Build a voice AI agent that answers calls, qualifies leads, books appointments, and transfers to a human when needed, all from a drag-and-drop workflow builder in your browser. Dograh ships as a Docker Compose stack (API, web UI, Postgres, Redis, MinIO) that you self-host on any Linux server with automatic HTTPS provisioning via Let's Encrypt. The visual workflow builder lets you design multi-turn conversation flows by connecting nodes for greetings, intent classification, tool calls, and handoffs; describe your use case in plain English and the platform generates the LLM prompt and node graph for you. Connect your own speech-to-text, LLM, and text-to-speech providers (OpenAI, Anthropic, Gemini, ElevenLabs, Deepgram, local Whisper, Kokoro, or any OpenAI-compatible endpoint) or use the built-in Speech-to-Speech mode with Gemini Flash Live and GPT-Realtime-2 for sub-200ms latency. Telephony plugs in through Twilio, Vonage, Vobiz, or Cloudonix for inbound and outbound calling, with live agent transfer when the conversation needs a human. Webhook tool calls connect to Salesforce, HubSpot, Google Calendar, Cal.com, or any REST API without writing orchestration code. The ClonedVoice feature mixes real human voice recordings for high-frequency phrases with neural TTS fallback for dynamic content, cutting costs while improving caller trust. A built-in MCP server lets AI coding agents like Claude Code or Cursor design, test, and edit workflows through natural language. Deploy on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD 2-Clause licensed.

Once a voice agent is imported or built, Lampline connects it to a phone line, sends an AI caller to grade real calls, and keeps it all on your own server. Start by importing a Dialogflow CX or CX Agent Studio export along with a report of anything to check, or build fresh in a drag-and-drop builder that mixes LLM steps with scripted pages for exact lines and form fields. Next, pick one of 20 model providers, including Claude, OpenAI, Gemini, Bedrock, Groq, and DeepSeek, or run Ollama with local speech and no API keys. Test by chat or microphone while each step lights up, and let agents call HTTP and MCP tools and save records in collections of their own. Then connect callers through Twilio, Telnyx, or any SIP trunk, PBX, or session border controller via jambonz, with transfers to a person that carry the call's details as SIP headers. Finally, evals phone the agent over a real line, where an AI Test Caller brings background noise, accents, and interruptions, grades each transcript check by check, and reports typical and p95 response times as callers hear them. Each agent stays a folder of YAML and Markdown that you can review in git and lint or test with the vk CLI. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

MikoPBX gives a small business a complete phone system on a server it controls, with extensions, call queues, IVR menus, and call recording instead of per-seat hosted PBX fees. Follow a call through it: incoming rules per provider match exact numbers or patterns, fall through by priority when nobody answers, and end at a default route. Each employee gets an extension with SIP credentials, forwarding for no-answer, busy, and unavailable states, and an optional recording switch. Queues offer seven distribution strategies, including Ring All, Least Recent, Fewest Calls, and Memory Hunt, and can announce each caller's position and estimated wait. IVR menus play a recorded greeting, route keypad choices to departments or extensions, and fall back to a default number after a set number of retries. Call history filters by caller, destination, or DID, flags missed calls in red, and plays or downloads recordings as WebM, MP3, WAV, or OGG. Voicemail, call transfer, call pickup, and a holiday and night-time switcher serve daily needs, while free and paid marketplace modules, among them a softphone, auto dialer, and LDAP/AD sync, handle the rest. A firewall, Fail2Ban, passkey sign-in, and CrowdSec integration protect the system, and a REST API with more than 250 endpoints lets other tools manage it. The interface speaks 26 languages. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

FreeSBC sits at the edge of your phone system so your FreeSWITCH or Asterisk never has to face the public internet. It is the only element with a public address: phones register through it over SIP on UDP, TCP, or TLS, browsers call through WebSocket with WebRTC terminated at the edge (ICE-Lite, DTLS-SRTP, and RTCP-mux, relayed onward as plain RTP), and carriers reach your switch through it as an outbound proxy, with the switch's private addresses hidden from every SDP body, Contact, and Request-URI it constructs. The switch stays on a private LAN as the registrar and call brain, holding credentials and carrier accounts, while FreeSBC anchors all media on its own ports with hardened first-packet latching and a silence watchdog, and never transcodes. Against the background radiation of SIP scanning, it applies per-IP rate limits with separate limits for carrier sources, scanner fingerprinting with in-memory bans, and admission control for public INVITEs and REGISTER enumeration, and every denial is a silent drop. A multi-switch pool hashes users across switches, and one fixed private socket keeps the trusted side simple. The embedded WebUI, REST API, and Prometheus metrics sit behind a bcrypt-checked admin login, showing live calls and media ports. One static binary, one YAML file, no database, no Redis, and no separate media process to babysit. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

One Janus installation can host a video meeting in one session, stream a camera feed in another, and bridge a browser call into a telephone network in a third, because Janus is a general-purpose WebRTC server whose work is done by interchangeable plugins. The VideoRoom plugin publishes each participant's streams to everyone else in the room with simulcast and viewport selection, so a class or team call adapts quality per viewer instead of forcing one bitrate on all. Streaming mounts live or prerecorded sources, including RTSP cameras and RTP feeds, and hands them to any number of WebRTC viewers, while AudioBridge mixes voices into conference rooms with recording and signed-token access. SIP and NoSIP plugins register with existing VoIP infrastructure and place or receive calls, translating between WebRTC media and telephone audio so a web page can ring a desk phone. Record&Play captures publisher streams to files you can replay through the same server, TextRoom adds data-channel chat rooms, and Lua or JavaScript plugins let you script custom media logic without recompiling the core. Applications talk to Janus over HTTP or WebSocket APIs, with RabbitMQ, MQTT, and NATS transports for bus-driven deployments, and event handlers report session activity to your monitoring stack. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

With over 20,000 GitHub stars and adoption by companies building everything from telehealth platforms to AI voice agents, LiveKit is the most widely deployed open-source real-time communication server available. The Go-based Selective Forwarding Unit handles hundreds of concurrent participants per node with adaptive bitrate streaming, simulcast layers, SVC codec support for VP9 and AV1, and end-to-end encryption. Client SDKs span JavaScript, Swift, Kotlin, Flutter, React Native, Rust, Python, Unity, and ESP32 embedded devices, while server-side APIs cover Node.js, Go, Ruby, Java, Python, Rust, PHP, and .NET. The Agents framework enables building AI-powered voice and video applications — real-time speech-to-text, LLM-driven conversations, and computer vision pipelines — running as server-side participants in any room. Egress records sessions to S3-compatible storage or streams to RTMP endpoints, while Ingress pulls external feeds from OBS via RTMP, WHIP, or SRT into LiveKit rooms. The SIP bridge connects traditional telephony to WebRTC rooms for hybrid conferencing. JWT-based authentication, webhook notifications, room-level moderation APIs, and selective subscription give operators granular control. Deploy as a single binary for development, Docker Compose for production single-node, or Kubernetes with the official Helm chart for distributed multi-region clusters using Redis for state coordination. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Build, deploy, and monitor chatbots and LLM-powered agents on one open-source conversational AI platform: Botpress. Its Studio is a visual development environment: a drag-and-drop canvas arranges conversation logic with nodes for messages, questions, choices, and actions, while a built-in emulator simulates conversations for debugging before anything goes live. Agents ground their answers in a knowledge base assembled from uploaded documents, ingested websites, and past conversations via retrieval-augmented generation, and the LLM layer connects to multiple model providers - GPT-4, Claude, Mistral - with a configurable model strategy. An autonomous engine handles reasoning, tool orchestration, persistent memory across sessions, and sandboxed code execution, and custom code actions in TypeScript extend agents past prebuilt workflows. Over 100 integrations deploy the same bot to WhatsApp, Telegram, Slack, Microsoft Teams, and web chat, and connect it to HubSpot, Zendesk, Zapier, and arbitrary APIs and webhooks. Human handoff, conversation analytics, and quality monitoring cover production operation. Originating in 2017 from a Montreal team, the community edition is developed openly on GitHub.

Tiledesk lets you build AI-powered conversational agents with a visual drag-and-drop designer, then deploy them simultaneously across web chat, WhatsApp, Telegram, Facebook Messenger, Instagram, email, and Slack without rebuilding per channel. The no-code Design Studio combines LLM-powered conversations with conditional logic, external API calls, and branching dialogue trees that work identically everywhere. Multi-RAG knowledge management separates content into isolated repositories with hybrid search combining traditional full-text retrieval and semantic understanding via Qdrant vector embeddings, enabling accurate answers even when users phrase queries in unexpected ways. LLM integration supports GPT-4, GPT-4o, Anthropic Claude, and any model exposing an OpenAI-compatible API including locally hosted models via Ollama for complete data sovereignty. The human-in-the-loop system provides seamless escalation from AI agents to live support staff with full conversation context preserved, while multi-agent workflows enable complex orchestration where specialized bots collaborate on different aspects of a customer interaction. REST and MQTT APIs power integration with external systems and webhook-triggered automations, and pre-designed templates accelerate common scenarios. Docker Compose deployment starts the full stack including server, dashboard, messaging engine, and widget. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Add a live support desk to any website with Live Helper Chat, where visitors talk to operators or bots and you own every transcript. Site owners paste a generated embed snippet into any page, and the start-chat fields are customizable. Chats are routed by department, language, location, or custom attributes, wait in a priority queue, and move between agents. Operators, departments, and simultaneous chats are unlimited. Agents watch a visitor type before the message is sent, read pages visited and time on site in the online visitors list, and send proactive invitations to people who linger. Voice, video, and screen sharing run through Jitsi or Agora, and a screenshot shows what the visitor sees. Bot designers chain triggers and actions in a visual builder, call ChatGPT, Gemini, Ollama, Rasa, or any REST API, and hand the conversation to a person when needed. Incoming email becomes tickets beside chats, and extensions connect Telegram, WhatsApp, Facebook Messenger, and Twilio SMS. Staff answer from the browser, a desktop app, a Chrome extension, or iOS and Android apps. Management tools include roles, groups, statistics, transcripts, and an archive, and extensions add two-factor login, LDAP, and single sign-on. It suits banks, healthcare teams, universities, and game studios that must keep chat data in house. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Unleash the power of Chatwoot, the open-source superhero in the world of customer experience! This platform is perfect for businesses craving to connect with their customers across a multitude of channels without breaking the bank. Wave goodbye to the high-and-mighty likes of Intercom, Zendesk, and Salesforce Service Cloud, and say hello to a wallet-friendly powerhouse. Chatwoot turns your agents into customer service ninjas, armed with the latest in workload management, performance tracking reports that refresh themselves (because who has time for that?), and automations that work smarter, not harder. Zap through conversations with lightning-fast responses and manage your social media and email interactions in a single bound. Plus, with Chatwoot, you get to be the Sherlock of customer satisfaction, deducing your CSAT scores on autopilot. All this hosted on RepoCloud, where the cost is as tiny as the effort you'll need to switch over. Get ready to engage, enlighten, and entertain your customers with Chatwoot!

Support teams handling website live chat, email queues, and social messaging channels gain a unified, AI-assisted helpdesk in Bytedesk. Incoming conversations from web widgets, mobile SDKs, WhatsApp, WeChat, and email flow into a single agent workbench equipped with skill-group routing, VIP priority rules, and automatic human handoff. Customer-facing AI agents connect to Ollama, DeepSeek, OpenAI, Qwen, and Zhipu models to answer recurring inquiries using retrieval-augmented generation (RAG) over internal knowledge bases and FAQ libraries, complete with function calling and Model Context Protocol (MCP) tool execution. Complex escalations convert into SLA-tracked tickets with custom approval workflows, or transition directly into browser-based WebRTC video calls, screen sharing sessions, and FreeSwitch voice call center queues. Supervisors track real-time queue depth, bot resolution rates, token usage, automated AI quality scores, and customer satisfaction surveys from the analytics dashboard. Native client SDKs for Web, iOS, Android, Flutter, UniApp, WordPress, and WooCommerce make embedding customizable chat widgets straightforward across any storefront. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

With 26,000 GitHub stars and consistent victories over ElevenLabs in blind evaluations, Chatterbox delivers state-of-the-art text-to-speech with zero-shot voice cloning requiring only 5 seconds of reference audio. The model family spans three architectures: Chatterbox Multilingual V3 (500M parameters, 23+ languages including Arabic, Chinese, Japanese, Korean, Hindi, French, German, Spanish, and Portuguese), Chatterbox-Turbo (350M parameters optimized for voice agents with a single-step distilled decoder achieving ~200ms time-to-first-speech), and Chatterbox-Nano (110M parameters running 3x faster than realtime on 8 CPU cores for edge deployment). Unique among open-source TTS systems, Chatterbox introduces emotion exaggeration control — adjusting intensity from monotone to dramatically expressive via a single parameter — and native paralinguistic tagging where tokens like [laugh], [cough], [chuckle], and [gasp] inject natural vocal reactions inline without post-processing. The alignment-informed inference pipeline eliminates hallucinations and repetition artifacts common in autoregressive TTS. Built-in PerTh neural watermarking embeds imperceptible forensic identifiers in generated audio for provenance tracking. Trained on 500,000 hours of cleaned speech data across all supported languages. Voice conversion scripts enable transforming existing audio into any cloned voice. Deploy via pip install with PyTorch, serve through Gradio interfaces or custom FastAPI endpoints, and expose via HTTP streaming or WebSocket for sub-200ms conversational applications. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.