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.

Slashdocs gives AI agents and the people who supervise them one shared home for finished work, replacing reports pasted into chat threads with reviewable HTML documents that live at a permanent address. An agent publishes a single self-contained HTML file, an architecture review, incident postmortem, product spec, data analysis, or QA report, and teammates open it in the browser to read the rendered page rather than raw markup. Reviewers anchor comments to exact words, resolve or reopen threads, and follow links straight to a heading or discussion, while Slack notifications announce new activity with personal mute controls for quieter channels. Every publish creates an immutable version guarded by optimistic concurrency, so an agent can read the feedback and push the next revision without overwriting anyone's copy. Agents connect through a remote MCP endpoint with browser OAuth or service-account keys, and people sign in through OpenID Connect with providers such as Google, Okta, Entra ID, or Keycloak. The companion CLI creates, pulls, pushes, and comments on documents with compact output or JSON for scripts, and folders plus sharing controls keep a growing library organized. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Aizen is a coding agent that actually lives on your server: one small binary you can message from your phone, which fixes code, runs the tests, and reports back before you are anywhere near a keyboard. Leave it running on the box and drive it from Telegram or Discord, approving risky edits with a tap while it works behind NAT with no inbound port to expose. In the terminal it is a single chat and agent loop with a live heads-up display of model, tokens, and context, reading files in parallel, editing symbolically through the language server, and running your shell under an approval layer with a hard floor that refuses catastrophic commands even on auto-approve. It does not get to claim done early: a verify gate runs your typecheck and test suite and sends it back to fix what it broke, git-backed checkpoints let you rewind a bad turn, and seven capability-scoped sub-agents can fan out across finding, planning, building, reviewing, testing, research, and recall when a job wants a team. Point it at any OpenAI-compatible endpoint, from hosted models to your own local server, extend it with MCP servers and slash-command macros, and let the sandbox keep every child process away from your API keys with the network denied by default. 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.

taOS is a self-hosted operating system for AI agents that lives on hardware you already own, offline by default and cloud only when you invite it. Open one URL and a full web desktop appears: floating windows, a dock, launchpad, widgets, notifications, and 43 bundled apps, from mail and kanban projects to an app store with over a hundred one-click installs. Agents deploy through a guided wizard into isolated containers (LXC on bare metal, Docker on a VPS), each with its own memory store, files, secrets, and network identity. taOS owns the agent lifecycle outside the framework, so you can swap SmolAgents for LangChain or OpenClaw and the agent keeps its history, channels, trained adapters, and API keys untouched. Long-term memory is a temporal knowledge graph with hybrid search on your disk, not a row in a vendor database, and the messages app works like a private Discord that also installs as a phone PWA. Local inference spans Apple Silicon, NVIDIA, AMD, Rockchip NPUs, Raspberry Pi boards, and salvaged Android phones, with auto-clustering that pools idle machines into one compute fabric. Messaging connectors cover Telegram, Discord, Slack, Matrix, email, and webhooks, and a rollback command returns the system to a known-good state when an experiment misbehaves. 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.

Ask a hard question and get back a cited report instead of a chat answer: Deep Research Web UI plans its own searches, reads the pages it finds, checks claims against the sources, and shows its work as it goes. The research unfolds as a live tree in your browser, each branch a search direction with streaming responses, so you watch a broad question narrow into answerable parts. When snippets are not enough, it fetches full source pages and extracts verbatim evidence, sharing one token and request budget across the run. Every claim cites its source inline, and clicking a citation opens an evidence panel with the source, retrieval time, and the excerpt behind the finding. Findings can be followed up: name what to verify and the agent searches again, updating only the passages that cite that finding while the original report stays untouched in your history. You bring the models, from OpenAI-compatible endpoints, DeepSeek, and OpenRouter to a local Ollama or LiteLLM proxy, paired with Tavily, Firecrawl, Google PSE, You.com, or Serply for the searching. Finished reports export as Markdown or PDF, search separates your question from time and source filters and retries once with a revised query when evidence is thin, and Server Mode keeps the team's API keys in environment variables behind an optional access password instead of in every visitor's browser. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Recognized by the CNCF Landscape in the AI Agent – Workflow Orchestration category alongside Dify and Temporal, Astron Agent is iFLYTEK's fully open-source platform for building, deploying, and managing enterprise multi-agent systems — backed by 8,900+ GitHub stars and the production infrastructure behind one of China's largest AI companies. Unlike pip-install frameworks such as LangGraph, CrewAI, or AutoGen, Astron Agent ships as a complete microservices platform spanning 10+ services across Java, Python, Go, and TypeScript: a ReactFlow-based visual workflow builder for low-code agent orchestration, native integration with the Model Context Protocol (MCP) for tool calling, a built-in model management layer supporting iFLYTEK Spark, OpenAI, Anthropic, and on-premises MaaS deployments, and a multi-tenant Go authentication service powered by Casdoor. The standout differentiator is native RPA integration via the companion astron-rpa project (7,200+ stars), providing 300+ pre-built automation capabilities spanning browser, Office document, and enterprise system interaction — enabling agents to execute physical UI actions rather than only API calls. Infrastructure includes PostgreSQL for multi-tenant data isolation, MySQL for application metadata, Kafka for event streaming, Redis for caching, and MinIO for object storage, all orchestrated through Docker Compose with explicit health checks and dependency chains or production Kubernetes Helm charts. 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.

This is a marketing operations control center that replaces fragmented CRM, outreach, content, and analytics tools with a unified self-hosted interface designed for AI agent-assisted go-to-market teams. The CRM module manages leads through a configurable pipeline funnel with stages from New through Sequenced, Replied, Interested, and Booked, tracking source attribution, industry segments, company size, lead quality scores, and LinkedIn URLs per contact. Outreach sequencing supports email campaigns with pause controls, audit endpoints, suppression workflows, and engagement tracking. The content operations surface provides calendar views, content item management, performance metrics, and approval queues for editorial control. Analytics and KPI dashboards show impressions, engagement, and send volumes over configurable time periods, with optional connectors to Plausible, Google Analytics 4, X, and LinkedIn for cross-platform reporting. The OpenClaw-native agent runtime enables dynamic agent and squad discovery, workspace management, session monitoring, and communications surfaces. Automation scheduling uses cron job templates with OpenClaw-compatible schedule variants including cron expressions, every intervals, and at timestamps. The tech stack combines Next.js 16 App Router with React 19, Tailwind CSS 4, Recharts, and Zustand for state management. Authentication supports session cookies, API keys, and optional Google OAuth with role-based access controls. All state persists locally in SQLite via better-sqlite3 with no required external infrastructure. On RepoCloud, deploy Marketing Dashboard on a dedicated VPS with persistent SQLite storage, root SSH access, and complete control over your marketing operations data, all under the MIT license.

Close the laptop, walk away, and your coding agents keep working; CodeRail is the remote control that lets you supervise them from a browser or your phone without handing your machines to anyone's cloud. A small bridge on each computer connects outbound to your server, so there are no open ports and no VPN to babysit, and each machine keeps its own Claude Code and Codex logins because CodeRail never holds your AI keys. Chats show plans, tool calls, models, modes, and background tasks, and when an agent wants to run something sensitive, the approval lands with you wherever you are, including as a phone push notification. Real terminals outlive the browser tab, files can be viewed, edited, uploaded, and downloaded in place, and git work, pull requests included, sits beside the conversation that produced it. Each chat even gets a browser on the computer itself, shared live with everyone in the chat and drivable by the agent. Roles run Owner, Operator, or Viewer per computer, narrowed down to folders and agents, with every change audited, and sessions keep running with every browser closed while history stays readable offline. 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.

Give your AI assistant a name, a memory you can actually inspect, and a permanent seat on your own server. OhMyBuddy has two sides that share the same models and tools. The Buddy side keeps one ongoing conversation, learns your preferences, and shows a receipt under any reply that saved something, so every memory can be reviewed, edited, or undone. The Workspace side opens real project folders with threads, streaming tool calls, file diffs, side chats, and a branching history view. Add scheduled tasks, an artifacts library, and a media lab for image, video, and speech generation. Connect extensions, MCP tools, a browser, and subagents when a job needs more hands. Sessions live on the server, so a laptop, a tablet, and a phone home screen all continue the same chat, with notifications when a reply finishes. Bring Claude, GPT, Gemini, DeepSeek, or any OpenAI-compatible relay, and protect the instance with an access token. Keep a personal AI on hardware you control, reachable from every device you own. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. ISC licensed.

Obscura is the headless browser you point Puppeteer or Playwright at when Chromium feels like renting a truck to fetch a letter. Start the server and your existing automation connects over the usual DevTools protocol, opens pages, clicks, types, waits for selectors, and reads the fully rendered result, JavaScript included. Scrape one page or fan out across many in parallel, evaluating an expression on each and getting structured output back. Capture viewport or full-page screenshots, export PDFs, intercept requests to block or rewrite them, and manage cookies and headers per session. An MCP mode lets AI agents drive the browser as a tool instead of shelling out to scripts. Stealth mode randomizes fingerprints per session, presents realistic browser identity signals, and blocks thousands of known tracker domains before they load. Proxies, persistent storage for cookies and local storage, and robots handling round out the controls for longer crawls. The whole thing starts instantly and sips memory compared with a conventional headless Chrome, so a modest server can keep many more pages in flight. 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.

Describe the task in plain words, pick the sources and model it may use, and an agent plans the workflow before running it. That is the core loop: agents build editable visual workflows from a task description, execute them on demand or on a schedule, and keep everything traceable. Prefer building by hand and the canvas offers 17 preconfigured steps, branching, undo and redo, JSON import and export, plus eight starter templates. Feed it real work by importing PDF, DOCX, XLSX, CSV, JSON, and text files, or by connecting folders, HTTP endpoints, and approved local programs. Upload a screen recording and it identifies the actions with timestamps, turning a demonstrated process into an editable workflow you can refine. Model calls go to the endpoint you choose: Ollama, LM Studio, vLLM, or any OpenAI-compatible service, local or cloud with your own credentials. Every run can be inspected step by step, cancelled mid-flight, and exported as JSON, CSV, or Markdown reports. Observations from completed runs land in a knowledge and learnings store, where you review them and promote the useful ones into reusable skills for the next task. The Docker release bundles the application with FFmpeg and local Whisper support, and your documents stay 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 License 2.0 licensed.

Designed for developers on the go, Yep Anywhere turns any smartphone browser into a full-featured control center for supervising, steering, and reviewing autonomous AI coding agents. Operators can monitor live execution across multiple active projects simultaneously without sitting at a desktop terminal. Real-time reasoning feeds. Instant push alerts for permission prompts. One-tap tool approvals. Developers can unblock pending tasks mid-turn, redirect active workflows, or queue sequential follow-up prompts for automatic delivery at the next safe milestone. An integrated source control viewer displays syntax-highlighted working-tree and commit diffs, allowing reviewers to attach line-level comment bundles directly back into the agent context. Mobile voice transcription lets users dictate instructions straight into running sessions, while photo library integration makes uploading bug screenshots effortless. All agent credentials, CLI configurations, and repository data remain private on the host server without requiring third-party cloud database accounts or proprietary device pairing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Run a whole fleet of AI agents as managed services, each with its own model, memory, schedules, and sandboxed workspace, from one admin console. Create an agent, point it at OpenAI, Anthropic, OpenRouter, or any OpenAI-compatible endpoint, store its API keys encrypted, and it is ready to chat in the browser. People sign in with a device key and get a session list, streaming replies, and file attachments. The Agents table shows status, last activity, sessions, errors, and token spend for the past 24 hours, and the Stats page tracks users, sessions, events, and total tokens. Cron or one-shot schedules let an agent send a daily brief, and each run is logged. Owner, user, and guest roles control who may talk to an agent or change it, and policy and approval tabs gate risky tool calls. Skills and MCP servers are registered once and enabled for one agent or the whole fleet, and instructions can be pushed to every agent at once. Sessions, memories, and secrets sit in PostgreSQL, so state persists across gateway restarts. Use it for an internal agent platform, a support desk, or one agent per customer. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Getting a language model into the chat apps people already use takes a single self-hosted server running AstrBot, which answers in QQ, Telegram, Discord, Slack, Lark, DingTalk, LINE, and WeCom. The model itself is a setting. OpenAI-compatible endpoints, Anthropic, Google Gemini, DeepSeek, Ollama, and LM Studio all work, with fallback models and retry limits for failed requests, and Dify, Coze, or Alibaba Cloud Bailian can take over a conversation too. A bare model cannot act, so the built-in agent calls MCP servers and Skills, delegates to SubAgents, runs scheduled tasks, and executes code in an isolated sandbox. It cannot read your files either, so a knowledge base takes PDF, Word, Markdown, and EPUB uploads and searches them with hybrid dense and BM25 retrieval. Personas shape each bot's personality, and Whisper or Edge TTS adds speech. When an answer looks wrong, the ChatUI shows thinking, tool calls, token counts, and latency, and a per-message trace timeline shows how the bot got there. Because the panel steers the bot, administrator IDs, session whitelists, optional TOTP login, and HTTPS protect it. Backups live under System Settings, and the plugin market installs any of more than 1,000 extensions in one click. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

DocsMint is a self-hosted knowledge workspace where your team writes documentation once and both people and AI agents retrieve it through hybrid search and a built-in MCP server. Documents live in a rich visual editor with Markdown import and export, organized by folders, categories, and tags, with sharing and version history. Search blends exact title matches, multilingual keyword search, typo-tolerant fuzzy matching, and semantic vectors, then widens results through graph relationships between documents, so a query in one language or phrasing still finds the right page. Every edit quietly refreshes the index in the background; nothing needs manual re-embedding. Agents connect through 22 MCP tools covering search, reading, creation, updates, folders, snapshots, and export, over a local stdio bridge or the HTTP endpoint on your own installation. Category-scoped API keys hand each integration only the slice of the library it may read, edit, or write, while a global key serves trusted automation. The same operations are available through the REST API, a typed TypeScript SDK, and a terminal CLI for scripts. The web application installs as a PWA with offline reading, and AI features run on your choice of an OpenRouter key or a fully local Ollama setup. 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.

Agent code needs somewhere disposable to run, and Sandstorm turns one modest VPS into a fleet of thousands of isolated sandboxes that wake the moment work arrives. You create sandboxes through a plain HTTP API, starting from a registered template or forking a tagged snapshot, with per-sandbox memory ceilings, attached volumes, and egress rules set on each call. Every sandbox is a gVisor container with its own network namespace, so untrusted agent code runs away from your host and away from its neighbors. Idle sandboxes cool down through four tiers, from running hot, to frozen in place with a wake time near ten milliseconds, to checkpointed on disk and back in about a fifth of a second, so a small machine can hold far more sandboxes than it could ever keep running at once. A single binary acts as master, node, and web console: the master tracks desired state and places work across nodes, nodes behind NAT dial out to join the fleet, and a gateway on each node wakes a sleeping sandbox and forwards its traffic automatically. The built-in Hub pulls ready-made snapshot packs for warmed runtimes like Python with numpy or a pre-warmed Playwright browser, skipping cold starts entirely. 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.

Autonomous red team execution without manual script coordination is what PentaGI delivers through a multi-agent penetration testing platform engineered for automated security assessments. Security engineers configure testing scopes, target IP ranges, domain lists, and rules of engagement through an interactive web console with real-time execution graphs. Autonomous agent personas break down high-level assessment goals into discrete tactical phases, orchestrating network port discovery, service banner fingerprinting, web application crawling, and CVE verification. Specialized agents query integrated Graphiti knowledge graphs and local vulnerability repositories to synthesize attack paths, validate exploitability, and confirm finding veracity before issuing alerts. Operators monitor live agent terminal streams, inspect sandboxed tool executions, and adjust active LLM provider routes across OpenAI, Anthropic, or local Ollama endpoints. The template editor allows red teams to compose reusable testing playbooks with customizable security prompt chains, safety constraints, and automated remediation reporting. Audit logs capture full command histories, raw tool outputs, and LLM reasoning steps to generate compliance-ready technical documentation. 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 call your AI agents make becomes a searchable trace in LangWatch, and the same platform tests and scores those agents before a new prompt or model reaches users. The Trace Explorer filters by origin, user, model, cost, and evaluator, reads each run as a waterfall, flame graph, topology, or sequence diagram, and takes traces from the Python, TypeScript, and Go SDKs or any OpenTelemetry source. Agent Testing sends simulated users, in text or beta voice calls, through your agent while a judge passes or fails every criterion with its reasoning, adds multi-turn red teaming, and compares two agents side by side. The Experiments workbench scores prompts and agents on datasets with LLM judges, exact match, and RAG checks, then compares runs on cost, latency, and pass rate, while online evaluations monitor live traffic and guardrails block unsafe replies. Prompts keep version history and staging or production tags, Workflows wire prompts, Python code, and HTTP calls on a visual canvas, and annotation queues route traces to human reviewers. Alerts fire when a graph crosses a threshold, automations post to Slack, email, or webhooks, and scheduled reports go out by email or Slack. Claude Code, Codex, Copilot, Gemini CLI, and opencode report session cost, pull request cost, and terminal replays, and an MCP server exposes trace search and prompt management to coding assistants. 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.