Loading tool…
Project tracker where sandboxed AI agents pick up tickets alongside the human team
Tulsk is a project workspace built around agents: you file projects, tasks, sprints, cycles and dependencies as usual, then assign some of them to sandboxed AI agents that can delegate to each other. A Workspace Chat watches the board, flags risks and writes briefings. It connects to Slack natively plus Gmail, GitHub and Google Calendar, and exposes an API catalogue and an MCP server with more than fifty tools so external agents can drive it. Billing splits the subscription from the agent compute: Starter is $39 a month with $50 of agent work and up to six agents, Pro is $99 with $120 of agent work and no agent cap. No company entity or country is published.
Free plan includes $5 of one-off agent work. Starter $39/month bundles $50 of agent work and 6 agents; Pro $99/month bundles $120 and unlimited agents; Enterprise is quoted. The homepage separately advertised $7 per extra seat, so the seat model is not consistent across the site.
Use tool ↗Tulsk is one of the few trackers that treats agent runs as first-class work items with their own budget line, which makes the spend visible instead of buried in an LLM bill. The MCP server and API catalogue mean other agents can file and close tickets against it. It is early: no company details, no country, and the seat pricing on the homepage contradicts the pricing page.
Watch out: The plan fee and the agent-work allowance are two separate budgets; heavy agent use will exceed the bundled $50 or $120 well before the month ends.
Side-by-side fact sheets against the competitors our research names — pricing, platforms, API and both verdicts on one page.
No reviews yet — be the first to review Tulsk.
Reviews are tied to your EffectHub account — one review per tool, so the rating for Tulsk reflects real users.
No questions yet — ask the first one about Tulsk.
Questions about Tulsk are tied to your EffectHub account, so answers can reach you and the section stays free of spam.