3 apps Chatfuel
AstrBot screenshot thumbnail

AstrBot

Getting a language model into the chat apps people already use takes a single self-hosted server running AstrBot, which answers in QQ, Telegram, Discord, Slack, Lark, DingTalk, LINE, and WeCom. The model itself is a setting. OpenAI-compatible endpoints, Anthropic, Google Gemini, DeepSeek, Ollama, and LM Studio all work, with fallback models and retry limits for failed requests, and Dify, Coze, or Alibaba Cloud Bailian can take over a conversation too. A bare model cannot act, so the built-in agent calls MCP servers and Skills, delegates to SubAgents, runs scheduled tasks, and executes code in an isolated sandbox. It cannot read your files either, so a knowledge base takes PDF, Word, Markdown, and EPUB uploads and searches them with hybrid dense and BM25 retrieval. Personas shape each bot's personality, and Whisper or Edge TTS adds speech. When an answer looks wrong, the ChatUI shows thinking, tool calls, token counts, and latency, and a per-message trace timeline shows how the bot got there. Because the panel steers the bot, administrator IDs, session whitelists, optional TOTP login, and HTTPS protect it. Backups live under System Settings, and the plugin market installs any of more than 1,000 extensions in one click. 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.

Deploy
BrightBean Chat screenshot thumbnail

BrightBean Chat

BrightBean Chat is a self-hosted chat automation platform that builds visual flows once and runs them across Instagram, WhatsApp, Messenger, Telegram, SMS, and email, so your audience automations live on your server instead of a per-contact subscription. You drag conditions, delays, randomizers, data collection, and message nodes onto a canvas, test the draft while the live version keeps running, then set it live with every save versioned. Flows start from keywords, comment-to-DM triggers, story mentions and replies, follows, ref URLs, QR codes, or calls to the public API. Every channel lands in one shared inbox where teammates assign conversations, label them, schedule replies, and take over from the bot, which pauses the automation for that contact. Contacts carry custom fields, tags, and segments that stay unified across channels, and imports and exports keep the list portable. Broadcasts and multi-step drip sequences check opt-outs and each platform's 24-hour messaging window before sending, pace themselves per channel, and show exactly who will receive a message and who is skipped. Per-node counters track sent, delivered, failed, and clicked, while a bearer-authenticated REST API and signed webhooks hand leads to Make, Zapier, n8n, or your own systems. 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.

Deploy
OpenReply screenshot thumbnail

OpenReply

Someone comments LINK under your Instagram reel, and OpenReply, a free self-hosted ManyChat alternative, sends them a private DM with your link automatically. Each campaign ties one or many keywords, matched as whole words or partial, to a post or reel, and can add a public reply under the comment. The same keywords also fire on inbound DMs and text replies to Stories, so "Reply LINK to this Story" works with no post at all. Messages greet people by name with {username}, carry up to two link buttons, and route through tracked redirects that report clicks and click-through rate per campaign. An optional follow gate holds back the link until the person follows you, re-prompting until they do. The inbox lets you read Instagram conversations and reply from the dashboard within Meta's 24-hour window, and delivery logs record every send, skip, and failure with a reason. Sending stays under Meta's cap of 750 private replies per hour for each account, with overflow queued rather than dropped. Agencies can connect several Instagram accounts to one workspace, invite clients as owner, admin, or member, start from campaign templates, and read campaign settings and stats through a read-only API and MCP server. The dashboard speaks English, Traditional Chinese, Brazilian Portuguese, and Russian. Connect through Zernio's managed connection or your own Meta app, with no password sharing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy