Lampline

Lampline is an open-source, self-hosted platform to build, test, and run voice agents locally or on your own servers.

Lampline lets developers build, test, and run open-source voice agents on their own hardware or servers. It imports existing agents from Dialogflow CX and CX Agent Studio, including flows, pages, playbooks, forms, and tools, and converts them into folders of YAML and Markdown. The platform includes a drag-and-drop builder, a test console that highlights steps in real time, built-in document search, and HTTP and MCP tools. Users can test phone agents over real phone lines using an AI test caller and Google Voice. It supports phone calls and SIP through Twilio, Telnyx, or jambonz, and integrates with models from Anthropic, OpenAI, Gemini, Vertex AI, Azure OpenAI, Bedrock, Groq, Mistral, DeepSeek, Grok, and Ollama.

Lampline at a glance

Best for: Software engineer
Runs on: Web, macOS, Windows, Linux, Docker, CLI, self-hosted, open source
Pricing: Free
Released: October 2026
Category: AI agent tool
Website: github.com/c4rohan/lampline

Key features

Import Dialogflow CX and CX Agent Studio agents
Test voice agents using an AI caller over phone lines
Run agents locally via Docker or native Python
Integrate with 20 model providers including Ollama
Handle phone calls via Twilio, Telnyx, and SIP trunks
Inspect calls live with a step-by-step test console
Store agents as version-controlled folders of YAML and Markdown

Use it for

Building and running self-hosted voice agents
Testing phone agents automatically with AI callers
Migrating voice agents from Dialogflow CX
Deploying local voice models with Ollama

Alternatives to Lampline

VoiceGremlin — Validate AI voice agents with real phone calls and plain English test cases.
Beeline — Combines human team chat and AI agent workflows in a single shared room.
LiteLLM Agent Control Plane — Provides a single API to call all your agents across different runtimes.
Mobilerun — Control real mobile devices and automate tasks with any large language model.
LLMStack — Builds AI applications and agents with custom data without writing code.
OpenHarness — Manages Claude Code, Codex, and Hermes from a single command center.
Clai — Query twelve models and local Ollama directly from your terminal using unix pipes.
Agentloop — Provides a clean agent loop with provider-agnostic LLM access, hooks, and safety budgets.
Agenta — Build and automate AI agents that run on your own infrastructure or the cloud.
MyAgent — It features built-in permission controls, long-term memory, and skill self-evolution.
AgentDock — It coordinates multi-device workflows and provides secure environment access.
Goose — Runs locally on your machine with support for 70+ extensions and any LLM.

All Lampline alternatives