logo

dograh-hq/dograh

Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow...

View on GitHub ↗Jump to charts ↓Open shareable report →

dograh-hq/dograh has 5.5k+ stars and 1.5k+ forks on GitHub, is written in Python, and was last pushed on Oct 18, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 59 minutes ago
Type:Server / PlatformCategory(s):Voice & Speech AIAgent Frameworks & SDKsAI App Builders & PlatformsAI Agents & LLM Apps
Added to GitGenius on May 31st, 2026
Created on September 9th, 2025
Open Issues & Pull Requests: 98 (+0)
GitHub issues: Enabled
Number of forks: 1,501
Total Stargazers: 5,898 (+0)
Total Subscribers: 44 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 2.8 days
Mean response time: 10.4 days
90th percentile: 22.0 days
Tracked items: 140

Most active contributors

Sign in to see contributor activity.
Sign in

Related repositories by overlapping contributors

Maintainer activity

3 people did triage or write work on this repository in the last 12 months.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 18, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits. How this is counted.

How this project is maintained

About 19% of issues opened in the past year have never received a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Almost all tracked open issues have seen activity in the last three months. 70% of issues opened in the past year have been closed, leaving a working backlog. Three people close 89% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 51
New in 7 days: 8
Closed in 7 days: 4
Avg open age: 4 days
Stale 30+ days: 38
Stale 90+ days: 4

Recent activity

Opened in 7 days: 8
Closed in 7 days: 4
Comments in 7 days: 1
Events in 7 days: 3

Top labels

  • bug (69)
  • documentation (6)
  • good first issue (1)
  • question (1)

Most active issues this week

Sign in to see which issues are moving.
Sign in
Explore full issue details

Detailed Description

Dograh is an open-source, self-hosted voice AI platform that provides an alternative to proprietary services like Vapi and Retell.

The platform addresses the need for organizations to build and deploy voice agents without vendor lock-in or reliance on third-party infrastructure. It works by offering a visual workflow builder where users can design voice agents, then deploy them either on their own infrastructure or through Dograh's cloud offering. The tool supports flexible integration with any LLM, speech-to-text, and text-to-speech provider, and includes native support for Model Context Protocol and telephony systems.

Teams should choose this tool if they prioritize data residency, source-level customization, and avoiding vendor lock-in. It suits organizations that want to self-host their voice AI infrastructure or those already committed to open-source tooling. Unlike Vapi and Retell, which are proprietary SaaS-only platforms with per-minute pricing, Dograh is free to self-host and allows complete control over every line of code. The platform also supports bring-your-own-key integration across all AI components, whereas competitors limit customization to their pre-configured integrations.

Maintainers typically respond to new issues and pull requests within a few days. Work in the issue tracker is dominated by bug reports, documentation improvements, and user questions.