Picture a small staff of AI agents clocking in on your own server, each with a name, a specialty, its own model, and a private Linux desktop it can click around in. Every agent works inside a disposable Docker workstation with a shell, persistent files, and a Chromium browser, so it can research the web, write and run code, and finish multi-step tasks without touching your own files. You watch an agent click and type in real time, and when a login, payment, or one-time code needs a human, you take over the desktop, then hand it back with a note and let it continue. Pair a Telegram bot by scanning a QR code and you can assign work, answer questions, and receive results from your phone, with no public URL or port forwarding. Routines turn recurring requests into schedules, so a morning briefing, a price watch, or a weekly report runs by itself and reports back when it is done. Each agent can use a different model, from OpenAI, Anthropic, Google, xAI, Groq, Mistral, or DeepSeek to a local Ollama endpoint, and every reply shows its cost while a monthly budget pauses paid models automatically. Agents remember what matters about you across every thread, and logins or cards you save sit in an encrypted vault the agents themselves never see. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Accepted as a NeurIPS 2025 Spotlight paper and rapidly approaching 6,000 GitHub stars, AI-Researcher from the Hong Kong University Data Science Lab delivers the first fully autonomous scientific research system — a multi-agent platform that takes a list of reference papers and returns a complete research contribution with working code, validated experiments, and a formatted academic manuscript. The pipeline orchestrates five distinct phases: a Resource Collector systematically gathers materials from arXiv, IEEE Xplore, ACM Digital Library, Google Scholar, GitHub, and Hugging Face; an Idea Generator performs gap analysis against semantic embeddings to produce 3-5 novel hypotheses with feasibility scores; an Algorithm Designer transforms concepts into functional implementations; a Validation Engine automates testing, performance evaluation, and iterative optimization; and a Manuscript Creator generates polished full-length papers with figures, tables, and citations. The Gradio-based web GUI provides intuitive tabs for environment configuration, example selection, and real-time monitoring of research progress, while the production deployment at novix.science offers immediate browser access without local setup. Scientist-Bench provides a standardized benchmark comprising state-of-the-art papers across diverse AI research domains for evaluating autonomous research capabilities. The system supports multiple LLM providers including OpenAI, Anthropic, Google Gemini, and OpenRouter models with per-task routing for cost optimization. Deploy via Python with pip dependencies or Docker containerization. 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.

Prototype multi-agent AI systems without writing orchestration code: AutoGen Studio is Microsoft's low-code interface over the AutoGen AgentChat framework. You compose teams of LLM-powered agents in a visual Team Builder, either by drag-and-drop from a component library or by editing the declarative JSON specification directly. Each agent gets a model, a prompt, tools (Python functions), and the team gets termination conditions and an orchestration pattern, sequential or LLM-driven. The Playground runs teams interactively with live message streaming between agents, a visual control-transition graph, tool-call and code-execution tracking, and pause/stop controls, which makes it a practical debugger for agent behavior. Finished teams export as JSON for use in any Python application via the TeamManager class, or serve as an API endpoint. Any OpenAI-compatible model endpoint works, including local servers like Ollama or vLLM. Microsoft labels it a research prototype: use it for prototyping and evaluation, and build production systems on the underlying AutoGen framework.

AgentDock turns the computers and servers you already run into machines an AI assistant can operate for you through one secure MCP endpoint. Connect ChatGPT, Claude, Codex, or any other MCP client and the agent works in the real environment: reading and writing files, searching code, running shell commands, and driving Git where the project actually lives. Long jobs survive interruptions because task state and checkpoints persist on the node, ready to resume where they stopped. Browser work is covered as well, with web pages driven through a native Chrome DevTools connection that reuses your logged-in sessions, captures screenshots, and can even operate macOS desktop applications. Capabilities grow through installable Skills and dynamic MCP servers, so a node picks up new tools without a rebuild. Run a single node on a laptop, or spread nodes across VPS hosts and containers and pair them with the optional NexusDock console for one fleet view, shared Recall memory, reusable workflow templates, and a single MCP address for every machine. Access stays locked down with Bearer tokens or OAuth sign-in, loopback-only defaults, and optional Cloudflare Tunnel or HTTPS exposure when a remote client needs a way in. 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.

Running AI agents in production takes more than a model call: Omnara supplies the durable runtime, tools, approvals, and complete event history around any model, on your own machines. You define an agent once in a small YAML file: instructions, a model from OpenAI, Anthropic, OpenRouter, Bedrock, LiteLLM, Ollama, or your own endpoint, and the machines it may use. Launch agents from the REST API, the TypeScript SDK, the command line, or the dashboard, then stream every event live or receive it as a webhook while the agent works. Agents run shell commands and edit files on sandboxes from twelve providers, or on your own laptops, VMs, and containers through a daemon that connects outward, so no inbound ports or SSH keys are exposed. Every step is written to Postgres as an event log, which means an agent survives crashes, restarts, and disconnected machines and resumes exactly where it stopped. Tool permissions can run immediately, ask a person first, or block outright, and agents can start subagents, follow cron schedules, and keep shared memory files between conversations. Teams meet the agents where they already talk: mention the bot in Slack or Discord, or let a GitHub pull request trigger a review, with questions and approvals handled in the thread. 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.

Built as a developer-first alternative to SendGrid, Mailgun, and Postmark, Posta delivers a complete self-hosted email infrastructure platform handling both outbound delivery and inbound reception through a single HTTP API with official SDKs for Go, PHP, and Java. The Go backend processes email through Redis and Asynq with automatic retries, priority queues, and async delivery while PostgreSQL stores templates, contacts, campaigns, and delivery analytics. Outbound features include versioned multi-language templates with variable substitution and stylesheet inlining, bulk campaigns with subscriber targeting and A/B testing per-variant metrics, scheduled timezone-aware delivery with draft/paused/cancelled lifecycle states, email address verification checking syntax, MX records, disposable domains, and role accounts, plus web view links with signed expiring URLs and one-click unsubscribe headers. The built-in SMTP receiver with TLS handles inbound email at your domains, parses messages and attachments, scores spam, and forwards structured payloads to your application via HMAC-verified webhooks with real-time SSE notification streams. The Vue-based dashboard manages templates, SMTP server pools, domains, contacts, API keys, campaigns, and email logs with dark and light mode support while admin-level platform metrics expose delivery rate trends, bounce rate graphs, and latency percentiles alongside Prometheus integration and daily health reports. Deploy via Docker with PostgreSQL and Redis. 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.

Replacing HubSpot, Zendesk, Intercom, and Linear with a single self-hosted platform, erxes delivers an Experience Operating System trusted by over 4,000 GitHub stars and built on a modern Nx-powered monorepo architecture. The core ships with six foundational modules — My Inbox for omnichannel conversations across email, web chat, voice, and Discord; Contacts for unified customer profiles; Products for catalog management; Segments for behavioral targeting; Automation for visual workflow builders; and Documents for template generation. Beyond the core, a plugin marketplace activates Frontline for ticket management and omnichannel support queues, Sales for deal pipelines and lead scoring, Operations for project boards with cycle management, Content for headless CMS and knowledge bases, and Team for employee directories, time clocks, and internal chat. The technical stack combines GraphQL Federation with Apollo Server v4 and tRPC v11 microservices on Node.js, React 18 micro-frontends via Rspack Module Federation with TailwindCSS 4, MongoDB with Mongoose for persistence, Redis for caching, BullMQ for job queues, and Elasticsearch for full-text search. Deployment supports Docker Compose orchestration with automatic service discovery across all plugin containers. The Global Profile architecture enables agencies to manage multiple client brands under a single login with separated data stores. iOS and Android SDKs embed the messenger widget directly into mobile applications. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPLv3 licensed.

Automate your entire SSL and TLS lifecycle with Certimate, an infrastructure-grade certificate management platform that handles domain verification, ACME issuance, scheduled renewals, and multi-cloud deployment from one unified control plane. A drag-and-drop workflow designer lets administrators construct visual pipelines linking domain validation, certificate issuance from Let's Encrypt or ZeroSSL, and automated distribution to edge destinations. Built-in automation interfaces connect with over seventy DNS providers to handle automated DNS-01 challenge record creation and cleanup without manual API scripting. Engineers can deploy renewed certificates directly to Nginx, Apache, Traefik, and Caddy instances via automated SSH commands or native webhooks. Cloud delivery workflows push updated certificates to AWS CloudFront, Cloudflare, Alibaba Cloud, Tencent Cloud, and Kubernetes Ingress secrets without service interruption. The web management console tracks expiration dates across multiple domains, highlights failing renewal attempts, and dispatches instant alerts through email, Telegram, DingTalk, and enterprise webhooks before outages occur. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Browse trending titles, search anything, request it in two clicks: Jellyseerr gives Jellyfin, Emby, and Plex users a beautiful storefront for the media library. Born as the Overseerr fork that added Jellyfin and Emby support (the projects have since unified as Seerr), it handles the full request lifecycle - users authenticate with their existing media-server accounts, pick individual seasons or movies in a clean interface, and admins approve or decline from a simple queue, including on mobile. Approved requests flow straight to Sonarr and Radarr, which handle acquisition automatically, with support for separate 4K server instances. Regular library scans keep availability accurate, so users see instantly what already exists instead of requesting duplicates. A granular permission system controls who can request what - auto-approval for trusted users, quotas and limits elsewhere - and override rules adjust request routing by user, tag, or other conditions. Watchlist and blocklist functions curate discovery, notifications reach email, Discord, Telegram, Slack, Pushover, and Pushbullet, and both PostgreSQL and SQLite are supported. Localized into many languages, it turns "can you add this movie?" texts into a self-service system that runs itself.

Edict is a multi-agent orchestrator that runs every AI request through a court-style chain: a crown prince agent triages it, a planning department drafts the work, a review department can veto the plan, and specialist ministries execute what survives. Casual chat gets a direct reply, while real commands become kanban tickets whose titles are scrubbed of file paths and metadata. A vetoed plan returns for rework; an approved one is dispatched in parallel to ministries for finance, documentation, engineering, compliance, infrastructure, and HR. Commands arrive through Feishu, Telegram, or Signal channels configured in OpenClaw. The dashboard shows cards by state with heartbeat badges and stop, cancel, and resume controls, plus a department monitor and a memorial archive that turns finished work into five-phase timelines you can copy as Markdown. Nine edict templates add parameter forms and cost estimates, an officials panel ranks agents by merit score while tracking token spend, and per-agent model switching restarts the gateway in about five seconds. Agent thinking, tool calls, and results stream live. A permission matrix limits who may message whom, illegal state jumps are rejected, and every transition lands in an audit log. Worked examples cover competitive analysis, code review, and weekly reports. Dashboard login protects the console, and a systemd unit keeps it running across reboots. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

An 8MB Go binary that boots in under one second, uses less than 10MB of RAM, yet delivers full AI agent capabilities across 16+ chat platforms simultaneously. PicoClaw connects to Telegram, Discord, Matrix, IRC, Slack, WeCom, DingTalk, WeChat, LINE, and QQ while supporting LLM providers spanning OpenAI, Anthropic, Gemini, DeepSeek, AWS Bedrock, Azure, and local models via Ollama. Native Model Context Protocol support enables standardized tool integration, and the built-in smart routing engine directs simple queries to lightweight models to reduce API costs while sending complex tasks to capable models. Tool capabilities include secure shell execution, filesystem access, web search, cron scheduling for recurring tasks, and sub-agent spawning with status tracking. Gateway mode transforms PicoClaw into a full AI backend with REST API endpoints accessible from any client. The Skills system loads hierarchical behavior definitions from SKILL.md files, enabling customizable agent personalities and workflows. Compiles for x86_64, ARM64, ARMv7, RISC-V, MIPS, and LoongArch, making it deployable on hardware as cheap as a $10 Sipeed LicheeRV Nano. Achieved nearly 30,000 stars within six months of its February 2026 release. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

A fair-source chatbot and conversational-form builder: Typebot assembles conversations in a visual graph editor. In a visual graph editor you chain blocks from four categories: bubbles display text, images, video, audio, and embeds; inputs collect data through text fields, email, phone, buttons, picture choices, date pickers, file uploads, and Stripe payments; logic blocks handle conditional branching, variables, URL redirects, A/B testing, and custom JavaScript; integration blocks call webhooks, OpenAI, Google Sheets, Google Analytics, Meta Pixel, Zapier, Make, and Chatwoot. Build once, deploy anywhere: custom domains, WhatsApp, or embedded in any site as a container, popup, or chat bubble through a fast native JS library with no iframe and no external dependencies - plus an HTTP API for executing bots programmatically from any language. Theming covers fonts, colors, roundness, and shadows with custom CSS and reusable templates, and results arrive in real time with drop-off and completion analytics plus CSV export. Two Next.js apps (builder and viewer) self-host via Docker under the Functional Source License, which converts to Apache 2.0 after two years.

Automate transactional and marketing messages across email, SMS, mobile push, WhatsApp, Slack, and custom webhooks from a single visual journey canvas. Dittofeed provides the capabilities of Customer.io or Braze while keeping customer PII within your own infrastructure and eliminating volume-based pricing entirely. The drag-and-drop journey builder creates multi-trigger automations with branching logic, wait nodes, random cohort splits for A/B testing, and local timezone delivery without writing code. User segments combine trait conditions, event history, and array-based filtering through AND/OR operators with real-time evaluation. Template authoring supports both a low-code visual editor and direct HTML/MJML input, with templates reusable across journeys and one-off broadcasts. Data flows in through Segment integration, Reverse ETL connections, or the REST API with Web, Node.js, and React Native SDKs. Message delivery routes through SendGrid, Amazon SES, Twilio, or SignalWire with per-channel analytics tracking opens, clicks, bounces, and unsubscribes. Authentication supports Keycloak, AWS Cognito, and GCP OAuth for enterprise SSO. Embeddable iframe and headless React components let SaaS platforms white-label journey builders into their own products. Deploy on RepoCloud with a dedicated VPS for full GDPR compliance under the MIT license.

Enterprises requiring production-grade governance for long-running autonomous AI operations can rely on OpenGeni, a self-hosted orchestration platform with human-in-the-loop approvals, Connected Machine execution, and comprehensive audit replays. Operators can configure durable multi-turn workflows that execute continuously toward specified goals without premature termination, automatically pausing when human verification, structured multiple-choice decisions, or critical credential approvals are required. Teams can assign execution workloads across ephemeral cloud sandboxes or route them straight to enrolled Connected Machines to run commands directly against local code repositories without exposing inbound network ports. The integrated web console lets developers inspect live Server-Sent Event activity streams, replay complete turn histories from audit logs, inspect generated artifacts, and cancel or steer in-flight agent tasks on demand. Platform administrators can enforce fine-grained access policies through GitHub App repository bindings, broker temporary role-scoped secrets, and maintain a shared organizational knowledge base where agents propose findings for human review before vector indexing. 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.

Designed as a unified personal AI workstation, QwenPaw operates as an autonomous digital copilot that coordinates scheduled automations, interactive coding sessions, and multi-channel team communication across everyday messaging apps. Users can dispatch long-running research tasks, process office documents including PDF, Excel, and Word files, and execute browser-based data collection without manual intervention. The built-in web console and terminal interface provide full visibility into agent reasoning, allowing operators to inspect intermediate thinking steps, review proposed file edits, and approve sensitive tool calls. Through direct connectors for Discord, Telegram, DingTalk, Lark, and WeChat, teams can trigger specialized skills or query shared workspaces directly from their existing group channels. A self-evolving personal memory system continuously indexes chat interactions and local resources into editable Markdown files, ensuring knowledge persists across restarts and task delegations. Built-in guardrails including a sandboxed execution runtime, tool access policies, and automated skill scanners protect underlying host files from unauthorized modifications during autonomous scripting runs. 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.

Configure each indexer once, not five times: Prowlarr is the indexer hub of the *arr stack, removing the most tedious duplication in a media automation setup. Instead of configuring the same torrent trackers and Usenet indexers separately in Sonarr, Radarr, Lidarr, Readarr, and Mylar3, you add each one once in Prowlarr and it syncs them to every connected app automatically, complete with category mappings; with Full Sync enabled, adding or removing an indexer propagates everywhere, and a tracker URL change is a one-place fix. Coverage is the deepest available: 500+ torrent trackers with definitions added constantly, 24 native Usenet indexers, generic Newznab and Torznab support for anything else, and custom Cardigann YML definitions with JSON and XML parsing for obscure sources. Built on the same .NET/React base as its siblings, it also earns a place as a search tool in its own right: unified manual search queries every indexer simultaneously at a category level, and you can push multiple releases straight to your download clients without touching Sonarr or Radarr. Health checks and status notifications flag failing indexers, per-indexer statistics track success rates and response times so you can cull unreliable sources, and per-indexer proxy support (SOCKS4/5, HTTP, FlareSolverr) handles trackers behind Cloudflare.

PilotDeck introduces a WorkSpace-first architecture where each project receives its own isolated file system, memory store, and skill set, preventing context bleed between parallel tasks. White-box memory makes generation, extraction, storage, and retrieval fully visible, letting users audit, edit, pin, and rollback individual entries when the agent misremembers, while Dream Mode consolidates memory fragments during idle windows. Smart Routing auto-detects task difficulty and sends complex calls to flagship models like Claude Sonnet or GPT-4o while routing simple requests to lighter models, achieving claimed 70% cost savings through on-device and cloud co-orchestration with TokenSaver tiering and sticky session binding. Always-on background execution keeps agents running after the user closes the browser, with Discovery and Cron-based scheduling for recurring workflows. The platform natively supports the Model Context Protocol for first-class MCP server integration, community skills via ClawHub on npm, lifecycle hooks intercepting PreToolUse and UserPromptSubmit events, and custom memory store providers. Multi-provider fallback automatically switches to backup providers on timeout or rate-limit errors. The WebSocket and HTTP gateway serves web, CLI, desktop, and Feishu IM channels from a single configuration. 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.

II-Agent is an autonomous AI agent platform that ranked first on the GAIA benchmark by combining multi-step task planning with a full-stack execution environment spanning research, coding, browsing, and content creation. The platform runs a React frontend on port 1420 backed by FastAPI on port 8000, with PostgreSQL for persistence, Redis for task queuing, and MinIO for S3-compatible file storage, all deployable via Docker Compose. Users switch between Anthropic Claude, OpenAI GPT, and Google Gemini mid-conversation using bring-your-own-key authentication. Task domains include deep research with source triangulation, website and mobile app generation from prompts, storybook creation with illustrations, video and image generation via Google Veo and Imagen, presentation building with live collaborative editing, and document manipulation covering PDF extraction, Excel formulas, Word editing, and PowerPoint creation. Built-in connectors integrate Gmail, Slack, GitHub, Notion, Google Calendar, Discord, Dropbox, and Canva for workflow automation. A sandboxed code interpreter runs Python while browser automation with vision capabilities handles web interactions. Custom skills let teams package and reuse workflows. Context management handles up to 120,000 tokens with intelligent window sizing. 3,400+ GitHub stars. Apache-2.0 licensed.