| What it does | Virtual phone infrastructure for AI agents
| Agent memory that learns from experience
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2024
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Free trial
| Freemium
|
|---|
| Pricing | Free trial: 14 days free. Starter: €40/month for 1 phone. Team: €129/month for 3 phones. Enterprise: custom pricing. Call minutes: €24/month for 100 minutes, €70/month for 300 minutes, €230/month for 1000 minutes. Android tablet: €69/month (on waiting list).
| Self-hosted: Free, MIT licensed. Hindsight Cloud: Pay-as-you-go with free credits to start. Retain (store memories) $10.00 per million tokens, Recall (retrieve memories) $0.75 per million tokens, Reflect (synthesize patterns) $0.05 per call, Iris Extract (structured extraction) $7.50 per million tok
|
|---|
| Key features | - Real Android 13 OS with Samsung Galaxy S25 device profile
- HTTP API for tap, type, swipe, launch, install, read, screenshot, mic
- Google Play Store and alternative app installation
- Accessibility tree and screenshot reading for screen understanding
- Isolated containers with persistent app state between sessions
- One-to-one voice calls with synthetic voice
- APK upload and installation capability
- MCP server support for local integration
- Dashboard with device management and monitoring
| - Per-user persistent memory with preferences, history and decisions kept separate
- Cross-session persistence allows context to survive weeks between interactions
- Fast parallel retrieval in under 100ms through four strategies running simultaneously
- Works with any LLM without losing learned context when swapping models
- Learns from mistakes and corrects behavior on repeated problems
- Automatic pattern detection synthesizes individual facts into consolidated knowledge
- Conflict detection preserves both old and new states with timestamps when facts change
- Integrates with 20+ coding agents including Claude Code, Cursor, and Copilot
|
|---|
| What makes it different | - Real Android device in the cloud, not a simulator or emulator
- Agents interact via touchscreen like real users without app APIs
- Persistent isolated containers per agent phone with no sharing
- One-to-one voice calls enabling two-way agent communication
- Flat monthly pricing with no runtime metering unlike competitors
| - 94.6% retrieval accuracy on LongMemEval-S, beating next-best system at 74.0%
- MIT licensed open source with no usage limits, telemetry or restrictions
- Reflection layer automatically builds judgment and mental models over time without manual tagging
- Entity resolution handles hundreds of entities with 99.5% query reduction
|
|---|
| 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) | 8 ▲ +2 (up) since last check | 68 ▲ +1 (up) since last check |
|---|
| Trust Flow (Majestic) | 3 | 18 |
|---|
| Citation Flow (Majestic) | 27 | 47 |
|---|
| Referring domains (Majestic) | 25 | 1378 |
|---|
ERIUS PHONE
Vectorize