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.

Huginn has established itself as the definitive open-source automation engine for developers who refuse to hand their workflow data to third-party cloud services. The platform lets you build agents that scrape websites, monitor RSS feeds, track weather via APIs, watch Twitter streams, aggregate news, detect price changes, and trigger notifications through email, SMS via Twilio, Slack webhooks, or social media posts to Twitter and Tumblr. Each agent creates and consumes JSON events, propagating them along a directed graph where complex multi-step workflows emerge from simple single-purpose components. The web interface provides visual agent management with drag-and-drop scenario building, real-time event logs, scheduling controls, and a built-in agent library covering dozens of use cases out of the box. Huginn supports Liquid templating for dynamic event transformation, regex-based content extraction, JavaScript-based data manipulation, and HumanTaskAgent for crowd-sourced workflow steps. Custom agents can be packaged as Ruby gems and loaded via the ADDITIONAL_GEMS environment variable without modifying core code. Deployment options include Docker with the official huginn/huginn all-in-one image or huginn/huginn-single-process for production multi-container setups with PostgreSQL or MySQL backends, plus native support for Heroku and OpenShift PaaS platforms. 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 series once, set a quality profile, and everything downstream is automated: Sonarr is the smart PVR for Usenet and BitTorrent users. It monitors RSS feeds from your indexers, detects new episodes the moment they release, sends matching grabs to SABnzbd, NZBGet, qBittorrent, Deluge, or another download client, then renames files with fully configurable templates, sorts them into consistent folder structures, and notifies Plex, Kodi, or Jellyfin to update the library. Quality profiles define what's acceptable (HDTV, WEB-DL, Blu-ray, up to 4K) and an upgrade cutoff - when a better release appears, Sonarr replaces the existing file automatically, stepping from HDTV to WEB-DL to Blu-ray until the cutoff is met. Custom formats add weighted scoring for finer-grained release selection, with community-maintained TRaSH Guides presets as the widely accepted defaults. Failed downloads are handled without intervention: Sonarr retries with another release, and manual search shows every candidate with the reasons any was rejected. It scans existing libraries for missing episodes, fully supports specials, multi-episode files, and daily and anime series types, and a calendar view shows upcoming episodes across every tracked show. Runs on Linux, Windows, macOS, and Raspberry Pi, and pairs naturally with Prowlarr for centralized indexer management.

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.

Sim Studio lets teams build, deploy, and monitor AI agent workflows by dragging blocks onto a visual canvas and wiring them into executable pipelines, backed by over 1,000 integrations. The React Flow editor represents each step as a node: LLM calls, tool invocations, conditional branches, and data transformations form directed acyclic graphs that run as complete agent pipelines. Every major LLM provider works natively, including OpenAI, Anthropic, Google Gemini, Groq, and Cerebras, plus local models through Ollama and vLLM. Integrations span Gmail, Slack, Microsoft Teams, Telegram, WhatsApp, Notion, Google Workspace, Airtable, GitHub, Jira, Linear, Perplexity, Firecrawl, PostgreSQL, Supabase, Pinecone, and Qdrant. Built-in tables provide a database layer, a file store offers shared team storage, and knowledge bases powered by PostgreSQL with pgvector enable retrieval-augmented generation. Finished workflows deploy as REST API endpoints, scheduled jobs, or Slack bots, with block-by-block execution traces for full observability. Real-time collaborative editing via Socket.io supports simultaneous multi-user construction. Alternatively, describe agent behavior in natural language and Sim assembles the workflow automatically. Built on Next.js App Router, Bun runtime, Drizzle ORM, and Tailwind CSS. 29,400+ GitHub stars and 100,000+ builders. Apache-2.0 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.

Originally built at Netflix to orchestrate microservices powering 230 million subscribers and now trusted in production at Tesla, LinkedIn, and J.P. Morgan, Conductor is the most battle-tested open-source workflow engine available — with 32,000 GitHub stars and horizontal scalability to billions of executions. The architecture cleanly separates orchestration from business logic: workflows are defined in declarative JSON while workers execute tasks in any of seven supported languages (Java, Python, Go, JavaScript, C#, Ruby, Rust) with zero framework constraints. Durable execution persists every state transition, enabling automatic retries, configurable timeouts, crash recovery, and instant replay from any failure point without re-executing completed tasks. Native AI agent orchestration supports 14+ LLM providers (Anthropic, OpenAI, Google Gemini, AWS Bedrock, Mistral, Cohere, HuggingFace, Ollama), MCP tool calling, function calling, human-in-the-loop approval gates, and vector database integration (Pinecone, pgvector, MongoDB Atlas) for RAG pipelines. Deploy with your choice of five persistence backends (PostgreSQL, Redis, MySQL, Cassandra, SQLite), six message brokers, and Elasticsearch or OpenSearch for workflow indexing — all configurable via Docker Compose files included in the repository. The built-in web UI provides workflow visualization, execution monitoring, task queue inspection, and manual intervention controls. 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.

Reaching #1 on GitHub Trending with over 48,000 stars, OpenMontage is the first open-source agentic video production system — transforming AI coding assistants like Claude Code, Cursor, Copilot, Windsurf, and Codex into complete video studios that handle research, scripting, scene planning, asset generation, editing, and final rendering through natural language prompts. Twelve production pipelines cover animated explainers, cinematic trailers, documentary montages, talking heads, screen demos, podcast repurposing, character animation, localization and dubbing, avatar spokesperson videos, hybrid productions, clip factory batch processing, and animation workflows. Over 100 registered Python tools connect to 60+ providers including Kling, Runway Gen-4, Google Veo 3.1, FLUX, Google Imagen 4, ElevenLabs, and Suno AI for cloud generation, plus Piper TTS, WAN 2.1, Hunyuan, and CogVideo for fully local GPU rendering — while free footage from Archive.org, NASA, Wikimedia Commons, Pexels, and Unsplash powers the documentary montage pipeline's CLIP-indexed retrieval system for real-motion video without paid generation APIs. Two composition engines — Remotion for React-based programmatic video and HyperFrames for HTML/GSAP motion graphics — render final output with spring animations, word-level captions, kinetic typography, and SVG character rigs. A seven-dimension scored provider selector, pre-compose validation gates, post-render ffprobe self-review, slideshow risk scoring, configurable budget caps with per-action approval thresholds, and the Backlot live web dashboard for visual production monitoring enforce production-grade quality at every stage. 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.

Document-generation code is the worst kind of code in your backlog - Carbone kills it. Its insight is separating design from data - templates are ordinary office documents (DOCX, ODT, XLSX, PPTX, HTML, even custom XML) built in LibreOffice, Microsoft Office, or Google Docs, with mustache-like markers such as {d.companyName} typed directly into the text. Send a template plus JSON from your existing APIs to the HTTP API, and Carbone returns the finished document - exported as-is or converted to PDF, XLSX, CSV, HTML, PNG, EPUB, and more via its integrated LibreOffice converter (Chromium and OnlyOffice engines are also supported for HTML-fidelity and office-format conversions). The template language goes well beyond substitution: loops over arrays render dynamic table rows, filters and aggregations run inside the document, and built-in formatters handle dates, numbers, currencies, timezones, and locales, with custom JavaScript formatters when needed. One template serves multiple languages through translation markers with auto-maintained translation files. The XML-agnostic engine means anything your document editor can design - pagination, headers, footers, nested tables, charts - survives generation intact, and Carbone guarantees no breaking changes in template syntax. Node.js-based, fast via multi-threaded LibreOffice conversion. The invoices, contracts, and reports your product owes its users become template edits, not sprints.

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.

Salesforce's platform model, 100% open-source (Apache 2.0): Corteza is a Go/Vue.js low-code platform developed under a foundation, so there is no open-core bait to grow out of. The heart is Corteza Compose: namespaces contain applications, modules define record structures the way Salesforce objects do, and a drag-and-drop page builder assembles record pages, list pages, dashboards, and charts from configurable blocks. Automation comes from a visual, BPMN-style workflow engine plus JavaScript automation scripts, so cross-application business logic - approval chains, field updates, notifications - is configured rather than programmed. Granular role-based permissions reach down to individual modules, fields, and records, mirroring real organizational hierarchies. Corteza CRM ships as the flagship application built entirely on Compose: leads, accounts, opportunities, campaigns, and cases with a 360-degree customer view, covering most Salesforce standard objects - and because it is just a Compose app, adding or reshaping modules is configuration, not a fork. Everything is reachable over REST APIs, deliberately familiar tooling eases Salesforce admin migration, and a CLI can even generate synthetic records for load-testing what you build.

Modern engineering teams and busy households deploy Octop to run private, autonomous AI agents equipped with persistent memory workspaces, scheduled cron jobs, and direct browser automation. Users can orchestrate specialist agents tailored for software development, IT operations, content generation, and system diagnostics through an interactive React dashboard. The platform connects directly to Discord, Feishu, DingTalk, and WeCom, allowing team members to delegate complex tasks without leaving their everyday messaging apps. An integrated remote desktop and browser control engine lets agents navigate websites, capture screenshots, fill forms, and operate graphical software autonomously. Administrators can assign distinct MBTI personality profiles to agents, establish granular role-based permissions, configure scheduled cron workflows, and integrate custom Model Context Protocol servers for external tool access. Long-term memory persists across conversations through dedicated workspace files, ensuring contextual continuity whenever switching between underlying language models or team collaborators. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Open-sourced by the Databricks AI team under Apache 2.0 and reaching over 8,500 GitHub stars within two months of launch, Omnigent introduces the meta-harness concept: a common orchestration layer that sits above existing AI coding agents and makes them interoperable parts of a governed, collaborative system. The platform wraps Claude Code, Codex, Cursor, OpenCode, Hermes, Pi, and any custom agent defined in a simple YAML configuration file into sandboxed sessions with a uniform API, then exposes each session through the terminal, a web UI, a native desktop application, mobile interfaces, and a REST API. Built-in multi-agent workflows include Polly, a coding orchestrator that delegates tasks to parallel sub-agents in separate git worktrees and routes each diff to a reviewer from a different vendor, and Deep Research, which plans sub-queries, searches the live web through MCP servers, reads full pages, and cross-checks claims across independent sources. Contextual security policies go beyond static allow/deny rules by maintaining per-session state to enforce spend caps, model routing, approval gates for destructive actions, PII blocking, and repository-scoped write restrictions across server-wide, per-agent, and per-session levels. The OS sandbox restricts filesystem and network access while intercepting egress requests to inject credentials only on approved calls. Cloud sandbox providers including Modal, Daytona, E2B, CoreWeave, Kubernetes, and Databricks launch disposable execution environments per session. 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.

Baby Buddy is a private self-hosted child care tracker that centralizes feeding sessions, sleep cycles, diaper changes, and developmental health milestones into a collaborative dashboard for parents and caregivers. Caregivers can start quick timers on mobile devices to measure nursing intervals, bottle feedings, naps, and tummy time sessions with single-tap precision. The dashboard automatically calculates daily averages, feeding amounts, and awake windows to help families establish consistent daily sleep and feeding routines. Parents can track diaper changes by recording wetness, stool consistency, and color anomalies to spot digestive health changes early. Physical measurements including weight, height, and head circumference plot directly against World Health Organization growth curves to visualize percentile progression between pediatric visits. Multi-child profiles allow families with twins or multiple young children to switch contexts instantly and monitor individual growth timelines. Granular user permissions let parents invite nannies, babysitters, and relatives with restricted logging permissions while keeping administrative settings private. The built-in REST API and webhook system enable physical smart button clicks and home automation routines to log events instantly without opening a browser. Running 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.

OpenPost is an open-source content creation and publishing suite that unifies multi-platform social scheduling, graphic design, and video editing into a single self-hosted control center. Creators can compose one primary announcement and tailor bespoke copy, media attachments, and thread structures across sixteen distinct networks including Bluesky, Mastodon, X, Threads, LinkedIn, YouTube, and Discord. The integrated browser canvas lets you design multi-slide carousels with custom typography, layer ordering, and automated background removal without juggling external design software. A built-in multitrack video suite allows you to trim footage, render subtitle captions, insert transitions, and slice clips directly by highlighting spoken words in generated transcripts. Social managers can organize campaigns through an interactive visual calendar, stagger deliveries across automated queues, and monitor unified comment streams to answer incoming audience inquiries directly from a single inbox. Teams can organize multiple independent client brands into partitioned workspaces with role-based permissions, automated repost policies, and programmable scheduling webhooks via native REST and Model Context Protocol endpoints. 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.

TencentDB Agent Memory provides a team-level memory hub that transforms AI agent conversations, documents, and codebases into four governed, shareable memory assets: Chat Memory for conversation history, Skills extracted from completed tasks, LLM-Wiki built from document ingestion, and Code-Graph generated from codebase analysis. The four-tier semantic pyramid structures long-term memory from L0 raw conversation capture through L1 episodic extraction and L2 scenario aggregation to L3 persona synthesis, enabling hierarchical drill-down via node and result references instead of flat vector recall. The Node.js Gateway sidecar handles capture, extraction, storage, recall, and pipeline scheduling through RESTful HTTP v2 endpoints on port 8420, while the Memory Proxy intercepts Anthropic-format API calls to inject team memory context into Claude Code, CodeBuddy, and other coding agents transparently. Local SQLite with the sqlite-vec extension provides the default storage backend with hybrid BM25 keyword plus vector embedding plus reciprocal rank fusion retrieval requiring zero external API dependencies. Teams manage ownership, versions, status, visibility, usage counts, and agent bindings through the Memory Hub dashboard with role-based access control separating System Admin and team-level Admin and Member permissions. Official TypeScript and Python SDKs provide programmatic access for custom framework integration beyond the built-in OpenClaw plugin and Hermes Agent adapter. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT 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!