Sensors watch your infrastructure so your engineers do not have to watch it at 3 a.m. StackStorm is event-driven automation: Python sensors poll or listen to external systems (monitoring alerts, ticket updates, chat messages, webhooks, timers) and inject each event as a trigger. Rules match triggers against criteria you define and fire the response automatically, mapping the event payload straight into action parameters. Actions do the work: SSH commands, REST calls, and integrations for AWS, Docker, OpenStack, Puppet, Jira, Slack, and hundreds more from community packs, or your own scripts wrapped with a few lines of metadata. Multi-step responses become workflows that sequence actions with conditions, branching, and data passed between tasks, handling everything from disk-full remediation to full deployment pipelines. Everything bundles into packs, the shareable units that group sensors, rules, actions, and workflows per product or per automation, installable from the StackStorm Exchange or your own Git repositories. The web UI runs actions, explores workflow executions down to individual task results in real time, manages rules, and installs packs, while every execution, manual or automated, lands in an audit trail with its triggering context. ChatOps aliases even let the team trigger approved automations from chat. 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.

Vocero CRM turns WhatsApp into your sales floor, with a shared team inbox, a visual pipeline, and an AI agent that answers customers using only what your business taught it. Incoming messages land in a three-column inbox within two seconds, showing sent, delivered, and read states, enforcing the official 24-hour window, and offering approved templates when it closes. Every person who writes becomes a contact automatically and enters a Kanban pipeline you can rename, where dragging a card, adding notes, or archiving a lead takes seconds. The AI agent learns from question-and-answer pairs and free-text knowledge blocks, and answers only from what it knows. It bundles message bursts into one reply and hands the conversation to a human whenever the customer asks or the rules say so. Before the agent ever meets a real customer, the Laboratory sends six simulated customers at it, from the decided buyer to the angry one, and an independent judge scores each conversation from 0 to 100 with findings and one-click fixes you can re-test after every change. Owners create team accounts, message templates sync their approval status from Meta, and WhatsApp tokens sit encrypted at rest while every customer record stays on hardware you own. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

When an alert fires, OnGrid investigates it for you: an AI operations agent that correlates metrics, logs, traces, and topology, then names the root cause in plain language. A coordinator agent hands each question to specialist SRE, network, or database sub-agents, and the incident investigator walks the service graph for blast radius, queries Prometheus, Loki, and Tempo, and pins the cause to a line of source code before posting its report back to chat. Lightweight edge agents on every host dial out over a single tunnel, so no inbound ports are opened, and operators can reach any machine through an audited browser shell. The agent works through more than 26 read-only inspection tools in a sandbox, while anything that changes production waits behind an approval gate. Ask questions or receive reports in Slack, Telegram, Larksuite, DingTalk, or WeCom, and run it on Anthropic, OpenAI, GLM, DeepSeek, Gemini, Kimi, or any OpenAI-compatible endpoint. A workflow builder turns triggers, agents, tools, and notifications into repeatable automations, and a knowledge vault indexes runbooks, incident history, and repositories for search. Enroll Kubernetes clusters to inspect workloads and manage upgrades, or discover network neighbors, verify them over SNMP, and map them into the topology. Role-based access separates admins, users, and viewers. 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 34,000+ GitHub stars and a v1.5 release driven by 36 merged community pull requests, DeepTutor from Hong Kong University's Data Science Lab delivers a full agent-native learning workspace that goes far beyond chatbot wrappers. Eight integrated surfaces — Chat, Deep Solve, Quiz Generation, Deep Research, Math Animator, Co-Writer, Book generation, and Mastery Practice — share a unified context so the objective follows the learner, not the tool. The platform's three-layer memory architecture (L1 working, L2 session, L3 long-term) makes personalization inspectable rather than opaque, letting users see exactly what the system remembers and why. Knowledge retrieval operates across five pluggable engines — LlamaIndex with FAISS vectors, PageIndex for page-level citations, GraphRAG for knowledge-graph traversal, LightRAG for local or server-offloaded retrieval, and linked Obsidian vaults — with document parsing via MinerU, Docling, markitdown, or PyMuPDF4LLM. Partners extend the tutoring brain to 15+ messaging platforms including Slack, Discord, Telegram, Matrix with E2EE, and Mattermost, each carrying private memory with branch, resume, and replay capabilities. Subagent integration brings Claude Code, Codex, Gemini, and Kimi directly into learning sessions. The system supports 30+ LLM providers from OpenAI and Anthropic to Ollama for fully local operation, with multi-user isolation, admin controls, and a full CLI interface. 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.

Telegram Desktop's export is a file you make once by hand; Telegram Archive is a self-hosted backup that keeps saving your chats on a schedule and in real time, then lets you read them in a viewer that looks like Telegram. After one login with the code Telegram sends you, it stores messages, photos, videos, voice notes, stickers, documents, and link previews, saving each file once even when several chats share it. A live listener captures new messages, edits, and reactions as they happen, and a daily full pass fills any gaps. Every edit keeps its earlier text as a version, and with deletion tracking switched on, deleted messages stay in the archive marked as deleted. The viewer offers folders, forum topics, archived chats, pinned messages, polls, shared media, and search across every chat, plus a What changed feed of deletions, edits, and transcripts. Voice notes can be transcribed into searchable text by a server you run or rent. Family or colleagues get logins limited to chosen chats, or a share link that opens a single chat. One archive holds several accounts, a Telegram Desktop export can be imported for older history, and twelve themes suit phones and desktops. 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-or-later licensed.

Casibase lets organizations build AI-powered knowledge bases that answer questions from their own documents, connecting to 30+ model providers through a unified admin interface with RAG retrieval and multi-agent orchestration via MCP and A2A protocols. The platform plugs into OpenAI GPT-4o, Anthropic Claude, Meta Llama, Google Gemini, DeepSeek, Ollama local models, HuggingFace, Azure OpenAI, and additional providers, while embedding APIs from OpenAI Ada and Baidu handle vector representation of ingested documents. Document ingestion parses TXT, Markdown, DOCX, PDF, CSV, XLSX, and PPTX files with intelligent chunking strategies for optimal retrieval accuracy. The built-in chat interface provides real-time AI conversations with manual session handover for human agent escalation, and comprehensive chat session logging enables audit trails for compliance. Enterprise identity management integrates Casdoor for Single Sign-On supporting GitHub, Google, WeChat, and OIDC providers with fine-grained access control via the Casbin permission engine. The multi-tenant architecture supports isolated knowledge bases per organization with role-based user management and configurable storage, model, and embedding providers per tenant. The React frontend with Ant Design v5 provides a polished admin dashboard for managing providers, knowledge stores, chat sessions, and user access, while the Go backend with Beego framework handles API logic with MySQL or MariaDB persistence. 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.

Chitchatter is a browser-based chat room for text, voice, video, screen sharing, and file transfers that exists only while its members are connected and keeps no record of what was said. Every visit starts with a random room name generated on your device, a UUID or a readable passphrase, and you invite people with the link or a QR code. Public rooms admit anyone with the link; private rooms also require a matching password. Messages support Markdown, multiline text, and code blocks, and clicking a name opens a direct conversation. Newcomers to public rooms receive the earlier conversation from peers already there, and typing indicators show who is writing. Start an audio or video call, share your screen to walk a relative through a settings problem, or hand over a file of any size, encrypted before it leaves your browser. Public-key checks verify each peer automatically, with a green lock marking everyone who passes and an icon showing whether the link is direct or relayed. Embed a room in any web page with an iframe or a web component that takes a room name, user name, and color mode. Light and dark themes are built in, and notifications and sounds announce new messages while you work in another tab. Close the tab and the transcript disappears. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-2.0 licensed.

Twitch and YouTube Live, replaced by infrastructure you control: Owncast is a self-hosted live streaming and chat server. Point OBS, Streamlabs, or any RTMP-capable broadcaster at the server's ingest port, and Owncast transcodes the feed with FFmpeg into HLS with multiple quality variants, playing it in a built-in web page with a real-time chat beside it. Chat supports anonymous participation, custom emotes, and moderation tools - message removal, user bans and suspensions - with optional authentication via IndieAuth or a Fediverse account. ActivityPub integration puts the stream on the Fediverse: viewers on Mastodon and compatible services can follow a channel and get notified the moment it goes live. Video delivery can come straight off the server or offload HLS segments to S3-compatible object storage so a modest VPS handles thousands of concurrent viewers while only managing ingest and chat. The backend is a single Go binary with a React frontend - no accounts platform, no database server, no dependency stack - and the player embeds in any website. MIT-licensed, with roughly 9k GitHub stars, zero platform fees, and no algorithm or takedown policy between you and your audience.

With over 82,000 GitHub stars and 700,000+ downloads, LobeHub has evolved from its origins as LobeChat into a comprehensive multi-agent AI collaboration platform where humans and autonomous agent teams co-evolve. The platform's Agent Harness architecture functions as an operating system between AI models and applications, handling prompt presets, tool orchestration, lifecycle hooks, planning, filesystem access, and sub-agent management across 25+ model providers including OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Mistral, Groq, AWS Bedrock, Azure OpenAI, and local models through Ollama. Agent Groups enable sophisticated collaboration with sequential, parallel, iterative, and debate orchestration modes, allowing multiple specialized agents to tackle complex workflows simultaneously. The Agent Builder creates production-ready agents from natural language descriptions with auto-configuration, drawing from a marketplace of 505+ pre-built agents and 10,000+ MCP-compatible skills and plugins. Pages provide collaborative document editing with multi-agent co-authoring, while Schedules automate agent runs around the clock without human supervision. The knowledge base leverages PostgreSQL with pgvector for RAG-powered retrieval, and Personal Memory gives agents transparent, editable context that evolves through continual learning. The full self-hosted stack deploys via Docker Compose with PostgreSQL, Redis, RustFS for S3-compatible storage, and SearXNG for private web search, all configurable through environment variables. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. LobeHub Community licensed.

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.

Nodyx puts forum threads, real-time chat channels, peer-to-peer voice calls, collaborative whiteboards, and a drag-and-drop homepage builder behind one installation script on hardware you control. Create categories and threaded discussions that search engines index, then switch to Socket.IO-powered chat rooms where replies, pins, link previews, and @mentions update instantly. Voice channels connect participants through WebRTC mesh networking, keeping audio between peers without routing through third-party servers; a Rust-based STUN/TURN relay handles restrictive NATs so home-server deployments work without port forwarding. The NodyxCanvas layer adds CRDT-synchronized collaborative drawing with 11 tools, voice-aware cursors, and board-scoped chat, all persisted to PostgreSQL snapshots. Build your community's landing page with a visual editor that places widgets across 11 layout zones, then extend functionality by dropping third-party widget archives into the admin panel or authoring your own with the plain-JavaScript Widget SDK. Private conversations stay end-to-end encrypted with ECDH P-256 key exchange and AES-256-GCM ciphers where the private key never leaves the browser, and the OctoGuard module automates moderation with five matcher types plus configurable actions from muting to banning. For streamers, a native Streamer Hub bridges Twitch chat bidirectionally, provides a drag-and-drop soundboard, generates OBS browser-source overlays, and offers a mobile Stream Deck. Instances discover each other through a gossip protocol, forming a decentralized network without central coordination. 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.

Retrieval-augmented chatbots on your own knowledge base - that is the whole mission of Dialoqbase, an open-source bot-building platform. Feed it content through a broad set of data loaders - web pages and full crawls, sitemaps, PDFs, DOCX, CSV, plain text, GitHub repositories, YouTube videos, and MP3/MP4 audio - and it handles the whole RAG pipeline in one self-contained app: chunking, embedding, vector storage, and LLM querying. The distinguishing architecture choice is PostgreSQL with pgvector for embedding storage and similarity search, which removes the separate vector-database dependency, and Redis-backed Bull queues for ingesting large documents without blocking the API. Model choice is wide open: OpenAI, Anthropic Claude, Google Gemini, Cohere, Fireworks, Hugging Face, local models via Ollama, and any OpenAI-compatible endpoint, with an equally broad list of embedding providers. Finished bots embed on any website with customizable styling or deploy to Telegram, Discord, and WhatsApp, and an API creates and manages bots programmatically. Multi-user support adds registration limits and per-user bot quotas. MIT-licensed and free for commercial use.

With nearly 5,000 GitHub stars and a Hacker News launch that garnered 147 points, Colanode delivers the first genuinely local-first alternative to both Slack and Notion in a single self-hosted workspace — writing every operation to a client-side SQLite database before syncing to your server, so teams work at full speed offline, on planes, or through intermittent connections without ever losing a draft. The real-time chat system provides channels and direct messages with instant delivery via WebSocket, while the rich text editor offers Notion-style block-based pages for documents, wikis, meeting notes, and knowledge bases with headings, code blocks, embeds, and nested hierarchies. Customizable databases organize structured data with custom fields and three dynamic views — table for spreadsheet-style browsing, kanban for visual workflow boards, and calendar for time-based planning. Conflict-free Replicated Data Types powered by Yjs handle concurrent editing across pages and database records: multiple users modify the same document simultaneously and the system merges changes automatically without manual conflict resolution. File management supports upload, sharing, and organization within workspaces using pluggable storage backends including local filesystem, S3-compatible services, Google Cloud Storage, and Azure Blob Storage with TUS resumable uploads for large files. The server runs Fastify with Zod validation on Node.js 20+, persists to PostgreSQL with pgvector extension, uses Redis for event broadcasting, and deploys via a single Docker image. 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.

OpeniLink Hub turns a personal WeChat account into a programmable bot platform, with a web console, multi-bot management, and a one-click app marketplace that wires WeChat to Lark, Slack, GitHub, Notion, and twenty other services. Bind accounts by scanning a QR code, then watch every bot's status, expiry window, and message flow from one dashboard. Install marketplace apps without writing code: Lark gains 34 AI-callable tools across calendars, docs, tasks, and meetings, while GitHub brings 36 tools for issues, pull requests, and Actions. Every incoming message fans out in parallel over WebSocket for millisecond pushes, Webhook callbacks to your own servers, and an AI channel that answers through any OpenAI-compatible API. Message tracing follows each message from receipt to delivery, showing exactly which hop stalled when something breaks. Passkey sign-in with fingerprint or hardware keys keeps the console protected, with GitHub and LinuxDo OAuth as alternatives. Reminders, expense tracking, currency conversion, RSS digests, and cron-scheduled pushes run as installable apps, and expiry reminders warn you before the 24-hour reply window closes. Build your own integrations with official SDKs for Go, Node.js, Python, PHP, Java, C#, and Lua, or expose local CLI commands as chat-callable tools with the Runner app. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Spam bots flood busy Telegram groups with crypto scams and phishing links faster than human admins can delete them; TG-Spam watches every message and removes the junk before your members see it. Each message is scored by several checks at once: similarity to known spam samples, a stop-word dictionary, emoji and link counts, and a lookup against the Combot Anti-Spam database of known spammers. For borderline cases you can add OpenAI or Gemini as an extra judge, or write your own detection rules as Lua plugins that run inside the bot. The bot learns while you moderate: when admins approve a flagged message or ban a user it missed, the samples update, so the same trick fails next time. Members can report spam with a reply, repeat offenders accumulate warnings toward an automatic ban, and an admin chat gives your team one place to review borderline calls. Turn on the built-in server and the same engine answers spam checks over HTTP for your other tools, with a web UI to test messages, manage samples and dictionaries, and control the approved-user list. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Support teams, IT departments, and researchers can put their own documents behind chatbots and AI agents built with MaxKB, an open-source platform that grounds answers in private knowledge. A support lead starts by uploading Markdown, DOCX, PDF, TXT, HTML, XLSX, XLS, or CSV files, or by syncing a web site, and MaxKB splits, vectorizes, and indexes the content on its own. An IT department can place the finished agent in any third-party site or internal tool with no coding, as a full-screen page, a mobile view, or a floating chat window. Researchers get replies that show, and let them download, the knowledge sources behind each answer. Simple agents pick tools, skills, and MCP connections from the question itself, while advanced agents are drawn as workflows with branching, multi-path recall, loops, and variables. Custom scripts, which AI can help write, plus schedules and event triggers extend what an agent can do. The model manager registers local models such as DeepSeek, Llama, and Qwen beside providers such as OpenAI, Claude, and Gemini, across language, embedding, reranking, vision, speech, and image generation. Conversation logs feed analysis for operations. Dozens of ready-made agent templates, knowledge base templates, tools, and skills in the template center and tool store shorten the first build. 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.

Imp runs large AI chat models privately on one NVIDIA RTX 50 or RTX PRO graphics card, exposing them through OpenAI and Anthropic compatible APIs plus a built-in browser chat. Start it with a single Docker command, point it at a model, and the chat opens in your browser with saved conversations and a live readout of generation speed. Coding agents such as Claude Code and Codex connect by changing one base URL, so your editor talks to the model on your own hardware instead of a rented cloud endpoint. Tool calls, structured JSON output, streaming responses, and reasoning models all work over the wire, and requests can be protected with an API key, per-IP rate limits, and concurrency caps. Load GGUF files you already have or NVFP4 and FP8 SafeTensors checkpoints straight from Hugging Face with no conversion step before the first answer. When a model is bigger than the card, mixture-of-experts weights stay in system RAM while the busiest experts are cached on the GPU, so a 123.6 GiB model still answers from a 32 GB card. Supported models can also read images alongside text, and tokenize, health, and model listing endpoints make the server easy to wire into scripts and monitors. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

TgWitness preserves what your Telegram account actually saw, even when a message is edited three times and deleted before breakfast. A collector watches the chats, folders, or whole account you choose and records every captured message, edit version, and deletion notice in a local journal. The workspace reads like a familiar conversation view, with captured edits and deletion markers alongside the messages, and a searchable journal timeline ties observations together across chats. Open the edit history to compare versions side by side without overwriting the earlier observation. Connect people, replies, and shared links across recorded chats to trace how a claim travelled. Each account gets an isolated workspace with its own session and signing key, so separate investigations never contaminate each other. When a case moves, export the record as readable HTML, structured JSON or CSV, or a signed ZIP bundle whose hash-linked, Ed25519-signed records expose any tampering, verifiable offline with an independent fingerprint. Optional local OCR and transcription make media searchable, signed webhooks announce new observations, and encrypted backups copy the journal and timestamped checkpoints to S3-compatible storage. Read-only MCP access lets approved tools query the archive without touching the collector. Coverage reports show honestly where downtime left gaps. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.