| What it does | Autonomous AI coding agent with deterministic program repair
| Mac workspace for building software by directing AI
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2025
|
|---|
| Based in | ID
| IN
|
|---|
| Pricing model | Freemium
| Free
|
|---|
| Pricing | Core Basic: free (20 CLI / 15 Web runs per day, 50K daily AST tokens). Apex Pro: $11/month (100 CLI / 75 Web runs per day, 250K daily AST tokens). Sovereign Ultra: $44/month (400 CLI / 300 Web runs per day, 1.0M daily AST tokens). Annual subscriptions include 2 months free.
| 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 | - 4.1µs C-ABI latency native Rust Sub-Cortex execution
- Zero dirty diffs with strict AST grammar validation and dry-run verification
- Support for 6 production languages: Python, Rust, TypeScript/JavaScript, Go, C/C++, and Java
- Polyglot language engines with direct Tree-sitter CST surgery
- Machine-to-Machine sub-cortex infrastructure for autonomous agents
- Zero Code Retention policy with ephemeral in-memory processing
- 91.3% AST token pruning for repository context efficiency
- Multi-file repository context with automated test-runner verification
- Automated 5-Whys Root Cause Analysis and SRE incident diagnostics
- System-wide dependency mapping and security audit capabilities
| - 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 | - Eliminates 95% of LLM token overhead through deterministic compiler verification instead of probabilistic inference loops
- Operates locally with strict Zero Code Retention policy—no code logging, storage, or model training usage
- Sub-microsecond repairs in CPU L1 cache without garbage collection pauses via native Rust FFI
- Engineered as M2M sub-cortex infrastructure for autonomous agents, not consumer chatbot utility
| - 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) | Not checked yet ● no change since last check | 1 ▲ +1 (up) since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 15 | 0 |
| Referring domains (Majestic) | 2 | 0 |