| What it does | Small model. Big decisions.
| Local-first AI coding memory and recovery for Claude, Cursor, Codex, Gemini, and more
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | CA
| Not given
|
|---|
| Pricing model | Freemium
| Paid
|
|---|
| Pricing | Test plan: 125 million free input tokens per month with test_sk keys. Production plan: $0.04 per million input tokens with prod_sk keys (no charge for output tokens). Minimum credit bundle of $10 to unlock production access.
| $49 one-time lifetime license, no subscription or recurring fees, Windows/macOS/Linux desktop apps included
|
|---|
| Key features | - Classification with score distribution and confidence
- Text and image extraction
- Yes/no decisions with probability
- Entity recognition and extraction
- Field verification against source
- Multi-level classification (classify-tree)
- OpenAI SDK compatibility
- Sentiment or tone rating
- Question answering with source spans
- SDK support for TypeScript and Python
| - Session recovery across 31 AI coding tools including Claude, Cursor, Codex, Gemini, Cline, Devin, Windsurf, and more
- Git-aware state tracking with branch, diff, changed files, and recent commits
- Dependency graph showing file relationships and god-node detection
- 49 MCP tools callable directly from Claude Code, Cursor, Devin, and Windsurf
- Session Vault for local recovery history after crashes and outages
- Zero telemetry with local recovery and optional explicit exports only
- Hivy on-device intelligence for context trimming and drift detection
- Windows, macOS, and Linux desktop apps with CLI and VS Code/Cursor extension
- Council 12-agent review layer for risky handoffs to surface stale assumptions
|
|---|
| What makes it different | - Optimized for bounded decisions with millisecond latency, avoiding slow token-by-token generation
- Extremely cost-effective at $0.04 per million input tokens with no output token charges
- 125 million free test tokens monthly with no card required
- Production-ready with REST API, SDKs, and CLI interfaces
- Structured responses enable direct application logic without additional parsing
| - Recovers from disk state without needing the old session alive, unlike transcript-based approaches
- Works after the session ends or is locked out, unlike /compact or /handoff skills
- Formats for 31 AI tools instead of locking you into one platform
- Local-first with zero telemetry and no cloud sync unless explicitly configured
|
|---|
| 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) | 18 ● no change since last check | 8 ● no change since last check |
|---|
| Trust Flow (Majestic) | 28 | 5 |
|---|
| Citation Flow (Majestic) | 31 | 20 |
|---|
| Referring domains (Majestic) | 42 | 24 |
|---|
milliseconds.ai
ShardStitch