TEAM-14
Plan the campaign brief
Unassigned
Open-source project workspace
Your team and agents, working together.
Plan projects, delegate tasks to AI agents, and review the results together. Keep the brief, files, and discussion with the work.
Shared tasks · Agent delegation · Parallel sandbox work · MIT licensed
Your agents, your choice
Use your preferred runtime with your own credentials or API-billed models.
- Claude
- Codex
- Gemini
- Cursor
- Hermes
- OpenClaw
- Pi
- OpenCode
From a shared task to a reviewed result
Give work an owner, give agents the context to act, and keep your teammates involved as the project moves forward.
01 Projects
Plan the work with your team
Bring teammates, tasks, files, and conversations into a project. Assign work to a person or an agent and follow its progress on the board.
Explore Projects02 Agents & connectors
Delegate tasks to your agents
Assign tasks to specialist agents with their own instructions and tools. Equip a manager agent to delegate ready work, while agents run in persistent sandboxes within the capacity you configure.
Explore Agents03 Approvals & audit
Review the result. Decide what happens next.
Review task deliverables with your team. Configure review policies and connector approvals, inspect run history, and manage access and usage as your agent fleet grows.
Explore GovernanceYour workspace, your choice
Your Infrastructure. Your Data. Your Rules.
Choose where your workspace runs and which models your agents use.
Self-hosted by default
Run Tale on your own infrastructure or choose managed hosting. Local models keep inference local; external providers, connectors, and tools follow the connections you configure.
Security built in
Manage members, roles, single sign-on, budgets, and configured guardrails in the same product. Use audit records and run history to investigate what happened.
Fully open source
The entire codebase is public under the MIT license. Read it, audit it, change what you need — without asking anyone.
Plugged into the tools you already run
Connect the services your projects depend on. Configure credentials once, then grant the access agents and workflows need for their work.
- OpenAI
- Shopify
- Claude
- Cursor
- Gemini
- GitHub
- Microsoft
- Atlassian
- Slack
- Discord
- Gmail
- Tavily
SECURITY
Support for your deployment
Ruler GmbH · ISO 27001MIT LicensedOpen Source
Independent & Transparent
Swiss-based and vendor-neutral — no ties to a cloud or model provider, so your deployment answers only to you.
ISO 27001-certified services
Ruler GmbH is ISO 27001 certified. The scope covers Tale Enterprise and professional services. Ask us for the certificate and scope relevant to your deployment.
Work you can try with your team
Start with a clear brief, defined deliverables, and a review process.
Frequently Asked Questions
Still have questions?Contact the team
Tale is an open-source project workspace for teams and AI agents. Plan tasks with teammates, delegate work to agents, and review the results in the same place. It combines task boards, agent sandboxes, shared knowledge, and workflows. Self-hosting and private models are available when you need them.
Tale is for teams that want to organize work for AI agents and collaborate with them. Technical members configure agents, tools, and repository access; other teammates can describe tasks, discuss progress, and review results. Use it for software projects, marketing campaigns, research, reports, or recurring operational work. What an agent can do depends on its tools and permissions.
Yes, when the harness supports that subscription. Bring your own token or supported login credential and choose the matching runtime. You can also use API-backed models. Subscription calls follow the provider’s limits and bypass Tale’s gateway metering and spending caps; check that usage with the provider.
Yes. Tale is MIT-licensed and the full feature set ships in the free Community edition — Enterprise adds support and services, not features.
Tale can run on your own infrastructure with local models. An offline deployment also needs local dependencies and restricted outbound connections. Cloud models, external tools, and connectors can send data outside your network when enabled; self-hosting alone does not make them local.
Enterprise is billed per user/month, with two months free when paying yearly. Storage beyond the included quota is billed per TB/month. The Community edition stays free for self-hosted use.
No. All product features are available in the open source version too. Enterprise adds extended support and services.
No. You can bring your own models, but it's not required. Tale supports most major AI providers without markup — cloud model usage is billed at your provider's rates and is not included in the plans.
Yes. Tale supports the major cloud AI providers without markup — usage is billed at your provider's rates, so you keep your vendor and your existing billing.
Yes — hardware is available on rental, leasing, or purchase terms. Mention it when you contact the team and you'll get a quote for the configuration that fits.
Yes. Run Tale on your own infrastructure and connect a local model server, such as Ollama or vLLM, through a supported API. Check the deployment requirements and test the model with your chosen agent runtime before assigning work.
Yes. Custom model training and fine-tuning are available for clients. Bring it up in the demo call if you need it.
Bring your next project to Tale
Start a self-hosted workspace or bring a real task to a demo. See how your team and AI agents can work through it together.
Self-host in four commands
curl -fsSL https://raw.githubusercontent.com/tale-project/tale/main/scripts/install-cli.sh | bashtale init my-projectcd my-projecttale dev