| What it does | One memory. Every AI. Only yours.
| Career context layer for AI agents powered by structured assessments
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Not given
| Starter: Free with 10 AI credits per month and MCP server access. Pro: $9/month includes 500 AI credits, 1,000 Context API reads, and full profile with evidence trail. Coach: $490/year includes 50 sponsored client profiles per year and pooled API quota. Enterprise: Custom pricing. AI reports: $2 per
|
|---|
| Key features | - Chrome extension integration with ChatGPT, Claude, Gemini, Grok, DeepSeek and Kimi
- MCP server for coding tools like Cursor and Claude Code
- Python and TypeScript SDKs for custom agent integration
- Save conversations, web pages, documents and connected app content
- Review, correct and remove saved memory
- Control which AI tools access specific memories
- Export memory in documented formats
- Local deployment option with Python 3.12 or 3.13
- 93.1% answer accuracy on LoCoMo benchmark
- 67% fewer tokens than full conversation history on LoCoMo
| - Seven core assessments: RIASEC interest patterns, Big Five work style, Values, Skill confidence, True Colors temperament, DISC behavioral style, and Work approach preferences
- Structured JSON output with dimension scores, evidence trail, and constraints for agent consumption
- REST API and MCP server for agent integration
- Consent-scoped access with per-agent permissions and instant revocation
- Complete audit log tracking all agent reads and access
- Version history of assessments with 90-day retention
- Export profile as JSON or Markdown
- AI-powered career reports and agent-ready briefs
|
|---|
| What makes it different | - One unified memory across all your AI tools instead of separate memories in each
- Complete user control: review, correct, delete and export your memory anytime
- Runs hosted or locally on your own machine
- Published benchmark method and results for transparency
- Open source SDKs, CLI and MCP server on GitHub
| - Consent-first architecture ensures data is never shared without explicit permission
- Structured, machine-readable profile designed specifically for AI agent integration
- Fully portable and revocable—export everything or delete your account completely
- Single source of truth prevents re-explaining yourself to multiple tools
- Evidence trail with sources traceable back to original assessment dimensions
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 28 ▼ −1 (down) since last check | 16 ● no change since last check |
| Trust Flow (Majestic) | 11 | 6 |
| Citation Flow (Majestic) | 32 | 21 |
| Referring domains (Majestic) | 73 | 19 |