Dograh
Open-source voice AI platform with visual workflow builder
Visit app.dograh.com ↗What is Dograh?
Dograh is an open-source, self-hostable voice AI platform for building production voice agents. It offers a visual workflow builder, supports any LLM/STT/TTS provider, and can be deployed on-premises or self-hosted with no vendor lock-in. The project describes itself as an open-source alternative to Vapi and Retell. According to the repository, the platform is built with AI coding assistant support through MCP integration, allowing Claude Code and similar tools to help with setup and agent design.
Designed for teams needing data residency, regulatory compliance, and full transparency, Dograh provides speech-to-speech capabilities, flexible model integration, and source-level customization. It supports both cloud and self-hosted deployment options, with enterprise on-premises deployment available for regulated and high-scale teams.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Dograh automatically. Evidence: GitHub dograh-hq/dograh; repo has .claude, AGENTS.md, CLAUDE.md. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces

Manage teams of AI agents to run your business from one dashboard

Persistent memory for AI agents across Claude Code, Cursor, and MCP clients