| What it does | Persistent memory for AI coding agents that persists across sessions and tools
| Context-aware voice dictation that automatically formats speech for each app
|
|---|
| Stage | MVP
| Startup
|
|---|
| Founded | 2026
| 2024
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Free trial
| Free trial
|
|---|
| Pricing | Early access, enabled per company while onboarding founding teams. 50 free credits on signup, no credit card required.
| Not given
|
|---|
| Key features | - Preferences injected into every session on every AI coding tool
- Three scopes: personal, project, and company
- Auditable receipt for every memory injection
- Owner-editable and hard-deletable memories on demand
- Import from existing ChatGPT or Claude exports
- Engineering and general modes for non-engineering teams
- Works with Claude Code, Cursor, Codex and Grok Build
- Private stays private, every serve leaves a receipt
- Memories filtered per scope, not hidden in UI
- No credit card required to start
| - Context-aware formatting tailored to different apps
- 18 built-in contexts with unlimited custom contexts
- Auto-paste directly into any text field
- Three processing modes: Cloud, Bring Your Own Key, and Local
- Works across Mac, Windows, Linux, iPhone, and Android
- Hotkey activation from any app without tab switching
- Integration with AI assistants like Claude and ChatGPT
- Full on-device privacy mode with no data transmission
- Streaming transcription support
- Transcript storage and export locally on device
|
|---|
| What makes it different | - Solves the hidden tax of repeating the same instructions to AI agents every session
- Keeps personal preferences private while maintaining team and company policies
- Reduces context window token usage by 2.7x compared to raw history
- Immediate deletion with bodyless receipts for audit compliance
- Attached to you, not to a vendor's session store
| - Only AI dictation that respects privacy with local on-device processing
- Context-aware formatting outputs different formats from the same spoken words
- No tab switching or app switching required
- Eliminates manual cleanup and reformatting of dictated text
- Works in any application with a text field
|
|---|
| 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) | 4 ▲ +1 (up) since last check | 51 ● no change since last check |
|---|
| Trust Flow (Majestic) | 4 | 3 |
|---|
| Citation Flow (Majestic) | 22 | 38 |
|---|
| Referring domains (Majestic) | 40 | 159 |
|---|
Decispher Memory
Contextli