| What it does | Personal Agent OS built from memory you own
| The credential layer for AI agents
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| ES
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Not given
| Free: 1 agent, 30 runs/month, public scoring only. Pro: unlimited agents, 1,000 runs/month, private runs, $120/year or $12/month. Team: unlimited agents, 5,000 runs/month, 5 seats, $261/year or $29/month. Enterprise: 25,000 pooled runs/month, SSO, SCIM, from $499/month billed annually.
|
|---|
| Key features | - User-owned memory in Markdown and YAML
- Eight modules: Memory, Flow, Black Hole, Minutes, Codex, Prism, Audio, Facet
- Multi-step AI tasks with human approval checkpoints
- Meeting transcription sealed into memory
- Markdown-to-presentation generation with Prism
- Audio generation from notes
- Visual asset library with provenance tracking
- Private domain boundaries to exclude content from cloud AI
- Project mode to bind files and conversations into sealed context
- Compatible with existing Obsidian vaults without migration
| - Standardised work sample testing with composite scoring (40% success, 30% latency, 30% cost)
- Five-axis diagnostic radar (correctness, latency, cost, tool efficiency, robustness)
- Ed25519-signed certificates with public key verification
- Hiring Frontier cost-per-task analysis across model candidates
- Embedded badge rendering for README files
- Private screening (Pro plan and above)
- Team workspaces with up to 5 seats
- CSV and PDF export
- API access with rate limits
|
|---|
| What makes it different | - Memory and data remain on your device and under your ownership, never used for model training
- Files stay readable as plain Markdown and YAML with any text editor; no vendor lock-in possible
- Works with existing Obsidian vaults natively without import or conversion
- Private-domain content stays out of cloud AI context automatically
- AI recall includes sources so you can see what answers are based on
| - Standardised testing ensures scores are comparable, not self-reported
- Free forever for public scoring with no credit card required
- Model-agnostic testing works with any LLM provider
- Screening completes in under 5 minutes
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 3 ● no change since last check | 1 ● no change since last check |
|---|
| Trust Flow (Majestic) | 9 | 0 |
|---|
| Citation Flow (Majestic) | 21 | 19 |
|---|
| Referring domains (Majestic) | 22 | 10 |
|---|
badgeIA