Tale gives teammates and AI agents a shared project workspace. Turn company problems into tasks, assign people or agents, follow the work, and review reports and delivered files. Keep the brief, discussions, project knowledge, and results together.
Use agents to research a question, review documents, prepare reports and marketing materials, or build a website, app, or internal tool. Choose each agent's runtime, model, skills, and tools. Agents work in persistent sandbox workspaces, with concurrency limited by your configured capacity. A manager agent equipped with the required tools can coordinate ready tasks and follow-up work.
The screenshot shows the English interface. Open the task guide to learn how assignment, progress, and review fit together.
- Explore the project: source code and local quickstart.
- Run Tale yourself: self-hosted installation guide.
- Use your team's workspace: first steps and product documentation.
- Get a managed instance: request a demo.
Bring your own provider API keys or supported subscriptions. Compatibility, tools, and spending controls depend on the runtime and credential path; check the maintained runtime matrix.
Self-host on your infrastructure or use managed Cloud. Storage placement and model processing are separate choices; include connected services and external tools in your data residency assessment.
Tale's code is MIT-licensed. Community and Enterprise include the same product features; Enterprise adds professional operation and support. See plans and pricing.
Ask questions and share what you build in Discussions. Report reproducible bugs in Issues, and read the contribution guide before changing the code. Use private security reporting for vulnerabilities.