| What it does | An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
| AI Operating System for Enterprise
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Not given
|
|---|
| Pricing | Prototype: free during beta, then from December 16, 2026 it costs $1 per 1,000 agent calls after 1,000 monthly included calls. Production: $20 a month with 20,000 agent calls included, then $1 per 1,000 calls after that. Top-ups: $1 per 1,000 calls, from $10 to $500 at a time, never expiring.
| Free (Community): $0/user/month for up to 10 users, bring your own LLM keys. Starter: $20/user/month (annual) with 5,000 LLM credits/user/month. Professional: $30/user/month (annual) with 10,000 LLM credits/user/month. Enterprise: $45/user/month (annual) with 20,000 LLM credits/user/month and dedica
|
|---|
| Key features | - Prompt rebuilt from journal under token cap at each step to keep it bounded as history grows
- Spending limits checked before each model call at token prices you declare
- Resume after crash without repeating finished actions
- Tool calls returned as actions for your code to carry out
- Proof of what ran: check prompts, re-run engine, download hash-chained journal
- Integrations with Vercel AI SDK, OpenAI Agents SDK, LangGraph, Mastra, Pydantic AI
- MCP server for Claude Code, Claude Projects and Codex
- Works with any model via bring-your-own-key
- TypeScript and Python clients for HTTP API access
| - Team chat with channels, threads, and room-scoped isolation
- Smart Lists & Data with spreadsheet and Kanban views
- Documents & Files with centralized storage and versioning
- AI Bot Agents with permission-bounded execution
- MCP Apps for custom portals and integrations
- Sandbox isolated execution environment
- Full audit trail for compliance
- Multiple deployment options: cloud, self-hosted, air-gapped
- Room-level isolation and data boundaries
- Autonomous AI workflows with Sense → Think → Act cycles
|
|---|
| What makes it different | - Bounded prompt under a fixed cap while history grows, so costs per call stop climbing on long sessions
- Every run recorded with cryptographic proof: rebuilable prompts, hash-chained journal, re-runnable engine
- Resumes from crash without repeating finished actions using stable idempotency keys
- Budget enforcement before each model call, not reactive overage billing
- No model key storage or logging; your provider bills you directly
| - Self-hosted, air-gapped deployment for complete data sovereignty
- EU-compliant with GDPR, NIS2, and EU AI Act compliance built-in
- Room-scoped AI agents with full permission control and audit trail
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 20 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 4 |
|---|
| Citation Flow (Majestic) | 9 | 31 |
|---|
| Referring domains (Majestic) | 4 | 125 |
|---|
Argentic
PrivOS