Search the web from your own server, with no API key and no per-query bill: OpenSERP is a self-hosted search API that returns structured results from Google, Bing, Yandex, Baidu, DuckDuckGo, and Ecosia through one interface. Every answer arrives as ranked JSON with titles, URLs, snippets, source engines, and timing, ready for an agent, a RAG pipeline, or an SEO tracker to consume. A mega search aggregates and deduplicates across engines in a single call, image search does the same for pictures, and an extract mode reads linked pages back as clean Markdown for models to cite. AI agents connect over MCP with tools for search, mega search, fast search, image search, and batch extraction, and it is a built-in web search provider in Open WebUI. Developers get Python and TypeScript SDKs, an n8n node, a full OpenAPI reference, and a CLI that runs the same searches from a terminal. Engines load in a real browser session, proxy support routes traffic through HTTP or SOCKS5, and one Docker command serves everything on port 7000. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

PenguinHarness turns a one-sentence description of the agent you need into a working app, then lets other agents tune it round after round until its benchmark score climbs. Nine self-improvement algorithms ship as plugins, including OPRO, APE, ACE, and AWM, and every candidate becomes a snapshotted version with its score recorded in an Evaluation Center. Seventeen ready-made benchmarks cover data analysis, repository fixes, workflow automation, and terminal science tasks. Agents read and act on web pages through a built-in browser panel or your own Chrome, and each agent can grow a hot-reloaded workbench page like a contract review desk with uploads and downloadable reports. Add a machine over ssh and conversations in that workspace run there, inside the same window. A Cost Center breaks down spend per run, trajectories show every turn on an execution timeline, and replies can carry forms, charts, and live widgets. An Agent API streams runs to outside apps, and agents can be reached from Feishu, QQ, Telegram, or WeChat. 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.

One binary replaces your booking link and your meeting room: Calnode is a complete scheduler you run yourself, small enough to audit and cheap enough to forget. Create event types with durations, custom questions, and locations, set DST-correct availability with date overrides, and share a booking page where guests pick a slot, reschedule, or cancel without an account. Two-way sync with Google Calendar, Microsoft 365, and CalDAV checks real free and busy time across every connected calendar, then mints Meet or Teams links automatically. Teams route bookings round-robin, collectively, or by priority, while paid event types collect through Stripe before the slot confirms. Choose Calnode Rooms and the meeting itself happens in the browser on your LiveKit server, with host controls, consent-aware recording into your own storage, and an AI notetaker that files a transcript and summary on the booking. Agents get first-class access through the REST API, HMAC-signed webhooks, and a native MCP server, and visitors can even book by describing a time in plain language. Everything runs from one static binary and one SQLite file with streaming Litestream backups. 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.

Follow every sale from first inquiry to final payment inside one self-hosted CRM. Cordys CRM splits the lead-to-cash cycle into connected modules: leads with custom forms and one-click conversion, customers with contact records and shared follow-up among team members, and opportunities that advance through configurable stages from needs confirmation to won or lost. Quotations and contracts come next, with contracts carrying payment plans, payment records, business titles, and invoice records so every collection stays traceable. Orders link to contracts and move through a customizable status flow covering shipment requests, partial and full shipment, inspection, and completion. Approval workflows route requests to reviewers and keep an approval history, and real-time notifications reach users while they work. Administrators draw the organization chart, assign role-based permissions, configure modules and form fields without code, and review system logs. An MCP server secured with per-user API keys lets MaxKB agents search records, create leads, customers, opportunities, and contacts, log follow-ups, and update accounts, while an Agents module embeds those assistants in the CRM and CRM Skills connect OpenClaw and WorkBuddy to the sales process. Sales data can feed DataEase dashboards, WeCom, DingTalk, and Lark integrations link departments and messages to the office platforms teams already use, and the interface ships in English and Chinese. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed with FIT2CLOUD branding terms.

DeepSeek Harness gained over 60,000 GitHub stars within hours of its August 2026 launch, establishing itself as the first fully modular open-source agent runtime where literally every component is a swappable plugin. Built on the Cordis framework—a programming paradigm for spatiotemporal composability—dsh decomposes the entire agent stack into independently replaceable pieces: model adapters for DeepSeek, Anthropic, OpenAI, AWS Bedrock, Azure, and Google Gemini; tool registries covering bash execution, file system operations, web search, subagent delegation, and todo management; plus session stores, sandboxes, approval policies, orchestration loops, and the user interface itself. Four operating modes serve different workflows: Standard provides the full toolset, Code mode uses model-generated code to compose multi-round tool calls, Minimal strips down to a shell and editor for benchmarking, and Creator mode lets developers inspect the running runtime and test Cordis plugins in memory. The kernel handles plugin mounting, unmounting, and dependency resolution while typed events and services coordinate between components. Profiles and bundles allow the same codebase to produce entirely different products—a terminal coding agent, a browser-based workspace, a headless automation service, or an ACP/JSON-RPC endpoint—by swapping YAML configuration layers. Session history is stored as an append-only event stream for full trajectory replay, and project-level hooks on agent lifecycle events enable fine-grained behavioral customization. MCP client integration connects to external tool servers, while Agent Client Protocol enables programmatic orchestration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Cognee gives AI agents persistent long-term memory that survives across sessions, replacing the traditional stack of separate graph, vector, and session databases with a unified engine running on a single PostgreSQL instance. The memory-native API exposes four verbs (remember, recall, forget, and improve) enabling agents to persist context, retrieve cited answers, prune outdated knowledge, and self-improve from feedback. Under the hood, Cognee combines pgvector embeddings with a PostgreSQL-native graph store and cognitive-science-grounded ontology generation, delivering hybrid retrieval that fuses semantic similarity, structural graph traversal, and lexical search in a single query. Integrations span Claude Code, Cursor, LangGraph, OpenAI Agents, and any MCP-compatible client through a dedicated MCP server on port 8001, while the Python and TypeScript SDKs provide direct programmatic access. The platform supports swappable backends including Neo4j, FalkorDB, Qdrant, ChromaDB, Weaviate, Milvus, and LanceDB for teams with existing infrastructure. Built-in OpenTelemetry tracing, an experimental dashboard with knowledge graph visualization, multi-tenant user isolation, and audit trails ensure production readiness. Deploy via Docker Compose with optional profiles for PostgreSQL, Neo4j, Redis, and the web frontend. Reached v1.0 in April 2026 with 30,000+ stars. 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.

Accounted is an open-source accounting platform built for Swedish sole traders and limited companies that keeps double-entry bookkeeping, invoicing, payroll, and tax filings compliant with Swedish accounting law. Create and send customer invoices with mixed VAT rates, generate PDFs, and track payment status, while supplier invoices record input VAT and feed batch payment files your bank can upload. Connect the bank feed to reconcile transactions automatically, then watch matched entries clear in passes instead of hunting through statements line by line. VAT declarations map onto the SKV 4700 form with per-rate breakdowns, and tax reports export in the formats the tax agency expects for sole traders and companies. Run payroll with salary runs and payslips, file employer declarations, and sync the tax account so booked movements reconcile against the agency record. Every receipt and document lands in an archive with integrity checks and seven-year retention, and period locks with sequential voucher numbers keep the books audit-ready. An AI agent can categorize transactions, draft vouchers, and prepare declarations through the built-in agent tools, while every posting waits for your approval before it commits. Import or export the standard SIE format to move between Swedish accounting systems, and send or receive electronic invoices through the Peppol network. 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.

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.

OpenMA lets you build and run AI agents with the model, harness, and sandbox you choose, on infrastructure you control, while it handles the sessions, execution, and recovery around them. Create an agent in the console, give it work, and come back later to the same session, because conversation history, streamed progress, and execution attempts are preserved rather than tied to one process that might die. Agents start with shell, file, web, and browser tools, then grow through MCP services and reusable Skills, while resources such as GitHub repositories, uploaded files, and shared memory attach to the work that needs them. Deployments run agents manually or on schedules you define, environments carry their own networking and package configuration, and model cards keep provider settings in one place instead of scattered environment files. If a sandbox fails, the session survives it; a replacement harness can rebuild context from durable events and workspace checkpoints. Operate everything through the console, the API, or the CLI, and plug in the database, queue, and object storage your deployment already trusts. 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.

While ordinary chatbots sit idle between prompts, Agenvoy runs around the clock on your own machine, turning one-sentence requests into finished research, files, and reports. Say what you need once and it builds the missing tool itself, tests that tool inside a sandbox, saves it, and reaches for it again the next time a similar job appears. Recurring work becomes a schedule in plain words; a morning briefing, a watched folder, or a weekly report then runs unattended, and a long task interrupted mid-run resumes from its checkpoint instead of starting over. Ask questions about your own files and it searches them like a private archive, transcribing audio and video into text it can quote back to you. Each task is routed to the model tier that fits it, a light model for lookups and a heavy one for hard reasoning, across subscription logins, API keys from eleven providers, or a local Ollama that never phones home. Commands run in a sandbox with the network off until you approve a call, sensitive paths ask before they open, and credentials wait in the system keychain instead of the chat history. You drive it from the terminal, the browser dashboard, or Telegram and Discord when you are away from the desk, and it lends its sandboxed tools to Claude Code and Codex over MCP. 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.

Codeman is a self-hosted mission control for AI coding agents that runs Claude Code, Codex, OpenCode, Gemini, Copilot, and five more agent CLIs in persistent sessions you can watch and steer from any browser, phone included. Sessions live in tmux, so agents survive server restarts, network drops, and laptop sleep, with full scrollback replay when you return. Run up to twenty sessions as tabs or in a six-up tile grid, each streaming its real terminal with token and cost tracking, and tabs that blink when an agent goes idle or needs an answer. Idle detection re-prompts stalled agents, and when a subscription usage limit hits, Codeman parses the reset time, waits it out, and resumes the run unattended. Subagents appear as floating live windows tethered to their parent session, with real-time transcripts, token counts, and status badges. Agents can drive Codeman too, through a bundled skill, CLI verbs, and an MCP server that let one agent start, prompt, and collect answers from workers in other CLIs. Run a project in an isolated Docker container or on another machine over SSH, preview agent-created files in the browser, and reach everything from your phone with QR login and push notifications, or over Tailscale with a real certificate. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Fusio turns the data and services you already run into a managed API that partners, apps, and AI agents can actually use. The workflow starts small: add a database connection and a table becomes a REST endpoint, or proxy a remote service and route traffic between internal microservices. Each operation pairs an HTTP path with an action and a schema, so requests are validated and an OpenAPI specification plus client SDKs for major languages come out without extra effort. Custom behavior lives in reusable actions, and an AI assistant can draft actions and schemas from a plain-language prompt. Native Model Context Protocol support then offers those actions to autonomous agents as tools. Third-party developers get a self-service portal with documentation, testing tools, and their own keys. Every endpoint can be protected with scopes and rate limits. Asynchronous work runs through events, webhooks, cronjobs, and triggers. When the API becomes a product, plans, quotas, and transactions handle billing, and analytics follow usage, performance, and errors. A marketplace installs ready-made actions and apps, and the generator and test panels speed up development. 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 analysts write the context once, and everyone else just asks questions: nao turns your warehouse into an analytics agent that answers in plain English, showing the SQL and source files behind every answer. The data team builds the context layer by syncing warehouse schemas, dbt projects, documentation, and business rules into files the agent reads, then tests key questions offline against expected SQL before any change ships. Colleagues ask from the web chat, Slack, Teams, or any MCP client, and turn good answers into live dashboards, data apps, and slide stories they share with their team. Every conversation can be replayed, and when an answer earns a downvote, context recommendations turn the mistake into a fix that arrives as a pull request. You bring your own model key from any provider, sign people in with Google, GitHub, or GitLab, and keep warehouse permissions intact as queries run. Dashboards from Metabase or Tableau migrate over instead of starting blank. 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 outcome once, in plain language, and a small crew of AI agents divides the work between them and reports back in the same chat. You type the request in the team chat; Boo Zero, the team lead, splits it into jobs on a shared board and hands each card to the teammate best placed to do it. Teammates run on Claude Code, Codex, Hermes, OpenClaw, or Clawboo's built-in runtime, and one team can mix them freely, so the researcher, the writer, and the coder can each work on their strongest tool. You follow every card live on the board and in the chat, watch the team graph to see who is doing what, and add a reviewer agent when a second pair of eyes matters. Finished work returns to Boo Zero, which pulls the pieces together and answers you in the chat. Ready-made teams from the marketplace cover marketing squads, dev teams, and research crews, and you can bring an API key from Anthropic, OpenAI, OpenRouter and more, a free local model through Ollama, or your ChatGPT subscription through the Codex CLI. Spend is tracked per team with budget warnings before costs surprise you. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Daily Stock Analysis reads your watchlist every trading day and hands back a decision dashboard, with a score, a trend call, entry and exit levels, risk alerts, and catalysts for each stock. Quotes, K-lines, technical indicators, announcements, news, and fundamentals from several data sources feed a report written by the language model you connect, including Gemini, Claude, OpenAI-compatible endpoints, DeepSeek, or a local Ollama model. The web workspace covers manual analysis, task progress, history, full Markdown reports, backtesting, portfolio tracking, settings, and light and dark themes. Strategy chat answers follow-up questions in multiple turns using 15 built-in strategies, from moving-average crossover to Chan theory and wave theory. Smart import reads a screenshot, CSV, Excel file, or clipboard text to build the watchlist, with code, name, pinyin, and alias autocomplete. Reports are delivered to WeChat Work, Feishu, Telegram, Discord, Slack, or email on a schedule that skips market holidays. A market review summarizes index moves, breadth, and leading sectors. ETF rotation backtests compare annual results and flag data quality problems. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OpenKnowledge turns a folder of markdown files into a workspace where you and an AI agent can write in the same document. The editor feels like a Notion page but saves plain markdown, with a visual mode, a markdown mode, a properties panel for titles and tags, and a file navigator with search and tabs. Ask Claude, Codex, or another harness to draft a recap, and the edit appears beside the chat as you watch. Select any passage and leave a comment, then send all open comments to the agent in one message. A timeline panel lists every change with a before and after diff, so an agent's rewrite is easy to review and undo. Skills Studio covers writing, browsing, and installing agent skills, and it can link one skills folder across Claude, Cursor, Codex, and others. Starter packs set up LLM wikis and second brains, and a graph view shows how wiki links connect pages. Git sync shares a knowledge base with teammates, and rich components like callouts, tabs, and diagrams make specs readable. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

ZeroClaw puts one personal AI agent on every messaging app you already use, answering from your own server with your own model keys. A single instance binds Discord, Telegram, Matrix, Slack, WhatsApp, Signal, email, and webhooks at once, so you can start a conversation on your phone and finish it at your desk without losing context. You choose the brain behind it: Anthropic, OpenAI, a local Ollama model, or any OpenAI-compatible endpoint, with fallback chains that keep the agent answering when one provider has a bad day. The agent acts through tools that run shell commands, drive a browser, call HTTP APIs, and talk to custom MCP servers you plug in. A web dashboard gives you chat, a memory browser, a configuration editor, cron job management, and a tool inspector from any browser. Long-term memory lives in SQLite on your disk with embedding-based recall, so past conversations stay searchable and private. Supervised autonomy is the default posture: medium-risk actions pause for your approval, high-risk actions are blocked outright, and operating system sandboxes plus cryptographic receipts keep every tool call bounded and auditable. Event-driven standard operating procedures react to MQTT messages, webhooks, schedules, and hardware events, and named agents let different personalities guard different channels. Registered as a system service, it stays online around the clock. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT or Apache-2.0 licensed.