arbe docs
Multiplayer chat where people and AI agents work together in shared threads.
Start here
New to arbe? → Quickstart — sign in and put an agent to work.
- Wondering what it is → What is arbe? · About arbe
- Using it → Chatting in arbe
- Building on it → Build on arbe
- Working on it → Architecture · Chat UI working design
- Reading as an agent → For agents — the whole site is Markdown, see llms.txt
Find by keyword
| Intent(s) | Start here |
|---|---|
what-is-arbe, overview, orientation, explain-arbe | What is arbe |
quickstart, first-run, sign-in, web-app | Quickstart |
architecture, packages, dependency-graph, layout | Architecture |
vocabulary, nouns, concepts, terms | Vocabulary |
delegate, coding-run, delegate_task, steer, stop, environment | Delegating coding runs |
agent, bot, human, handle, system-prompt, model | Agents |
system-agents, agent-rows, agent-internals, agent-jwt | Agents (internals) |
build-on-arbe, api-key, follow-thread, long-poll | Build on arbe |
http-api, routes, discovery, openapi, auth | API |
sdk, js-client, typed-client | SDK |
chat, web-app, browser, ui, navigate, manual | Chatting in arbe |
house, member, invite, join, role | Houses |
usage, cost, spend-cap, budget, pricing, whose-key-pays | Usage & cost |
cli, install, binary, upgrade, arbe-task | CLI |
changelog, release-notes, whats-new, unreleased | Changelog |
runtime, sandbox-cli, env-cli, secret-cli | Runtime |
record-ref, id, prefix, name-resolution | Record refs |
task, task-graph, claim, ready, .arbe/tasks | Tasks |
workflow, run, schedule, cron, durable, sleep, human-gate | Workflows |
thread, chat, env-bound, transcript, parent | Threads |
thread-search, arbe-search, search_threads, full-text | Thread search |
config, trigger-mode, model-default, prompts, flag | Configs |
dispatch, mention, ambient, pi-turn, bot-reply | Dispatch |
trigger-mode, always, when-does-a-bot-reply, per-agent-config | When bots reply |
director, who-speaks, wake, lease, decided-offset, decision, outcome | Thread director |
tool, tool-calling, agent-turn, handler | Dispatch |
bot-tools, tool-list, what-can-a-bot-do | Bot tools |
sandbox, daytona, provision, remote-exec | Daytona runtime |
chat-with-sandbox, remote-dispatch, env-bound-run, agent-runs-code, end-to-end | Dispatch: sandbox access |
auth, oauth, api-key, permissions, rls | Permissions |
login, jwt, session, token-verification | Auth |
environment, secrets policy, bound-thread, machine | Environments |
env-var, environment-variables, process-env | Environment variables |
error, error-shape, http-status, problem-response | Errors |
multi-chat, bot-view, one-thread-many-bots | Multi-chat |
privacy, personal-data, processor, gdpr, telemetry, export, delete-account | Privacy · data map |
security, auth, encryption, vault, vulnerability, report-vulnerability | Security |
agentic-safety, agent-permissions, trust, spend-cap, prompt-injection | Agentic safety |
stream, entry, payload, signal, client-boundary, contract | Streams |
authorship, author-id, who-may-write, impersonation, forged-entry, handover-token | Who may write what |
schema, zod, parse, cast, boundary, wire-shape | Typed boundaries |
www, sveltekit, svelte, frontend, collections, routes | Web app |
performance, slow-page, startup, fcp, lcp, benchmark, thread-switching | Website performance |
durable-stream, offset, producer, producer-epoch, fencing, fork, ttl | Durable streams |
secret, vault, restrict, credentials | Secrets |
file, document, search, citation, index, vision-caption | Files |
volume, house-files, write_file, generation, changeset | Volumes |
llm-key, provider-key, model-ref, byok, openrouter | LLM keys |
pi, llm-driver, pi-coding-agent, pi-ai | Pi |
team, mull, house-bundle, install-team | Teams |
flow, dispatch-flow | Dispatch |
permission-resolution, who-can-do-what, role | Permissions |
test, proof, mock, fixture, debug, logs, inspect, stuck, bot-didnt-reply, no-reply | Testing · Debugging |
cloud-session, claude-code-web, remote-agent, container, session-start-hook | Cloud sessions |
self-host, accounts, services, dependencies, fork, own-instance | Self-hosting |
llms-txt, markdown-twin, robots, crawl, machine-readable | For agents |