# Dograh

Open-source self-hosted voice AI platform with visual workflows, MCP support, BYOK model routing, and telephony.

## Agent Decision Summary
- Risk level: moderate
- Source confidence: high
- Recommended workflows: Connector or protocol layer
- Permission surface: messages, external services
- Agent JSON: https://www.openagent.bot/bots/dograh.agent.json

## Summary
Dograh is an open-source voice AI platform positioned as a self-hosted alternative to hosted voice-agent products. It supports on-premise deployment, BYOK model choices, speech-to-speech or modular LLM/STT/TTS workflows, visual workflow building, MCP-native integrations, and telephony support.


## Guide
Dograh is an open-source self-hosted voice AI platform.

### What it is
It combines voice-agent workflows, telephony, BYOK model routing, visual workflow building, and MCP-native integrations.

### Why it matters
Voice agents are moving into real customer workflows, where hosting, latency, provider choice, and auditability all matter.

### How it works
Start with a low-risk voice workflow, test speech recognition and handoff behavior, and evaluate deployment requirements before production use.


### FAQ
- Is Dograh open source?
  - Yes. The GitHub repository is listed under the BSD-2-Clause license.
- Who should evaluate Dograh?
  - Teams building self-hosted voice agents or comparing open alternatives to hosted voice AI platforms should evaluate it.
## What It Does
It combines voice-agent workflows, telephony, BYOK model routing, visual workflow building, and MCP-native integrations.

## How To Evaluate
Start with a low-risk voice workflow, test speech recognition and handoff behavior, and evaluate deployment requirements before production use.

## Why It Matters
Voice agents are becoming a practical bot category, but many teams need control over hosting, telephony, and model providers. Dograh gives voice-agent builders an open-source platform to evaluate.


## Best For
- Teams building self-hosted voice agents
- Developers comparing alternatives to hosted voice AI platforms
- Operators who need telephony workflows with model-provider flexibility

## Not For
- Text-only chatbot projects
- Teams that do not want to operate voice, telephony, or speech infrastructure

## What It Actually Does
- Self-hosted voice platform: Dograh is positioned for on-premise and self-hosted voice AI workflows.
  - Why it matters: Voice agents often touch customer data and telephony systems, so deployment control matters.
- BYOK model routing: The project supports bring-your-own-key across speech-to-speech or modular LLM, STT, and TTS flows.
  - Why it matters: Voice teams can compare providers without locking the whole stack to one vendor.
- Visual workflows and MCP: Dograh includes a visual workflow builder and MCP-native positioning.
  - Why it matters: Voice agents need operational flows, integrations, and tool access beyond a single prompt.

## Typical Use Cases
- Voice support bots: Build inbound or outbound voice agents with human escalation and workflow controls.
- Telephony automation: Evaluate AI workflows connected to phone systems.
- Self-hosted voice experiments: Prototype voice agents while retaining deployment and provider control.

## How It Compares
- When to choose Dograh: Compare it with nearby bots by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need.

## Fit Matrix
- Connector or protocol layer: strong. Dograh has multiple signals for connector or protocol layer, including matching tags, capabilities, category, or positioning. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
- Browser automation: partial. Dograh has at least one signal for browser automation, but should be checked against a real task before adoption. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Coding agent workflow: partial. Dograh has at least one signal for coding agent workflow, but should be checked against a real task before adoption. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Local or private AI stack: partial. Dograh has at least one signal for local or private ai stack, but should be checked against a real task before adoption. Required check: Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
- Reusable skill workflow: partial. Dograh has at least one signal for reusable skill workflow, but should be checked against a real task before adoption. Required check: Run one skill end to end and check whether it produces evidence or structured output.
- Evaluation and observability: weak. Dograh is not primarily positioned for evaluation and observability in the current metadata. Required check: Add one repeatable test case and confirm results can run again in review or CI.

## Evidence
- verified: Dograh is listed as open source. Source: License metadata: BSD-2-Clause
- verified: Dograh has a recorded GitHub repository: dograh-hq/dograh. Source: Resource facts and GitHub source link.
- inferred: Dograh supports these recorded deployment modes: self hosted, cloud. Source: OpenAgent decision signal metadata.
- inferred: Dograh is tagged with support bot, messaging, workflow, mcp capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/dograh-hq/dograh
- Open Homepage: https://app.dograh.com

## Facts
- Category: bots
- Resource type: bot
- Open source: yes
- License: BSD-2-Clause
- Last verified: 2026-06-10
- GitHub repo: dograh-hq/dograh
- GitHub stars: 4313

## Capabilities
- support-bot
- messaging
- workflow
- mcp

## Structured Use Case Tags
- self-hosted-ai
- chatbot

## Getting Started
- Open the GitHub repository: https://github.com/dograh-hq/dograh
- Visit the app site: https://app.dograh.com

## Links
- GitHub: https://github.com/dograh-hq/dograh
- Homepage: https://app.dograh.com

## Structured Outputs
- JSON: https://www.openagent.bot/bots/dograh.json
- Markdown: https://www.openagent.bot/bots/dograh.md
- Agent JSON: https://www.openagent.bot/bots/dograh.agent.json
- Canonical: https://www.openagent.bot/bots/dograh