| What it does | An AI workforce that runs on your machines
| Connect your team's documents and websites to Claude, ChatGPT, Cursor or any MCP client for grounded answers with sources
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: $0/mo (1 agent, 10k API calls/mo). Starter: $9/mo (2 agents, additional agents $7 each). Pro: $29/mo (5 agents, additional agents $5 each). Business: $99/mo (25 agents, additional agents $3 each). Agentic OS early access is free while in beta.
| Starter $19/month (100 MB knowledge, 1,000 answers/month), Pro $49/month (1 GB knowledge, 5,000 answers/month), Scale $199/month (10 GB knowledge, 25,000 answers/month). 14-day free trial available.
|
|---|
| Key features | - Command Center shows goals, plans, and shipped work with pull request integration
- Agent runs on your own hardware with persistent, stoppable execution
- Signed, tamper-evident receipts for all memory access
- Encrypted Vault for private information sealed in browser before upload
- Trust score from 0 to 1000 based on verifiable activity
- Verified badge eligibility for published agents
- MCP tools for building and publishing custom agent capabilities
- JavaScript and Python SDKs with auto-instrumentation for tracking
- Cryptographic verification that instructions come from your workspace
- Full memory export with no vendor lock-in
| - Connect via MCP to Claude, ChatGPT, Cursor, Windsurf and any Streamable HTTP + OAuth 2.1 client
- Live web page crawling and indexing as sources
- OpenAI-compatible API for Responses and Chat Completions
- Named agents with scoped bucket access and policies
- Inline citations and structured source lists with signed links
- No vector database to manage or run
- Revoke client access within one minute
|
|---|
| What makes it different | - Agents run on your machines with full data privacy and local execution
- Verifiable, tamper-evident audit trail for every agent action
- Agent memory persists across model changes with no loss of context
- Finished work delivered, not chat logs—pull requests and shipped tasks
- Earn from published agents through creator payouts on the directory
| - Multimodal RAG that reads PDFs, images, charts and screenshots as sources
- Every answer includes citations and a source list users can verify
- No API key required for client connections, sign in with Calypso instead
- Knowledge stays isolated in your workspace and never trains shared models
- One URL works across Claude, ChatGPT, Cursor and any MCP client
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 7 ● no change since last check |
| Trust Flow (Majestic) | 0 | 1 |
| Citation Flow (Majestic) | 13 | 29 |
| Referring domains (Majestic) | 4 | 41 |