| What it does | One set of memories across every machine you work on
| Desktop app that compresses Claude Code and ChatGPT Codex inputs locally to cut token costs by up to 50%
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| NL
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Mac app free with no account on one machine; $15 per month to sync every machine with 14 days free trial; iPhone app $7.99 once.
| Pro: $4/month billed monthly or $3/month billed annually (for Claude Pro or ChatGPT Plus); Max x5: $20/month billed monthly or $15/month billed annually (for Claude Max x5 or ChatGPT Pro $100); Max x20: $40/month billed monthly or $30/month billed annually (for Claude Max x20 or ChatGPT Pro); Team &
|
|---|
| Key features | - Session capture from Claude Code, Codex and Cursor on Mac and Linux
- Full-text search over all memories by project, kind and machine
- MCP tools in every session for search, recent, status and machines
- Search from any browser at mem.i8l.tech
- Local viewer on 127.0.0.1 answering from hub or local mirror
- Project exclude list kept locally to prevent capture
- Export everything as SQLite file with one-click deletion
- One token per machine, revocable without affecting other machines
- Sync every 15 minutes using content identity
| - Local input compression of tool output and boilerplate
- Reversible compression preserving retrieval of original content
- Real-time savings dashboard and activity tracking
- Eight optional add-ons for further optimization
- Support for Claude Code IDE extensions and agent runners
- Privacy-first architecture with all optimization on-device
- Compatibility with Claude Pro, Claude Max, ChatGPT Plus, and ChatGPT Pro
- Minimal latency overhead of approximately 52 milliseconds
- Support for Windows, macOS, and Linux operating systems
- Project learnings saved to agent instruction files
|
|---|
| What makes it different | - Content identity ensures the same memory from multiple machines lands once safely
- Free on one Mac with no account or setup required
- Memories retained 30 days after subscription ends for export
| - Achieves 25-50% token reduction on typical Claude Code sessions without requiring model subscription upgrades
- All compression runs locally on your machine with no data sent to servers
- Reversible compression preserves output quality and allows retrieval of original content on demand
- Works transparently with existing IDE extensions and agent runners without workflow changes
- Built on open-source Headroom CLI engine available free on GitHub
|
|---|
| 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) | Not checked yet ● no change since last check | 15 ▲ +1 (up) since last check |
|---|
| Trust Flow (Majestic) | 0 | 6 |
|---|
| Citation Flow (Majestic) | 0 | 31 |
|---|
| Referring domains (Majestic) | 0 | 135 |
|---|
memsync
Headroom