OpenGTM turns a market, a list, or a workbook into enriched, researched, ready-to-contact prospects on servers you control. Give it a market and it sources companies and people; hand it a CSV or a Clay table and it maps the columns into a shared record library. Enrichment columns run as waterfalls that try providers in cost order until a field is filled, and before anything spends a cent you see best and worst case estimates, with a workbook budget ceiling that halts paid calls on its own. Research columns send an agent to answer the hard question for each row, and the answer keeps citations to the pages it actually fetched, so a human can audit the claim before outreach. Live audiences segment your records and watch for hiring and buying signals, refreshing on schedules and firing automations when a prospect heats up. Finished rows flow out to HubSpot, Salesforce, Slack, Sheets, Airtable, Instantly, Smartlead, webhooks, or a warehouse, while every cell keeps a trace of provider attempts, latency, and cost. Your own agents get the same workspace through a REST API, webhooks, and an MCP server with scoped read and write tokens, and a seeded zero-key demo means the team can explore the whole loop before adding a single provider key under Settings. 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.

Subtitles are the one chore Sonarr and Radarr leave behind - Bazarr finishes the *arr media stack by automating them. It connects to both via their APIs and mirrors their libraries - it doesn't scan disk itself, it manages exactly what your *arr apps index. For every monitored episode and movie it checks existing internal and external subtitles against your language profiles, then hunts missing ones across dozens of providers - OpenSubtitles.com, Podnapisi, Addic7ed, Subscene, and many regional sources - covering 184 subtitle languages including forced/foreign-dialogue tracks. Matching is smarter than filename guessing: releases are compared by release group and source, some providers support exact file-hash matching, and every downloaded subtitle gets a percentage score. Set a minimum score per Sonarr/Radarr connection and Bazarr rejects weak matches; enable upgrades and it replaces previously downloaded subtitles when better ones surface. Out-of-sync files get fixed too - automatic subtitle synchronization realigns timing after download, triggered only below a configurable score threshold so good subs aren't touched. Per-show and per-movie language configuration, download history, manual on-demand search, and adaptive searching that throttles provider API calls round it out, all behind a clean Sonarr-style web UI written in Python. If your library serves multilingual viewers, this removes the last manual step.

From the first rack to the last circuit, Nautobot is the open-source network source of truth that records what your network should look like and runs automation against it. Built-in models cover locations, racks, devices, interfaces, cables, VLANs, VRFs, IP prefixes, circuits, and contacts, so one searchable record replaces the spreadsheet and the wiki. Teams encode their own standards with custom fields, user-defined relationships, computed fields, and validation rules. Config contexts attach JSON or YAML data, such as syslog servers, to devices by location, role, platform, or tag. Jobs run your own automation code from the web UI, REST API, or command line, on a schedule, or through hooks when an object changes, with approvals and logs built in. Query the data over REST or GraphQL, and let the GraphiQL editor autocomplete a device and interface query you can save inside Nautobot. When an object is created, updated, or deleted, webhooks notify outside systems, with Jinja2-templated bodies and HMAC SHA-512 signatures. Git repositories can carry export templates, Jobs, and config contexts too, so YAML data and Jinja2 templates get pull request review before Nautobot syncs them. Open-source Apps add Golden Configuration for config backup, compliance, and remediation, Device Lifecycle for hardware tracking, SSoT for syncing other systems, and ChatOps. Object permissions and change logging keep a shared instance auditable. 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.

With over 2,700 GitHub stars, Auto Company is the first open-source framework that runs a fully autonomous AI company 24/7 — 14 specialized agents modeled after Jeff Bezos (CEO strategy), Werner Vogels (CTO architecture), Charlie Munger (critical analysis), DHH (full-stack engineering), Kelsey Hightower (DevOps), Seth Godin (marketing), and eight more domain experts collaborate through dynamic squad formation to ideate products, write code, deploy infrastructure, and execute marketing campaigns without human intervention. The five-layer architecture separates execution, orchestration, cognition, workflow routing, and observability, while the consensus memory pattern uses a single markdown file as a relay baton between cycles — no vector databases, no Redis, no embeddings required. A bash loop invokes Claude Code or OpenAI Codex CLI every 30 seconds, each cycle selecting 2-5 agents from the 14-person pool based on task context. Over 30 reusable skills handle specialized tasks from frontend design to competitive analysis and deployment automation. Circuit breakers trigger cooldown after consecutive errors, rate-limit detection auto-sleeps on API throttling, and sandbox rollback protects against destructive changes. The Python-powered web dashboard displays real-time cycle status, cost tracking per cycle averaging under $2, and agent activity visualization, with CLI control via make start, stop, monitor, pause, and resume. Supports macOS via launchd, Windows via WSL with systemd, and native Linux deployment. The npx create-auto-co command scaffolds a new AI company in seconds. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OpenGrokBot gives you always-on AI teammates that live on your own hardware, each with a computer of its own. Every teammate is a folder with a persona and hard boundaries, a thread in your sidebar, and a contained machine with its own browser profile, workspace, and persistent memory that survives between asks. You manage the crew from a workbench-style web client: message one teammate or the whole group, watch its browser screen live, set routines like a morning digest, and check what each one used today. The safety model is the point: credentials live inside the teammate's own browser profile, so at a login wall it asks you to take over its screen instead of asking for a password; standing instructions change only through a diff you approve; and a teammate cannot approve its own holds. Teammates hand work to each other under an allowlist with a hop limit, optional daily token ceilings stop spending for the rest of the day, and a stop button kills even a shell command mid-flight. Computers can be a Docker container per teammate, or Docker-free local browsers with sandboxed commands. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

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.

Every account you run deserves its own browser identity, and FoxProfile keeps those identities permanently separate instead of letting them bleed into one another. Create a profile once and it remembers its device: screen, GPU, CPU cores, fonts, and canvas noise are generated on first launch and reused on every later one, so the fingerprint a site saw yesterday is the fingerprint it sees tomorrow. Sessions stick too: history, cookies, and logins live in the profile directory, and the tabs you left open reopen where you left them. Each profile carries its own proxy (HTTP, HTTPS, SOCKS4, or SOCKS5, with a built-in checker) while timezone and locale follow the exit IP automatically or stay pinned to your choice, and the Check IP button compares the exit address across three services and flags mismatches or datacenter addresses. Cookies move in and out as standard editor JSON or Netscape files, whole profiles travel as ZIP archives, and bulk actions launch, stop, or delete fleets at once. On a server, the web panel runs profiles headlessly so you can manage them and view their screens from anywhere, the REST API scripts everything, and the MCP server lets AI agents drive the browsers directly. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Every Terraform change becomes a pull request with Atlantis, which runs the plan on your server, posts the output for review, and applies only the exact change reviewers approved. Open a pull request that touches Terraform code and Atlantis automatically runs terraform plan, posting the full output as a comment and a commit status your reviewers can inspect line by line. When the change looks right, a teammate comments atlantis apply and Atlantis executes the exact plan that was reviewed, then reports the result back on the same pull request. Each directory and workspace is locked while a pull request is open, preventing two changes from applying out of order, and locks can be inspected or discarded from the web interface. Apply requirements let you demand an approved review or a mergeable branch before anything runs, and optional policy checks evaluate plans against your rules before they can proceed. Repositories describe their projects, workspaces, and custom workflows in an atlantis.yaml file, including pinned Terraform versions, execution order groups, and parallel planning or applying across projects. Because Atlantis runs inside your infrastructure, cloud credentials never leave your network, and every plan, approval, and apply is preserved on the pull request as an audit trail. 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.

Generic AI writing sounds like nobody in particular; BullFlow writes from your own company knowledge instead. It first builds a private knowledge base from your documents, images, audio, and video plus structured records for your company, brand, products, customers, and cases. Ingestion runs entirely on local open models: OCR reads scans, semantic splitting and chunking prepare text, and hybrid vector plus full-text search retrieves passages with their sources and relevance scores shown under every answer. A creation agent then works in one conversation: it searches the knowledge base, drafts articles with images embedded in the text, generates image sets or short videos, and exports finished pieces as PDF or Word. Output adapts to where it is going, long-form articles for article platforms, multi-image posts with matching copy for image feeds. A separate distribution gateway sends one finished piece to many accounts across Chinese and international social platforms, checks account health on a schedule, and returns publish results and metrics by webhook. Around all of that sits a commercial shell: multiple tenants with isolated data, roles from super admin to finance, credit billing measured per token, image, and second, subscriptions, invoices, referral commissions, and a conversion funnel in the operations backend. Scheduled rules can generate and publish on a timetable with nobody watching, and notifications report each completion or failure. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Keep is an open-source AIOps and alert management platform built with Python FastAPI and Next.js. It provides a single pane of glass for monitoring alerts from 110+ integrations, alert deduplication, correlation, enrichment, and filtering, YAML-based workflow automation similar to GitHub Actions, AI-powered correlation and summarization, and customizable dashboards for incident management. With 12,100+ GitHub stars, Y Combinator backing, and an Elastic partnership, Keep is the open-source AIOps platform that centralizes alert management across your entire monitoring stack into a single customizable dashboard. Alert deduplication identifies duplicate notifications across providers, correlation groups related alerts into incidents based on rules or AI-powered semantic analysis using pluggable LLM backends supporting OpenAI, Anthropic, and local models via Ollama, and enrichment adds context from external sources like CMDBs and databases. Workflow automation follows a GitHub Actions paradigm with declarative YAML files defining triggers, conditions, and actions that can query MySQL, update Jira tickets, send Slack messages, execute Python scripts, or call REST APIs. Authentication supports no-auth, database, Auth0, Keycloak, OAuth2 Proxy, Okta, and OneLogin. The Common Expression Language enables advanced alert querying, slicing, and rule-based grouping to reduce noise. On RepoCloud, deploy Keep on a dedicated VPS with Docker Compose, root SSH access, and complete control over your alert infrastructure, all under the MIT license.

Claiming 60-80% token cost reduction compared to flat single-model deployments and backed by 6,500+ GitHub stars, OpenSquilla delivers an intelligent AI agent runtime where a local ML classifier evaluates every turn on message length, code blocks, keyword patterns, and semantic embeddings before routing it to the optimal model tier from C0 through C3. The pluggable provider layer connects natively to TokenRhythm, OpenRouter, OpenAI, Anthropic, Ollama, DeepSeek, Gemini, DashScope, Moonshot, Mistral, Groq, Zhipu, SiliconFlow, vLLM, LM Studio, and additional compatible backends with primary-plus-fallback selection. The four-tier cognitive memory architecture spans working, episodic, semantic, and raw layers with vector-semantic and BM25 retrieval powered by on-device ONNX embeddings that never leave your infrastructure. Security isolation operates at the syscall level via Bubblewrap on Linux and Seatbelt on macOS, complemented by policy-based execution controls and prompt injection protections. The unified TurnRunner executes identically across the Vue-based control console Web UI, terminal CLI, and chat channel integrations including Slack and Discord, ensuring consistent tool dispatch, retry logic, and decision logging regardless of entry point. Built-in skills cover deep research, multi-search-engine queries, document generation for DOCX, PPTX, XLSX, and PDF formats, GitHub integration, cron scheduling, and bounded subagent delegation. Per-agent workspaces with durable session storage provide transcript replay, context state management, and per-call cost tracking with automatic quota enforcement. 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.

FastGPT lets you build production AI agents and knowledge base chatbots through a visual drag-and-drop workflow editor, connecting any LLM provider to your documents with retrieval-augmented generation that cites sources and reduces hallucination. The workflow canvas chains LLM calls, conditional branching, HTTP requests, code sandbox execution, and plugin nodes into complex conversation flows and agent skill pipelines without writing backend code. The knowledge base engine ingests documents in ten formats (TXT, Markdown, HTML, PDF, DOCX, PPTX, CSV, XLSX, URL scraping, and CSV batch import) then applies automatic chunking, hybrid vector retrieval with semantic reranking, and QA-pair splitting to deliver accurate, citation-backed answers. FastGPT connects to virtually any LLM provider through its AI Proxy aggregation layer: OpenAI GPT-4o, Anthropic Claude, Google Gemini, DeepSeek, Qwen, ERNIE Bot, and models hosted via Ollama all work through a unified OpenAI-compatible API. Bidirectional MCP support enables agents to call external tools and expose their own capabilities to other systems. Completed applications can be shared via login-free links, embedded as iframe widgets, or integrated with WeCom, Lark, DingTalk, and WeChat Official Accounts through the published REST API. Application operation logs, conversation annotation, and per-model usage analytics provide full lifecycle governance for compliance-sensitive deployments. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. FastGPT Open Source License (Apache 2.0 based) licensed.

With over 46,000 GitHub stars, nanobot is the ultra-lightweight personal AI agent framework that delivers full agentic capabilities — tools, persistent memory, multi-agent workflows, scheduled automation, and 10+ chat channel integrations — in approximately 4,000 lines of readable Python core code. The agent loop receives messages from any connected channel, builds context from session history and long-term memory files, calls the configured LLM provider, executes requested tools, and publishes replies back to the originating channel. Supported LLM providers include OpenAI, Anthropic, Google Gemini, DeepSeek, Qwen via DashScope, Moonshot/Kimi, Ollama, vLLM for local models, and any OpenAI-compatible API through OpenRouter or LiteLLM. Chat channels connect the agent to Telegram, Discord, Slack, WhatsApp, Feishu/Lark, DingTalk, Email via IMAP/SMTP, QQ, Matrix with end-to-end encryption, Mattermost, and the built-in browser WebUI served from the published Python wheel with no separate frontend build. Built-in tools include filesystem read/write/edit, shell execution with configurable sandboxing via bubblewrap, web search and fetch with SSRF protection, MCP server integration, cron scheduling, image generation, and subagent spawning for parallel task delegation. The Dream memory system consolidates session history into persistent markdown files for long-term context retention across conversations. Deployment runs as a CLI agent, a persistent gateway server, a Docker container with Docker Compose, or an OpenAI-compatible API server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Radarr, Sonarr, and their sibling apps watch RSS feeds for new releases but never go back for what your library is still missing, and Houndarr fills that gap by asking them to search in small, polite batches. It reads the wanted lists of every connected Radarr, Sonarr, Lidarr, Readarr, and Whisparr instance and sends a few search commands per cycle, so a big backlog drains over days instead of arriving as one Search All Missing burst. Each instance has its own batch size, sleep interval, hourly cap, per-item cooldown, and post-release grace period, plus an optional download-queue limit, allowed search windows such as 09:00-23:00, and tag filters that include or exclude items. Three independent passes run per instance: missing items, cutoff-unmet items below your quality profile, and upgrades for files that already meet cutoff, with the last two off until you enable them. Sonarr, Lidarr, and Readarr can search by season, artist, or author, and search order is random or oldest-first. The dashboard shows library health, recent hunts, hourly budgets, and a cooldown schedule per instance, with Run Now buttons for on-demand cycles. The Logs page records every search and skip with its reason in a filterable audit trail that copies as TSV. A key-gated widget endpoint feeds Homepage dashboards, and built-in login or reverse-proxy authentication protects the interface. 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.

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.

Aegra runs your LangGraph agents on your own infrastructure with the same SDK and APIs you would use on the managed platform, so moving in does not mean rewriting your agents. You deploy an agent once and clients connect through Agent Chat UI, LangGraph Studio, or CopilotKit, while threads, runs, and checkpoints persist between sessions instead of vanishing when a process restarts. Streaming answers arrive token by token over server-sent events, and if a connection drops, the stream reconnects and replays missed events rather than losing the run. Human-in-the-loop gates pause an agent at the step you choose, wait for a person to approve or edit, and then resume from exactly that state. Scheduled cron jobs trigger runs on standard or seconds-level expressions with timezone support, which turns agents into recurring workers for reports, checks, and follow-ups. When traffic grows, Redis-backed workers process runs with lease-based crash recovery, so a dead worker's job is picked up instead of disappearing. Authentication handlers plug in JWT, OAuth, or Firebase, custom endpoints sit beside the agent API, and traces fan out to the observability backend you already run. 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.

With over 7,400 GitHub stars and benchmarked at 0.89 seconds average session lifecycle — 1.7x to 9x faster than competing browser automation platforms — Steel Browser delivers production-grade headless Chrome infrastructure purpose-built for AI agents that need to interact with the modern web. The TypeScript-based server exposes a REST API providing on-demand browser sessions with full CDP (Chrome DevTools Protocol) access, allowing connections from Puppeteer, Playwright, or Selenium through standard WebSocket endpoints without framework lock-in. Each session maintains persistent state including cookies, localStorage, IndexedDB, and authentication credentials across requests, enabling stateful multi-step agent workflows that survive session restarts. Built-in anti-detection includes stealth plugins, browser fingerprint randomization, and configurable user-agent rotation, while the proxy chain manager handles IP rotation through residential, datacenter, or custom proxy pools. CAPTCHA solving integrates natively so agents encounter fewer blocking interrupts during autonomous navigation. The Session Viewer provides real-time WebRTC-streamed visual debugging of live sessions and playback of recorded sessions with full network request logging. Browser Tools APIs convert any page to clean Markdown, readability-optimized text, PDF documents, or high-resolution screenshots with a single API call. The MCP Server integration exposes Steel sessions as tools accessible to Claude, Cursor, and other Model Context Protocol-compatible AI agents. Deploy via Docker with a single container or use Docker Compose for production configurations with automatic resource cleanup and session lifecycle management. 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.

GoCD treats delivery as a pipeline you can see: every commit enters a sequence of stages, passes or fails in the open, and travels from first build to production deployment along one visible, traceable path. Stages split work into jobs that run in parallel on a fleet of agents, so unit tests, integration suites, packaging, and security scans finish together instead of queueing behind each other. Pipelines connect with fan-in and fan-out dependencies, meaning a release pipeline waits for every upstream component to pass before it assembles them, and one library build can feed a dozen services. The value stream map draws that whole web on one screen, from the triggering commit through every stage to deployment, and any run can be compared with another to spot exactly what changed. Materials watch Git, Subversion, or Mercurial repositories and start pipelines on new commits, while artifacts produced by one stage are fetched, versioned, and promoted by the stages after it. Environments group pipelines and agents so test and production stay isolated, resources tag agents by capability, and elastic agents appear on Docker, Kubernetes, or cloud hosts only while work exists. Pipeline definitions can live in YAML or JSON inside a repository, changing through code review like the software they deliver, and templates keep repeated release patterns consistent across teams. 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.