| What it does | Local-first AI coding memory and recovery for Claude, Cursor, Codex, Gemini, and more
| A fast, lean coding agent for your terminal
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Paid
| Open source
|
|---|
| Pricing | $49 one-time lifetime license, no subscription or recurring fees, Windows/macOS/Linux desktop apps included
| Not given
|
|---|
| Key features | - 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
| - Starts in 13ms and uses only 17MB peak memory
- Works with any model: local or hosted APIs
- Reads Claude Code and Codex settings automatically
- Background runs on separate branches
- Verifies work by running project checks
- Undo function to revert changes
- Sandbox environment for safe command execution
- Spend limits and usage tracking
- MCP server support and plugins
- Scheduled runs
|
|---|
| What makes it different | - 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
| - Fastest coding agent: 1.5ms CPU per turn vs 4.2-145ms for other agents
- Lowest memory footprint at 17MB peak vs up to 960MB for competitors
- Most efficient token usage on real tasks
- Single 20MB portable binary requiring no installation
|
|---|
| 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 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 5 | 0 |
|---|
| Citation Flow (Majestic) | 20 | 8 |
|---|
| Referring domains (Majestic) | 24 | 1 |
|---|
ShardStitch
Chanto