Tale documentation

Tale is the orchestrator for AI agents. You can chat with models over your own documents, build agents that handle a job end to end, run automations in the background, and manage customer conversations from one inbox — with your choice of AI providers and your data pinned to a region you control.

The product ships in two editions; every feature, API, and role is identical between them. The only thing that differs is who runs the stack. Pick your edition, then jump to the section indexed by what you do day to day.

New here? The fastest path to a running instance is the self-hosted quickstart — install the CLI, then tale init and tale start, and you are signed into your own org in minutes.

Pick the entry that matches what you are here to do. A cloud user who wants Tale to run the stack starts at Cloud. A self-hoster standing up an instance on their own infrastructure starts at Self-hosted. A platform builder — agents, automations, integrations — lives in Platform, the canonical feature reference. An operator keeping a self-hosted instance patched and observed goes to Operate. A contributor changing the source starts with Contributor setup.

Pages in this section

Cloud — Tale operates the stack; pick this when running infrastructure is not where the team should spend its hours.

Self-hosted — install Tale on your own VPC, on-premises hardware, or in an air-gapped environment.

Platform — the canonical product reference, identical for Cloud and self-hosted. Most day-to-day reading lives here.

Tutorials — role-indexed walks from "I want to do X" to a working result on a fresh instance.

Develop — REST API, webhooks, integration SDK, contributor workflows.

Where this fits

Once you have picked an edition and a role, the rest of the docs sit one click away. If you already know your edition and want the feature reference, go straight to Platform — the canonical documentation for every user-visible feature, identical across both editions. Source, issues, and release announcements live at GitHub.