A budget model, the launch document that explains it, and the slides that present it can live side by side in one self-hosted office workspace that people and AI agents edit together. Personal and Team Spaces organize Sheets, Docs, Slides, relational Bases, and Boards, with Recent, Trash, file import, and export views keeping everyday housekeeping close at hand. Sharing follows role and node aware access control, including anonymous viewing, so a single table or document can be opened to a reader without exposing the whole space. Data and references stay connected across artifacts as the workspace changes, which keeps a figure corrected in a sheet consistent with the document that quotes it. The Workspace Agent drafts and revises content in isolated Worktrees, verifies its own changes, and hands the result to a person for review before anything reaches the trunk. Several review rounds can happen while humans keep editing in the Browser, and nothing merges until someone approves it. The Workspace CLI connects existing agents to your deployment, so automation can create content, inspect data, render screenshots and PDFs, and run layout checks before review. Sign-in accepts passwords, GitHub, Discord, or application OAuth, and files move in and out as XLSX, DOCX, PPTX, and CSV without a separate conversion project. 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.

OneCLI gives every employee a sandboxed personal AI agent that works across company tools without ever seeing the real credentials it uses. Create an agent for each person, grant only the services that person may touch, and chat with it from its dashboard page or directly inside Slack channels and direct messages. The agent keeps its own filesystem, shell, memory, and skills between conversations, so follow up messages can redirect work in progress instead of starting over. Schedules wake agents at the right time to run recurring checks, reports, and follow ups without a person remembering to prompt them. When an agent calls Gmail, Salesforce, HubSpot, GitHub, Sentry, or another connected service, the gateway checks the request against team policy and injects the stored credential only for that call. Sensitive actions can pause for a deterministic human approval in chat, so sending an email, deleting a ticket, or changing a deal stage waits for your yes. Shared team connections let administrators connect a service once and grant it per agent, while memory remains readable and editable by the owner at any time. 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.

Three lab PDFs, a phone photo of a printed slip, and a spreadsheet become one cholesterol trend in Mirobody, a health data engine you host yourself, with the source file behind every number. Upload reports in 23 file types, import an Apple Health export, or connect Garmin, Oura, and Whoop, and every reading keeps a link to the page it was read from. Test names in English, Chinese, Japanese, and other languages resolve offline to LOINC codes and UCUM units, so HbA1c and Glycated Hemoglobin land on one series, and a name it cannot place stays unresolved instead of guessed. Ask questions in plain language and the agent shows each step as it works, charts the trend, and opens the reading and file behind every figure. A health journal turns one typed sentence into coded symptoms, blood pressure readings, and a medication entry, and a denied symptom like no fever is never logged. Genetic exports from 23andMe, AncestryDNA, and WeGene, or a VCF, can be queried by rsID, gene, or region. A care circle lets relatives share their own records on their own terms, and Claude Code, Codex, and Cursor can read your record through the built-in MCP endpoint. Choose OpenRouter, OpenAI, Gemini, Anthropic, or DeepSeek for answers, or keep every model on your own machine. 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.

Your coding agents work in separate terminals and cannot ask each other anything; Imbo gives Claude Code, Codex, opencode, Cursor CLI, and six other agent tools one shared messaging network, so a session can send a question to another session and get an answer while both keep working. Messages land inside the receiving session mid-task, and a reply wakes an idle session so it can act on the answer. You add people by account ID, and their agents can message yours; group chats let several sessions from several people coordinate on one brief, with every reply reaching every member. Sessions can send files that land in the receiving machine's ~/.imbo/files folder, and an agent asks you first before sending your data out, deleting files, spending money, or touching production. From the web app or the iPhone app you can message your own sessions from anywhere, and a closed Claude Code session reopens in the background to pick the message up. The server is a single binary with a bundled PostgreSQL, HTTPS through Let's Encrypt, email code sign-in, and optional domain restrictions on who may register. 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.

DeerFlow 2.0 is ByteDance's ground-up rewrite that transforms what began as a Deep Research framework into a batteries-included super agent harness handling tasks lasting minutes to hours autonomously. Built on LangGraph and LangChain, the runtime orchestrates a lead agent that plans, decomposes, and delegates to sub-agents executing in isolated Docker or Kubernetes sandboxes with persistent filesystem access, while an extensible skills system lets developers add capabilities as Python functions or MCP servers with OAuth token flows. The harness ships with long-term memory using persistent event loops with per-agent isolation, scheduled task execution via cron, context engineering with manual compaction, and a web UI at localhost:2026 for interactive sessions. Model support spans OpenAI GPT-4o/GPT-5, Anthropic Claude via OAuth, Google Gemini, DeepSeek, Qwen via vLLM, and OpenRouter-compatible gateways with per-model pricing configuration. IM channel integration connects Telegram, Slack, Feishu/Lark, Discord, WeChat, WeCom, DingTalk, and Buzz without requiring a public IP — all using long-polling or WebSocket transports. Production deployment uses Docker Compose with nginx reverse proxy, PostgreSQL or SQLite persistence, Redis stream bridges for multi-worker scaling, and lease-based run ownership with automatic orphan recovery. The terminal workbench TUI enables headless operation. 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.

A question goes in; a cited, long-form report comes out - GPT Researcher is an open-source autonomous research agent. A planner agent decomposes the query into sub-questions, execution agents crawl 20+ web sources in parallel with JavaScript-enabled scraping, and a publisher aggregates findings into a 2,000+ word report with inline citations, exportable to PDF, Word, and Markdown. The Deep Research mode extends this recursively: each result yields follow-up questions that are explored to configurable breadth and depth in a tree pattern, while accumulated learnings, citations, and visited URLs are shared across branches. It also researches local documents (PDF, CSV, Word) alongside the web. LLM and search providers are pluggable, including OpenAI, Anthropic, Google, DeepSeek, and Ollama for models, and Tavily, Google, Bing, DuckDuckGo, and SearXNG for retrieval. It ships as a Python package, a FastAPI server with web frontend, a Docker image, and an MCP server for use inside Claude or Cursor. MIT-licensed.

SourceWeft is an AI workstation you host yourself, where agents, your documents, and your model keys work in one place instead of scattering across chat tabs you do not control. Describe a job and a lead agent breaks it down, handing research, exploration, and execution to focused sub-agents that share the same working context and files. Agents draw on a skill library covering presentations, HTML pages, images, meeting summaries, and study guides, and you can add your own skills so good workflows become repeatable. MCP servers, web search, and web extraction connect agents to outside tools, while approved commands run inside a sandboxed environment that cannot touch the rest of your server. Feed it PDFs, web pages, notes, YouTube videos, Notion, Drive, Gmail, or Slack, then follow citations from any answer back to the source material it came from. Bring your own keys for the chat and indexing models you prefer, organize the team into workspaces with roles and access controls, and pick up any conversation from the web app or desktop clients. 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.

Once a voice agent is imported or built, Lampline connects it to a phone line, sends an AI caller to grade real calls, and keeps it all on your own server. Start by importing a Dialogflow CX or CX Agent Studio export along with a report of anything to check, or build fresh in a drag-and-drop builder that mixes LLM steps with scripted pages for exact lines and form fields. Next, pick one of 20 model providers, including Claude, OpenAI, Gemini, Bedrock, Groq, and DeepSeek, or run Ollama with local speech and no API keys. Test by chat or microphone while each step lights up, and let agents call HTTP and MCP tools and save records in collections of their own. Then connect callers through Twilio, Telnyx, or any SIP trunk, PBX, or session border controller via jambonz, with transfers to a person that carry the call's details as SIP headers. Finally, evals phone the agent over a real line, where an AI Test Caller brings background noise, accents, and interruptions, grades each transcript check by check, and reports typical and p95 response times as callers hear them. Each agent stays a folder of YAML and Markdown that you can review in git and lint or test with the vk CLI. 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.

When an agent breaks production at 3 a.m., "the model did it" is no incident report: Bernstein decides in advance what your AI agents may touch, then keeps receipts proving what they did. You write policy as code: which roles may do what, what needs human approval, and what must be recorded before a task counts as done. A deterministic scheduler with no model in the coordination loop turns each goal into parallel tasks, so replaying yesterday's plan reproduces yesterday's task graph exactly. Every coding task runs in its own git worktree behind merge gates; nothing lands on your main branch until tests, lint, and type checks pass. It drives the CLI agents you already use (Claude Code, Codex, Gemini CLI, Aider, Goose, dozens more), mixing cheap local models with heavy cloud ones in one run. Approvals can demand a hardware key touch, and role fences hold whatever an agent tries inside its task. The journal, lineage record, and optional tamper-evident audit chain capture every step, sealed into an Ed25519-signed receipt verifiable offline from the file alone. Non-code work gets the same treatment: an artifact contract names the deliverable (report, dataset, audit evidence pack), and the task completes on a signed receipt instead of a commit. You supervise from the browser dashboard or terminal UI, watching tasks, agents, approvals, and costs live. 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 77,000 GitHub stars accumulated in under five months since its March 2026 launch, Paperclip has become the default control plane for teams running multiple AI agents in production. Rather than juggling dozens of terminal tabs with Claude Code sessions, Codex instances, and Gemini CLI workers, Paperclip organizes all agents into a company structure with org charts, reporting lines, role-based permissions, and per-agent monthly budgets that trigger hard-stops when exceeded. The platform supports any runtime through its adapter system — Process adapters manage local CLI agents like Claude Code, Codex, Cursor, Pi, and OpenCode as child processes, while HTTP adapters trigger remote agents via webhooks to OpenClaw, serverless platforms, or custom endpoints. Heartbeat-based execution wakes agents on configurable schedules, injecting goal context, budget state, and workspace paths directly into the invocation payload. The Work and Task System provides atomic checkout with execution locks, first-class blocker dependencies, and structured work products to eliminate duplicate effort. Governance features include approval workflows, decision tracking, emergency stops, and full audit trails tracing every mutation to an actor. Deployment runs as a single Node.js process with embedded PostgreSQL locally or scales to external Postgres for production, installable in one command via npx paperclipai onboard. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Big repositories, small questions: Open Kritt is a self-hosted platform that splits vulnerability research into focused tasks for AI agents and returns ranked, de-duplicated findings. Build a workflow as a tree of prompt steps, where each step declares the structured output it must produce and the next level launches one fresh agent per result. Scan remote or local repositories along with their dependencies, using Codex, Claude Code, or Grok Build as the harness. Every workflow ends in one fixed finding schema covering file, line, vulnerability type, trigger flow, and a malicious input example. Post-scripts then validate each finding, build a proof of concept, or write the report. Markdown severity rankers tell the model how to prioritize for your bounty program, and repeated findings collapse automatically. Model access comes from a Codex login or OpenAI, Anthropic, DeepSeek, OpenRouter, or xAI keys, with an Active switch to choose which accounts take new work. A dashboard tracks blueprints, scans, and findings, a headless command-line tool imports workflows and launches scans on servers without a browser, and finished scans export as one ZIP with a share-safe manifest. Built-in workflows, including an entry-point-driven hunt, give you a starting point. 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.

Kandev provides a command center for orchestrating AI coding agents across parallel workstreams. The Go backend paired with a Next.js frontend delivers kanban boards with drag-and-drop columns, pipeline workflow definitions with per-step agent handoffs, and an IDE-like review workspace combining file editor, file tree, terminal, browser preview, and unified git diffs. Multi-provider support connects Claude Code, GitHub Copilot, Codex, Qoder, Grok, and custom agents through configurable profiles with per-agent prompts, runtimes, and review gates. Tasks execute in isolated git worktrees with multi-repository support, letting agents work on separate branches simultaneously while changes surface in a consolidated review interface. Native integrations with GitHub, GitLab, Jira, Linear, Sentry, and Slack pull external issues into the kanban and link tasks to pull requests. Kandev exposes streamable HTTP and SSE MCP endpoints, enabling external clients — Cursor, Claude Desktop, Augment — to create tasks and read workspace context programmatically. Workflow definitions export as portable YAML for sharing across installations. Agentic workflows chain multi-step pipelines mixing different models per step — Opus for architecture, Sonnet for implementation, with human review gates between stages. 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.

OpenCode puts a capable coding agent in a browser tab, so a project on your server can be worked on from any device. Start a session, describe the change, and watch the agent read files, edit code, and explain what it did in plain language. A review panel lists every changed file with unified or split diffs, a file tree, and a git changes view, so nothing lands without a look. Sessions open as tabs, run in parallel, and keep a searchable history per project. The model picker spans more than 200 providers plus free hosted models, and any OpenAI compatible endpoint can be added from a config file, which keeps local and self-hosted models in reach. Settings offer top tabs, side tabs, or an inbox layout, optional permission auto-accept, steer or queue behavior for follow-up prompts, timeline detail levels, themes, and fonts. Extensions cover MCP servers, plugins, and skills, and custom agents and commands capture the team's habits. One-time pairing links connect a new browser or app to the server 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.

Versus Incident is a self-hosted AI SRE agent and incident manager that learns what normal looks like in your logs, metrics, traces, and Kubernetes clusters, then opens a triaged incident the moment something genuinely new appears. Detection earns trust gradually. Training mode only observes and catalogs patterns; shadow mode records what it would have alerted so you can judge its instincts; detect mode creates real incidents with an AI-written summary, a severity, and suggested next steps attached. Existing alerting does not have to move: Alertmanager, Grafana, Sentry, CloudWatch, Fluent Bit, and custom scripts post to the same webhook endpoint, and every incident, however it arrived, is rendered with your Go templates. Delivery fans out to Slack, Microsoft Teams, Telegram, Viber, email, and Lark. Silence has a deadline, because unacknowledged incidents escalate to on-call through PagerDuty, AWS Incident Manager, Opsgenie, incident.io, or ServiceNow. The Kubernetes dashboard gathers cluster health and capacity, workloads, resource relationships, recent changes, Helm releases, and GitOps status, and a DevOps chat agent in the web UI answers questions against the connected systems while responders work. The admin dashboard reviews learned patterns, shadow events, and raised incidents, so the agent's judgment stays inspectable. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Pi Web is a browser interface for the Pi coding agent ecosystem, providing a visual workspace that reads the same local configuration and session files as the CLI. The session workspace groups conversations by project with running state indicators, context usage percentages, cost tracking, and compaction details, while two branching modes let users create independent session files from earlier messages or fork branches within existing sessions to explore alternative coding directions. Real-time streaming via Server-Sent Events delivers agent responses with structured Markdown rendering, thinking steps, tool call visualization, and image drag-and-drop input. The project file explorer browses working directories with syntax-highlighted source preview, Git diff inspection, and rendering for Markdown, images, audio, PDFs, and DOCX files with automatic refresh. Git worktree support switches checkouts from the sidebar while keeping sessions from the same repository grouped together. The Models panel manages provider authentication via OAuth and API keys, model selection, model smoke tests, and models.json configuration shared bidirectionally with the CLI agent. The Skills panel lists, searches, installs, and toggles agent skills without terminal access. The interface ships with English and Simplified Chinese translations, light and dark themes, a chat minimap, keyboard shortcuts, and completion sounds. Basic Auth protects remote access when binding to non-loopback addresses. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With over 15,000 GitHub stars accumulated since its February 2025 launch, BillionMail delivers the rare combination of a production mail transfer agent and a full email marketing suite in a single self-hosted package — eliminating the monthly per-subscriber fees charged by Mailchimp, SendGrid, and similar platforms. The Go-based architecture bundles Postfix for SMTP transmission, Dovecot for IMAP and POP3 mailbox access, Rspamd for intelligent spam filtering and greylisting, and RoundCube for browser-based webmail, all orchestrated through Docker Compose with PostgreSQL for persistent storage and Redis for queue management and caching. The marketing engine supports unlimited subscriber lists with tag-based segmentation, scheduled campaign sends, A/B subject line testing, and both HTML and drag-and-drop visual template editors for crafting responsive emails without coding. Real-time analytics dashboards track sent volume, deliverability rate, open rate, click-through rate, and bounce reasons, while the platform provides step-by-step DNS record configuration wizards for SPF, DKIM, and DMARC to maximize inbox placement. A transactional email API exposes REST endpoints for single and batch sending, enabling integration with CRM systems, e-commerce platforms, and custom applications. Auto-provisioned free SSL certificates, Fail2ban brute-force protection, and privacy-first architecture with zero third-party tracking ensure secure operation. The platform installs in under eight minutes via a single shell script and supports SMTP on port 25, SMTPS on 465, submission on 587, IMAP on 143/993, and POP3 on 110/995. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPLv3 licensed.

Powering notification delivery for thousands of organizations with over 39,000 GitHub stars, Novu is the open-source communication infrastructure that eliminates the need to build separate integrations for every messaging channel. The TypeScript-based platform provides a single API endpoint that routes notifications across In-App Inbox, Email via SendGrid, Mailgun, AWS SES, and Postmark, SMS through Twilio, Vonage, and Plivo, Push via Firebase Cloud Messaging, Expo, and APNS, and Chat through Slack, Discord, Microsoft Teams, and WhatsApp. The embeddable React Inbox component delivers real-time WebSocket-powered notifications with read/unread states, action buttons, and user-controlled preferences directly inside your application. The workflow engine orchestrates complex multi-channel delivery with conditional branching, time delays, digest batching to reduce notification fatigue, throttle controls, and per-step channel fallbacks. Novu Connect introduces Agent Communication Infrastructure enabling AI agents built with LangChain, Claude, or custom frameworks to hold threaded two-way conversations with humans across any supported channel through a single conversation model with identity resolution and credential management. The backend runs on Node.js with NestJS, MongoDB for notification storage, Redis with BullMQ for job queuing, and Socket.io for real-time delivery. Self-hosting deploys via Docker Compose with the dashboard accessible at port 4200. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.