KruvoThe AI coworker that gets work done, and asks before it acts.
Kruvo delivers finished work, not chat: a codebase reviewed for vulnerabilities with fixes ready to go, a polished document, a Slack reply with the numbers, a triaged inbox, a morning brief in your Telegram.
Runs on your machine. Bring your own model key or go fully local with Ollama. Free to use, no time limit.
What you get
Real deliverables
Documents, spreadsheets, reports and web pages land as files you can open and share. Not a to-do list, the work itself.
Work from your phone
Message the Kruvo bot on Telegram or mention it in Slack. A session opens on your desktop, the work happens with your tools, and the answer comes back to the chat.
Your everyday tools
25+ integrations, GitHub, Slack, Jira, Notion, Linear, HubSpot, Outlook, Gmail, Google Calendar, plus your terminal and local files. Anything reachable over MCP plugs in too.
Standing automations
A morning brief, a weekly report, a watch over a channel. On a schedule, with full transcripts, and every approval parked in your inbox until you answer.
Specialist coworkers
Security review, cloud posture and incident triage ship with the tools, working style and check-ins for one job already set up. Findings come from real scanners plus model reasoning.
Bring your own model
OpenAI, Anthropic, Google Gemini, Mistral, DeepSeek, Qwen, Kimi and more. Open-weight models via Together and Fireworks. Fully local with Ollama.
How it works
- Tell Kruvo the outcome you want. "Prepare a customer brief", "untangle my calendar", "check where the release stands across Jira and GitHub".
- It breaks the task into steps and works across your desktop, files and connected apps.
- Before anything consequential, sending a message, changing a calendar, running a command, it checks in and you approve or redirect. From the app, or from your phone.
- You get the finished deliverable, with an audit trail that answers "who did this, and why?".
Governed by design
Governance is the architecture, not a plugin. The agent cannot grant itself new permissions, and no prompt can talk it past a gate.
1 Hard floors
Dangerous and irreversible operations are human-only, always. No mode, including full auto-approve, lowers these floors.
2 Earned autonomy
Actions are approval-gated by default. One-off approvals can graduate into standing rules, then into allowlists. Each step explicit, visible and revocable. A reviewer model handles the routine and escalates the uncertain; repeated denials trip a circuit breaker.
3 An audit trail
Every tool call is recorded with its approval provenance, auto-approved, user-approved or denied, with the reviewer's reasoning attached, and persisted with the conversation.
Local-first, by default
The agent loop, your conversations, connector tokens and model keys all live on your machine, in the app's local secret store. Your data leaves it only through the model and the integrations you choose. Kruvo Cloud is optional: it brokers one-click connections and relays messages for people who want the convenience, and it never sees your conversations.