| What it does | Autonomous AI agents that plan, execute, and deliver work without setup or babysitting
| AI teammates that do recurring business work with approvals, budgets, and receipts
|
|---|
| Stage | Startup
| MVP
|
|---|
| Founded | Not given
| 2025
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: $0/month with unlimited projects and tasks plus $2 of agent work to get started, no credit card required. Starter: $39/month with $50 of agent work monthly and up to 6 AI agents. Pro: $99/month with $120 of agent work monthly and unlimited agents, marked as most popular. Enterprise: custom pri
| Free: 1,000 credits (one time), no card required. Pro: $29/month with 10,000 credits monthly. Team: $99/month with 35,000 credits monthly. Enterprise: from $1,500/month. Credits cost $0.001 each; typical costs are 6 credits for a chat message, 3 credits for a background task run, 15-60 credits for d
|
|---|
| Key features | - Create agents by describing their role in natural language; Tulsk automatically builds them with the right skills, tools, and schedules
- Agents run continuously in the cloud on schedules, events, mentions, or connected channels without user intervention
- Memory system that learns preferences and project context, separated between personal and team-shared knowledge
- Reusable skills that agents follow consistently without re-explanation across the entire team
- Approval system for writes to connected apps and new connections before agents act
- Connect Slack, Telegram, or WhatsApp for agents to receive and respond to messages with the team's preferred communication tools
- Real workspace files created by agents with live preview; files persist even when the workspace computer sleeps
- Mac desktop app for quick access via keyboard shortcut to chat, inbox, and workspace in any application
| - Agents run per task on demand with no servers to manage
- Every tool call is policy-checked with a receipt
- Approvals for third-party reach, deletion, and untrusted content
- Credential vault where the model only sees a handle, never a key
- Sandboxed code execution with deny-all egress by default
- Web chat on every plan; Slack and email on Team plan
- Per-agent budgets with work metered in credits
- Workspace export with activity log on Team and Enterprise plans
|
|---|
| What makes it different | - Agents run autonomously in the cloud without requiring setup, configuration screens, or DevOps knowledge
- Integration with any HTTP API, MCP server, or internal company API without agents being limited to one suite
- Reusable skills and shared knowledge layer allow teams to teach patterns once and have all agents follow them consistently
- Free tier with unlimited projects and tasks plus $2 of agent work lets teams start and explore without credit card commitment
| - Security and cost controls built in by default, not enterprise add-ons
- Idle agents cost nothing; work runs on demand then stops
- A standing team you can see with receipts for every action
- Built for work you have to answer for with approvals and audits
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 23 ● no change since last check | 19 ▲ +1 (up) since last check |
|---|
| Trust Flow (Majestic) | 3 | 4 |
|---|
| Citation Flow (Majestic) | 30 | 30 |
|---|
| Referring domains (Majestic) | 122 | 105 |
|---|
Tulsk
OpenLegion