| What it does | Desktop app that compresses Claude Code and ChatGPT Codex inputs locally to cut token costs by up to 50%
| Mac workspace for building software by directing AI
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2025
|
|---|
| Based in | NL
| IN
|
|---|
| Pricing model | Freemium
| Free
|
|---|
| Pricing | 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 &
| Free during early access. When paid plans begin: USD 14.99 a month (only if you choose to continue; you will be notified before any charges begin).
|
|---|
| Key features | - 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
| - Shared Brain: one persistent memory that every agent shares, starting from past conversations
- Approval-based workflow: review every edit with its plan and exact lines before keeping it
- Code map: every file explained in one sentence with docs and linked files opening in the same window
- Voice and dictation: speak to agents or dictate anywhere on Mac with project-specific speech tuning
- Real terminal: run your own commands beside agents while switching screens
- Calendar and music integration: Google Calendar and YouTube playlists beside your code with read-only access
- Local processing: Brain, voice, and code stay on your Mac; Oplyr never receives your code
- Project-scoped access: AI works only in the project you open and cannot access secrets like .env files
- Model and effort control: switch agent, model, and compute level from top bar with usage in view
|
|---|
| What makes it different | - 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
| - No API keys required: use Claude Code and Codex as you already have them signed in, without any API configuration
- Shared agent memory: both Claude Code and Codex learn from each other, so context is never lost between agents
- Privacy first: your code never leaves your Mac and Oplyr has no access to your AI provider credentials
- Deliberately built: in development since December 2025 with each release tested for real work before shipping
|
|---|
| 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) | 16 ▲ +1 (up) since last check | 1 ▲ +1 (up) since last check |
| Trust Flow (Majestic) | 6 | 0 |
| Citation Flow (Majestic) | 31 | 0 |
| Referring domains (Majestic) | 135 | 0 |