Tale
Open-source project workspace for teams and agents
About Tale
Tale is an open-source project workspace where teammates and AI agents work on the same tasks. You add work to a shared board, assign each task to a person or an agent, and review the delivered reports and files in one place. It addresses a common gap: agents run in separate tools, and their output is hard to track, review and govern alongside human work. Tale brings planning, delegation, review and audit into one product that can run on your own infrastructure.
The entire codebase is public under the MIT license, and the free Community edition includes every product feature for self-hosting, with support handled on GitHub. Tale Enterprise does not add features; it adds professional operation by Swiss company Ruler GmbH, whose ISO 27001 certification covers Tale Enterprise and professional services, plus installation, maintenance, a data processing agreement and support. Enterprise is priced in Swiss francs and euros at CHF 12 (EUR 14) per user per month, with two months free on yearly billing, and is arranged through the sales team. Agents can run on your preferred runtime, such as Claude Code, Codex or Gemini CLI, with your own API keys or supported subscriptions. Cloud model usage is billed at your provider's rates without markup.
Install the Tale CLI with a single command, then run tale init and tale dev to start a local instance, or request a managed deployment. Inside a project you describe the work as a task with the problem, source files and completion criteria, then assign it to a teammate or to a project agent configured with its own instructions, runtime, model and tools. Agents work in persistent sandbox workspaces, with concurrency limited by the capacity you configure, and a manager agent can delegate ready tasks when granted the tools to do so. You follow progress on the board, steer agents with @mentions in task comments, and inspect their reports and files before accepting the result or requesting changes. For recurring work, versioned automations add scheduled starts, workflow steps and connector approvals.
- •Shared task boards - Projects keep tasks, files, instructions and chats together, with work assigned to people or agents and tracked from to-do through review.
- •Project agents in sandboxes - Define each agent's instructions, harness, model and tools, and let it run in a persistent sandbox with live previews of files it builds.
- •Knowledge and retrieval - Prepare documents, knowledge entries and website content for retrieval so agents work from your company's information, and check the sources used.
- •Automations - Connect agent steps, conditions and actions into workflows, test them, and run them manually or through configured triggers, with each run inspectable.
- •Chat and Arena - Chat with your information and run one prompt through two models side by side to pick the better reply.
- •Governance and connectors - Manage members, roles, single sign-on, budgets, review policies, connector approvals, usage and audit records, and connect services such as GitHub, Slack, Google and Atlassian.
Tale is built for teams that want to organize work for AI agents and collaborate with them rather than run agents in isolation. Software teams can coordinate implementation, tests, review and documentation in a shared project. Marketing teams can turn a campaign brief into research, content drafts and reviews. Operations teams can track requests, investigations and recurring work with clear ownership. Organizations with compliance requirements can self-host on their own infrastructure, connect local model servers such as Ollama or vLLM, and choose Enterprise when they want a professionally operated deployment with a DPA and support.
Pricing
Priced in another currency
- Community$0/mo
- Enterprise12 CHF/mo
From the vendor pricing page, 2026-10-08
