| What it does | Persistent memory for AI coding agents that persists across sessions and tools
| Autonomous AI software engineer that connects to GitHub to resolve issues and ship pull requests
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Free trial
| Not given
|
|---|
| 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
| - GitHub integration for issue assignment and pull request automation
- Evidence-backed pull requests with test results and recordings
- Automated bug reproduction and verification
- Dedicated computer environment per session
- Mobile access to monitor tasks
- Cloud and local runtime options
- Test automation and code verification
|
|---|
| 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
| - Evidence-based code changes with recorded proof of testing and verification
- 22% more cost efficient than competitor models
- Opinionated architecture that improves the entire development loop
- Built for trust with real repositories and careful verification
- Maintains human judgment while automating mechanical coding tasks
|
|---|
| 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) | 3 ● no change since last check | 26 ● no change since last check |
|---|
| Trust Flow (Majestic) | 4 | 10 |
|---|
| Citation Flow (Majestic) | 22 | 34 |
|---|
| Referring domains (Majestic) | 40 | 245 |
|---|
Decispher Memory
Reason