Agenta delivers a comprehensive open-source LLMOps workspace that covers the full lifecycle of AI application development — from prompt engineering through production monitoring. The platform supports 15+ model providers including OpenAI, Anthropic, Google Gemini, Mistral, Groq, Together AI, Azure, AWS Bedrock, and self-hosted models via Ollama, enabling teams to switch between providers without code changes. The prompt playground allows side-by-side comparison of different configurations, while the evaluation system offers LLM-as-a-Judge assessment, 20+ pre-built evaluators covering semantic similarity, regex matching, and factual accuracy, plus custom Python evaluators for domain-specific requirements. Teams run evaluations through both the web UI for subject matter experts and the Evaluation SDK for programmatic CI/CD integration. The observability layer captures full trace visibility across complex agentic workflows, flagging quality issues like hallucinations and off-topic responses in real time. Human annotation workflows let domain experts review and annotate LLM outputs, feeding corrections back into the evaluation loop. The architecture supports Chain of Prompts, RAG pipelines, and multi-step agent workflows, integrating with frameworks like LangChain and LlamaIndex. Self-hosting deploys via Docker Compose with Traefik for routing, requiring only a clone, environment configuration, and a single docker compose command. On RepoCloud, deploy Agenta on a dedicated VPS with root SSH access, persistent storage for evaluation datasets and traces, and complete control over model provider credentials, all under the MIT license with no usage restrictions.

PandaDOS is a self-hosted control plane that turns Claude Code and Codex into long-running coding agents you direct through an issue queue from any browser, instead of babysitting a terminal. You file an issue with the outcome and acceptance criteria, and PandaDOS clarifies missing requirements, plans the work, picks the agent, and drives implementation, verification, and delivery in stages. Three approval levels, cautious, balanced, and automatic, decide which actions proceed alone; safe reversible steps continue automatically while destructive, irreversible, production, or secret-related decisions always come back to you. The browser workspace shows the real agent conversation, a native terminal, project files, Git history and diffs, and an execution summary, so you can inspect or intervene at any moment from a phone or laptop. Agents run on local or SSH-connected executor machines inside tmux sessions, and work sharing one repository is serialized while independent projects proceed in parallel without conflicting edits. Modules keep one assigned agent and durable project knowledge, so context from finished issues carries into the next task instead of evaporating when a chat ends. Teams can sign in through Feishu, ask the project manager questions in chat, and receive subscription notifications and approval cards on their phones. 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.

InvoicePlane manages the complete freelance and small-business billing cycle — draft quotes, convert them to invoices, automate recurring charges, collect payments through Stripe and PayPal, and generate EU-compliant eInvoice XML for automated processing by accounting systems. Deployed over 100,000 times across 193 countries, the PHP 8.2+ application on CodeIgniter 3 with MySQL or MariaDB handles everything from first estimate to final receipt. EU-compliant eInvoice generation creates machine-readable XML invoices meeting European Union standards since version 1.6.2. Recurring invoices automate periodic billing with configurable controls that pause generation when previous invoices remain unpaid. Online payment integration lets clients pay directly through Stripe, PayPal with Advanced Credit Cards, and Venmo support. The CRM-like client management module stores contact details, notes, custom fields, and complete transaction history per client. Product and task management modules let you build line-item invoices from reusable product catalogs and project tasks. Customizable PDF templates powered by mPDF support branded invoice layouts with QR codes, while email delivery via PHPMailer handles automated sending with configurable SMTP. A guest portal gives clients read-only access to view and pay their outstanding invoices and quotes. Financial reporting tracks revenue, outstanding balances, and payment history. The multi-language interface supports community translations, and multi-currency handles international invoicing. Deploy via Docker Compose with automatic database migrations. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Send a document, receive a PDF: Gotenberg is a Docker-based, stateless HTTP conversion API trusted in production by thousands of companies and adopted by notable open-source projects. Send files as multipart/form-data, get a PDF back; Chromium, LibreOffice, and fonts are the container's problem, not yours. Headless Chromium handles URLs, HTML templates, and Markdown with pixel-perfect browser rendering: it executes JavaScript, loads web fonts, waits for network idle, a JS expression, or a DOM selector before rendering SPAs, and accepts injected cookies and HTTP headers for authenticated pages. LibreOffice converts 100+ office formats - .docx, .xlsx, .pptx, and legacy formats - with page-range extraction and PDF/A archival conformance. Built-in PDF engines round out the pipeline in every image variant: merge, split, rotate, flatten, encrypt, watermark, stamp, read/write metadata and bookmarks, plus Factur-X/ZUGFeRD e-invoicing and PDF/UA accessibility compliance. Screenshots of URLs and HTML come from the same endpoints. Zero-transfer pipelines stream files directly between S3, MinIO, or GCS presigned URLs and Gotenberg, bypassing your application entirely, and webhooks enable async processing. Statelessness means horizontal scaling is trivial - run as many replicas as your conversion volume demands. Three image variants (full, Chromium-only, LibreOffice-only) trim the footprint to what you actually use.

CRW gives your apps and AI agents a private web data API that scrapes pages, crawls sites, maps links, and searches the web without sending every request to a hosted scraping service. Post a URL to the scrape endpoint and receive clean Markdown, HTML, screenshots, links, or structured JSON shaped by a schema you supply. Start a crawl when a whole section matters, then poll for progress while CRW walks pages asynchronously and returns the collected content in one job. Use map first to discover the URLs on a site before spending effort extracting pages you do not need. Connect agent tools through the MCP endpoint so assistants can search, scrape, and crawl from the same self-hosted service your applications call. Add browser rendering when JavaScript-heavy pages hide content from a plain HTTP fetch, and keep simpler pages on the fast lightweight path. Protect a public deployment with Bearer token authentication, your own reverse proxy, logging, and rate limits, or keep the service inside a private network for internal tools. Run one Docker container for the core API, or use the Compose stack when you want bundled search and rendering sidecars beside it. 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.

Ollaya serves decision models that answer typed questions about a message, ticket, or document with calibrated probabilities, through a self-hosted API shaped like the hosted service it can replace. Send a state, which can be an email, a support ticket, or any JSON, plus typed choice, score, and yes or no questions, and the model answers in one forward pass in milliseconds without generating text. Pull models by name the way Ollama users already know, with run, list, ps, show, copy, and remove commands managing the local store. Downloads verify every layer against its sha256 digest, resume when interrupted, and share blobs between models so storage stays lean. Existing TypeSafe code keeps working by changing one environment variable, because the /v1/systemone and /v1/decisions endpoints are wire-identical and the official SDK sends its key the same way. The native /api adds routing information and timings, model loading and unloading, and streamed pull progress for your own tooling. Put it to work triaging inboxes, routing requests to the right model or team, screening prompts for injection and jailbreak attempts, or replacing per-token LLM classification calls with a local answer. Agents reach the same engine through the bundled MCP server, and LiteLLM, LangChain, DSPy, LlamaIndex, n8n, and Dify connect through their existing integrations. 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.

Waiting for the right moment to buy usually means refreshing product pages for weeks, so PriceBuddy does the refreshing for you and speaks up when the price is right. Paste a product URL and it fetches the details and price, then rechecks on a global schedule or a per-product interval from every 5 minutes to every 24 hours. Stores are scraped with CSS selectors, regular expressions, or JSONPath, a headless browser covers JavaScript-heavy shops, and an optional AI provider (OpenAI, Anthropic, Gemini, or local Ollama) can recover missing prices or repair broken selectors. Attach several URLs to one product to compare retailers or marketplace listings, with in-stock, pre-order, and discontinued states shown beside each source. Unit pricing reveals the real cost per tablet or bag when multi-packs distort shelf prices, while history charts show minimum, maximum, and average over time. Alerts fire on a target price, a drop threshold, or a back-in-stock event and arrive by in-app notice, email, Pushover, Gotify, Apprise, Telegram, Discord webhook, or ntfy. Tags sort products into draggable dashboard groups, with optional smart sections for what to buy now, recent drops, and failed checks. Each user keeps separate products and settings, a REST API with scoped tokens serves your scripts, and a Chrome and Edge extension tracks items from the page you are viewing. 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 15,500 GitHub stars and over 1,100 forks, Plandex delivers a terminal-based AI coding agent purpose-built for the complex, multi-file tasks that overwhelm single-file AI assistants. The Go-powered server maintains a cumulative diff review sandbox that quarantines all AI-generated changes from your project files until you explicitly approve them — enabling 20-file refactors where you cherry-pick good changes and reject bad ones without touching git. A 2M token effective context window loads only what each step requires, while tree-sitter project maps index repositories exceeding 20M tokens across 30+ programming languages, providing structural awareness of class hierarchies, function signatures, and import graphs without burning tokens on full file content. The configurable model pack system assigns different models to different roles — Claude for planning, GPT for coding, Gemini for summarization — supporting Anthropic, OpenAI, Google, OpenRouter, Azure OpenAI, AWS Bedrock, DeepSeek, Perplexity, and Ollama for local models. Full auto mode handles end-to-end autonomous workflows including high-level planning, context loading, implementation, terminal command execution, and automated debugging of both terminal and browser applications. The interactive REPL provides fuzzy auto-complete, version-controlled sandbox branching, rewind to any previous point, and Git integration for commit message generation. The Plandex Server exposes 60+ REST API endpoints for programmatic orchestration across organizations, projects, plans, and branches. Deploy via Docker Compose for self-hosted operation with your own API keys. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Schools, training companies, and HR teams use Chamilo LMS to publish courses, guide learners step by step, and prove completion with grades, badges, and certificates. Teachers build courses from documents, videos, and 360 media, then arrange them into learning paths that unlock in sequence and track every learner's progress. Quizzes offer more than twenty question types with randomized draws, time limits, and adaptive testing, while assignments accept submissions, support co-grading, and plug into plagiarism checks. The gradebook turns scores into certificates with QR codes, and skills frameworks record competency levels as learners advance. Sessions let one course run for many cohorts on different calendars, attendance tools handle sign-in and Qualiopi style reporting, and the course catalogue can even sell enrolments through its e-commerce module. Discussion forums, live chat, surveys, and videoconference integrations keep classes social, and SCORM, QTI, LTI, and xAPI support means existing content and external tools slot in without conversion projects. Administrators import users in bulk, connect LDAP or OAuth2 logins, and export personal data for GDPR requests; learners get all of it in more than sixty languages, including right-to-left scripts. 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.

Gaining over 71,000 GitHub stars as one of the fastest-rising knowledge management platforms, AFFiNE merges the document editing capabilities of Notion, the infinite canvas of Miro, and the structured data of Airtable into a single cohesive workspace. The block-based editor built on the custom BlockSuite framework supports rich text, code blocks, embeds, tables, kanban boards, and database views with drag-and-drop composition. The whiteboard mode provides an infinite canvas where users can freely mix documents, sticky notes, shapes, connectors, and hand-drawn elements, enabling visual thinking alongside structured note-taking. Real-time collaboration allows multiple users to edit documents and whiteboards simultaneously with cursor presence, comment threads, and version history. The local-first architecture stores all data on your device by default using CRDT-based synchronization, ensuring offline access and data sovereignty, with optional cloud sync for cross-device availability. Workspaces organize content into hierarchical page trees with full-text search, favorites, tags, and trash management. The platform supports Markdown import and export, PDF export, and HTML export for interoperability. AI features powered by configurable LLM providers enable writing assistance, summarization, translation, and content generation directly within documents. The theming system supports light and dark modes with customizable accent colors. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Licensed under MIT with an open-source self-hosted edition.

OmniRoute is an AI gateway, aggregating 338 LLM providers including OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Kimi, MiniMax, and GLM into a single OpenAI-compatible endpoint at localhost:20128. The gateway catalogs over 1,200 models across 90 free-tier providers and 40 free-forever providers, automatically rotating through tier-1, tier-2, and tier-3 fallback chains when any provider exhausts its quota or returns errors. RTK plus Caveman stacked token compression reduces eligible context by 15 to 95 percent before forwarding requests, cutting API costs dramatically without degrading output quality. OmniRoute exposes its full routing engine through a built-in MCP server with 104 tools across 31 scopes over stdio, HTTP, and SSE transports, plus an A2A protocol server with six autonomous agent skills and JSON-RPC 2.0 streaming. The gateway integrates directly with Claude Code, Cursor, GitHub Copilot, Codex CLI, OpenCode, and Cline through standard base-URL configuration. Seventeen routing strategies include latency-optimized, cost-minimized, and auto-scoring modes that evaluate candidates on success rate, context fit, model fitness, quota state, and circuit-breaker health. The Next.js dashboard provides real-time provider status, usage analytics, combo chain configuration, and model catalog browsing via a responsive PWA. 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 27,000 GitHub stars and 349 releases shipping multiple times per week, Huly replaces four separate SaaS subscriptions — Linear for issue tracking, Notion for documents, Slack for team chat, and Motion for time-blocking — with a single self-hosted platform that charges nothing per seat. The issue tracker provides projects, sprints, roadmaps, custom workflows, and Kanban views with bi-directional GitHub and GitLab synchronization that keeps issues and pull requests in lockstep across both systems. Collaborative documents use CRDT-based real-time editing for wikis, meeting notes, and technical specs with nested page hierarchies and rich embedding. Team messaging delivers channels, direct messages, threaded conversations, reactions, and pinned messages in a Slack-equivalent interface that lives alongside your project context. The time-blocking planner schedules tasks into calendar slots with drag-and-drop, integrating directly with your issue backlog so nothing falls through cracks. A virtual office module provides audio and video rooms for standups and pair programming with external guest access. HR features handle team management, office hours, and PTO tracking. The architecture runs 30+ microservices on CockroachDB for ACID-compliant storage, Elasticsearch for full-text search, MinIO for file attachments, and Redpanda for event streaming. Desktop apps ship for macOS, Windows, and Linux alongside mobile apps for iOS and Android. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. EPL-2.0 licensed.

Running a VPN for family, friends, or a small team usually means babysitting servers one SSH session at a time, and Mistgate replaces that with one panel that keeps the whole fleet configured. Add a server from the browser by typing its address and root password: the panel pins the host key, checks the host, opens the ports, and installs the signed node agent for you. Each person gets one subscription link that their app turns into the server list, or a personal AmneziaVPN key per device, so a lost phone can be revoked without touching anyone else. Groups decide which protocol profiles a person receives, while per-user traffic quotas, expiry dates, device limits, and per-device speed limits keep sharing fair. Hysteria2 brings QUIC-based speed with port hopping, obfuscation, and certificate options; VLESS REALITY and AmneziaWG 2.0 and 3.1 cover networks where one protocol gets blocked, and Cloudflare WARP can serve as the exit for all three. Every five minutes the panel connects to each server the way a real client app would, a doctor on every node runs host checks with safe fixes, and alerts reach you on Telegram before your users notice. The public address shows strangers a decoy site while the admin hides behind a secret path, and encrypted backups go to your Cloudflare R2 bucket on a schedule. 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.

Turn any server into a high-speed media vault and file-sharing hub with Chibisafe, a self-hosted upload platform built for chunked large-file transfers, organized albums, and instant desktop screenshot workflows. Users drag and drop photos, videos, archives, or documents into the browser uploader, where multi-gigabyte files are automatically split into chunks to prevent network drops from ruining an active transfer. Uploaded media renders inside a responsive masonry or list gallery with in-browser video and audio previews, custom file tags, search filtering, and one-click shareable links. Organizers group related uploads into folders and public albums, mark sensitive collections with content warnings before loading, and publish syntax-highlighted text snippets or code gists alongside shortened URLs. Desktop and mobile power users connect ShareX, iOS Shortcuts, macOS quick actions, fswatch folder monitors, or the companion browser extension using personal API keys that route captures straight into designated albums. Instance administrators toggle between public, open-registration, and invite-only modes, enforce per-user storage quotas, offload storage to AWS S3, Backblaze B2, MinIO, or Wasabi via signed URLs, and customize rate limits or allowed extensions directly from the web settings panel. 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 34,000 GitHub stars and backing from a well-funded engineering team, Tailscale has fundamentally simplified how developers and system administrators think about secure networking. The client daemon establishes WireGuard tunnels directly between devices using sophisticated NAT traversal techniques, achieving direct peer-to-peer connections in the vast majority of network configurations without requiring port forwarding, firewall rules, or VPN concentrators. When direct connections prove impossible due to restrictive network environments, DERP relay servers provide encrypted fallback paths. MagicDNS assigns human-readable hostnames to every device on the network, eliminating the need to remember IP addresses across a tailnet. Subnet routing allows nodes to advertise access to entire local networks, enabling remote access to office resources, home labs, or cloud VPCs through a single gateway node. Exit node functionality routes all internet traffic through a designated device for privacy protection or geographic flexibility. Access control lists define granular policies for which devices and users can communicate with which services, enforced cryptographically at the network layer. The authentication layer integrates with identity providers including Google, Microsoft, GitHub, Apple, and OIDC-compliant systems for single sign-on access. Taildrop enables direct encrypted file transfers between devices without cloud intermediaries. The tailscale CLI provides complete network management from the terminal including status monitoring, route advertisement, and node configuration. Running Tailscale on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console provides a permanent, always-on node in your mesh network. BSD-3-Clause licensed with an active open-source community.

Used by millions of users at thousands of organizations worldwide and holding 29,000+ GitHub stars, Redash is the most established open-source SQL-first business intelligence tool — enabling anyone from analysts to executives to query databases, visualize results, and share dashboards without writing a single line of application code. The browser-based query editor supports SQL and NoSQL with schema browsing, auto-complete, query snippets, and parameterized queries that turn static reports into interactive data applications. Native connectors span 35+ data sources including PostgreSQL, MySQL, Amazon Redshift, Google BigQuery, Snowflake, ClickHouse, MongoDB, Elasticsearch, Databricks, Apache Presto, Microsoft SQL Server, and REST APIs — with an extensible data source API for custom integrations. Visualization types cover line, bar, area, pie, scatter, box plot, funnel, cohort, sankey, sunburst, choropleth map, and pivot tables, all draggable onto shared dashboards with cross-filtering parameters. Scheduled refreshes automatically update query results at configurable intervals, while threshold-based alerts notify teams via email, Slack, or webhook when metrics cross defined boundaries. SAML and Google OAuth SSO integration, role-based access control, API key management, and query-level permissions ensure enterprise-grade security for sensitive datasets. The self-hosted stack deploys via Docker Compose with PostgreSQL for metadata storage, Redis for job queuing, and Celery workers for background task execution. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD 2-Clause licensed.

Your team's group chat could have a colleague who has read every email, ticket, and document, remembers all of it, and answers in seconds; MindRoom puts AI agents like that into your chat rooms as full participants. Each agent is a real user on the open Matrix protocol, so you talk to it in MindRoom Chat on web or mobile, in any other Matrix client, or through bridges in Slack, Telegram, WhatsApp, and Discord. Give every agent its own model: a local model for private rooms, a frontier model for hard coding problems, and switch per room or thread whenever the work changes. Agents connect to more than 100 tools, including Gmail, calendars, GitHub, Google Drive, Home Assistant, and any MCP server, and they search your own documents and knowledge bases for answers with sources. Memory persists across conversations and platforms, so an agent remembers people, preferences, and project context months later and can turn repeated work into reusable skills. Before an agent sends an email or runs a command, an approval card shows exactly what will happen; you tap once to allow it, and sandboxed workers keep executed code away from your credentials. Schedule morning briefings, silent inbox checks, and recurring digests in plain language, or wake an agent from any other system with a single HTTP request. 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.

The utilities engineers otherwise scatter across a dozen ad-laden websites - 80+ of them - live together in IT-Tools, one fast, polished web app. Crypto covers JWT decoding, MD5 through SHA-512 hashing, HMAC and bcrypt generation, RSA key pairs, and password strength analysis. Converters handle JSON to CSV, YAML, and TOML, Base64 files, URL encoding, HTML entities, color formats, and Docker run commands to Compose files. Generators produce UUIDv4, ULID, BIP39 mnemonics, QR codes (including Wi-Fi QR), and tokens; text tools include a regex tester, diff viewer, slug and case converters; web utilities parse URLs and user agents, look up HTTP status codes and MIME types, and inspect Open Graph metadata; plus a cron parser, chmod calculator, and more. The privacy argument is the point: JWTs contain user IDs, hashes derive from passwords, JSON dumps hold PII - exactly the inputs you least want a third-party utility site to log. IT-Tools is a frontend-only static bundle (Vue/TypeScript, GPL-3.0, 39k+ GitHub stars) served by Nginx in one container, so everything runs client-side on your infrastructure with nothing transmitted anywhere. New tools ship roughly monthly, and a scaffolding script makes adding custom ones straightforward.