup flow, CLI commands, environment variables, and TOML files.CLI ReferenceThe agentos CLI is the fastest way to configure, run, inspect, and automate AgentOS.Web UIThe AgentOS Web UI is the local control console for setup, chat sessions, approvals, channels, logs, agents, usage, and operational status.Desktop App (macOS)AgentOS App is the native desktop app for macOS 13 or newer, on Apple silicon and Intel. It installs the engine for you, starts and supervises the local…Sessions and HistorySessions are durable AgentOS conversations. They let you inspect past work, resume a conversation, export a transcript, or stop a turn that is still running.GlossaryThis glossary defines common AgentOS terms in user-facing language. It is not a runtime design document.
Feature guides19
Feature CatalogAgentOS combines a personal-agent runtime with model routing, tools, memory, channels, scheduling, and reusable skills.Agentic TradingAgentOS treats trading as a first-class capability. Market research, portfolio analysis, and order execution reach the agent through partner-authorized…Wallets and TradingAgentOS can hold EVM wallets of its own and swap tokens on Base and Robinhood Chain through a pluggable swap provider: the AgentOS Aggregator (default, no…LP cardsUniswap V4 liquidity read-outs rendered as cards in the chat transcript. The engine produces the payload (agentos trade lp …), the transcript renders it…LP writesPhase 1 (docs/lp-cards.md) reads Uniswap V4 liquidity. Phase 2 lets the desk act on it — collect fees, remove liquidity, add liquidity — through the same…The liquidity booktrading.lp.bookEvery liquidity position the engine's wallets hold, across protocols, the way a wallet tracker lists DeFi positions.BridgeThe trading engine moves ETH and the USD stable between its two chains through Relay — a public, keyless REST API that prices a cross-chain transfer and…DCA mandatesA DCA mandate is a recurring buy the trading engine owns and runs by itself: buy $10 of ETH with USDC on Base every day until $300 is spent.Price triggersA trigger is a conditional order the trading engine watches and fires by itself: sell half my ETH if it drops under $3,800, buy $50 of ETH when it is back…BracketsA bracket protects a position with two price triggers at once: sell my ETH when it is up 20 %, or when it is down 10 %, whichever comes first.Stock Token marketsWhich tokens trade against NVDA? On Robinhood Chain a Stock Token is not only something you buy: it is the quote asset for hundreds of other tokens.Pilot RouterPilot Router is AgentOS's local model-routing layer. It helps the agent choose an appropriate model tier for each turn so routine work does not always run on…Tool CompressionAgentOS agents use tools. Tool calls can produce large outputs: command logs, JSON, web pages, search results, diffs, file contents, tables, and artifacts.MemoryAgentOS memory helps the agent recall durable context without replaying every old conversation. Use it for stable preferences, reusable project facts…SkillsSkills are task-specific instruction packages and scripts. They let AgentOS load relevant guidance only when a task needs it, instead of putting every…Browser automationThe browser tool lets the agent drive a real Chromium — navigate, read a page as an accessibility snapshot with element refs, click, type, fill forms, wait…Image FlowsAn Image Flow is a small node graph that makes images: a prompt goes in, optionally a prompt writer or an image description in between, one or more image…ACP Coding HarnessesAgentOS can hand coding work to an external coding agent (Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, OpenCode and 20 more) and get the result…Compaction and Cache ContinuityLong agent sessions need context management. AgentOS uses compaction, bounded history, tool-result projection, and cache-aware prompt placement to keep…
Surfaces & operations18
ChannelsChannels let AgentOS run from messaging platforms while sharing the same agent runtime as the CLI and Web UI.Providers and ModelsAgentOS supports multiple LLM providers through one configuration surface. You can run direct single-model mode or enable Pilot Router for tiered routing.Web SearchAgentOS can search the web through configured search providers and can fetch pages through guarded web tools.X (Twitter) SearchThe x search tool searches X posts, profiles, and threads. It is backed by xAI's server-side x search tool on the Responses API at…Artifacts and MediaAgentOS can create and deliver files as part of agent work: reports, HTML files, PDFs, slide decks, spreadsheets, generated images, and other artifacts.Tools, Approvals, and SandboxAgentOS tools give the agent useful capabilities. Policy layers, approval surfaces, workspace constraints, and sandbox posture control how those tools are…Approvals and PermissionsApprovals and permissions control how AgentOS tools are allowed to act. They matter most when an agent can write files, run shell commands, publish artifacts…Durable AgentsAgentOS agents are named runtime profiles. Use them when different work streams need different defaults, such as a research workspace, a writing workspace, or…SchedulingAgentOS scheduling lets you run recurring or one-time agent work from the gateway. Use it for reminders, periodic summaries, status checks, channel updates…HTTP APIThe AgentOS gateway is a Starlette ASGI application that exposes a REST HTTP API alongside its streaming WebSocket.Remote AccessThe gateway controls chat, tools, sessions, channels, approvals and configuration, all with your provider credentials.Run the Gateway in a ContainerRun the AgentOS gateway from the published container image on a server, a VPS or a home box, then use it from the desktop app, the Web UI or the CLI on your…MCP Client GuideAgentOS connects to external Model Context Protocol servers and offers their tools to the agent. This page is about that client side.MCP Server BridgeAgentOS can run as a stdio MCP server bridge for MCP-capable clients. Use this when another local AI client should call into AgentOS session workflows through…Usage and CostAgentOS records token usage and estimated cost from the running gateway. Use the cost view after routed, tool-heavy, channel, or long-context work to…Diagnostics and ReplayDiagnostics and replay help explain what happened during an AgentOS turn. Use them when a result was surprising, slow, expensive, interrupted, or hard to…OperationsThis guide covers day-two commands: sessions, cron, cost, diagnostics, replay, migration, durable agents, MCP, and install inventory.TroubleshootingThe Web UI's Settings › Health at http://127.0.0.1:18791/control/settings/health also reports readiness and recovery steps when the gateway is running.
For AI agents
Every page is also served as plain Markdown, so coding agents and LLM tools can read the docs directly. Point your agent at llms.txt, or request any docs URL with Accept: text/markdown.
- /llms.txtIndex of every page with a one-line summary
- /llms-full.txtAll docs as Markdown in one file
- /docs/core/quickstart.mdAppend .md to any docs URL for its Markdown
curl https://useagentos.dev/llms.txt curl -H "Accept: text/markdown" https://useagentos.dev/docs/core/quickstart