Respan Gateway is a single-binary LLM gateway that lets the SDK you already use call any AI model from any provider, translating between OpenAI, Anthropic, and Gemini API formats on the way through. Point an OpenAI, Anthropic, or Gemini client at it and you reach chat models on sixteen providers, plus any OpenAI-compatible endpoint of your own, with streaming, tools, images, and reasoning translated. Traffic control works the way operators think: name a route, send it to the cheapest or fastest provider, retry on failure, fall back to a second vendor, or hedge a slow call by racing another provider. Models that never had tools get them anyway, because MCP servers and built-in search, browsing, code, document, and memory tools run inside ordinary chat requests behind the gateway. Realtime voice crosses vendors too, with an OpenAI Realtime client able to talk to Gemini Live, alongside images, speech, transcription, embeddings, and video through one endpoint. A live request log in the web UI shows the client key, model, provider, status, tokens, cost, and latency of every call, so runaway agents and surprise bills are visible immediately. Everything is a plugin on one public Rust API, from routing and pricing to tracing, with examples for guardrails, PII masking, and billing. One TOML file configures keys, providers, routes, and tools, validates before it starts, and reloads on signal. 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.

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.

GoatCounter delivers meaningful web traffic insights — pageviews, referrers, browsers, screen sizes, country-level geolocation — without setting a single cookie, without collecting personal data, and without forcing GDPR consent banners on your visitors. Written entirely in Go and distributed as a single compiled binary consuming roughly 25MB of RAM, it adds just 3.5KB to your pages via the tracking script, with a JavaScript-free tracking pixel alternative for sites that avoid scripts entirely, plus backend middleware integration and log file import for server-side collection. The dashboard displays pageview counts per path with hourly resolution, referrer sources grouped by domain with full URL on hover, browser and OS version breakdowns, screen size distributions, and country-level location data derived from IP addresses that are immediately discarded after geolocation. Campaign tracking supports UTM parameters and custom data attributes. A public stats option exposes your dashboard at a shareable URL for build-in-public transparency. SQLite serves as the default database requiring zero administration, while PostgreSQL handles higher-traffic deployments with multi-site setups. Built-in ACME and TLS certificate management eliminates reverse proxy requirements for HTTPS — no Nginx or Caddy needed. The REST API provides programmatic access to all analytics data. Deploy as a single binary, via Docker with the official arp242/goatcounter image, or through native packages. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. EUPL-1.2 licensed.

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.

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.

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.

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.

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.

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.

Dify turns the notoriously complex process of building production-grade AI applications into a visual drag-and-drop experience that teams can actually ship and maintain. With over 87,000 GitHub stars and backing from prominent investors, the platform has become the go-to open-source LLMOps solution for organizations that refuse to be locked into proprietary AI stacks. The visual workflow canvas lets developers wire together LLM calls, conditional logic, iteration loops, tool invocations, and human-in-the-loop checkpoints without writing boilerplate integration code. Its RAG pipeline engine handles the full document lifecycle from ingestion of PDFs, Word documents, and HTML through configurable chunking strategies, embedding with models from OpenAI or open-source alternatives, vector storage in Weaviate, Qdrant, Pinecone, or pgvector, and hybrid semantic-plus-keyword retrieval with citation tracking. Dify integrates with hundreds of model providers including OpenAI GPT-4o, Anthropic Claude, Google Gemini, Mistral, Llama, and any OpenAI-compatible endpoint like Ollama for fully local inference. The agent framework supports both ReAct and function-calling strategies with 50-plus built-in tools spanning Google Search, DALL-E, Stable Diffusion, WolframAlpha, and custom API definitions. Published apps can be deployed as hosted web interfaces, embedded chat widgets, REST API endpoints, or MCP-compatible tools. Enterprise features include role-based access control, SSO integration, and audit logging. A built-in marketplace enables teams to share and reuse model providers, tools, and workflow templates across projects. 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 an open-source community edition.

With nearly 12,000 GitHub stars and a lineage tracing back to Sphinx Search, Manticore Search is the C++ search database that delivers the full-text, vector, and hybrid search capabilities of Elasticsearch at a fraction of the resource cost — starting in under a second and consuming just 40MB RAM for an empty instance. The SQL-first interface speaks the MySQL wire protocol, meaning mysql client, MySQL Workbench, and any MySQL-compatible driver connects natively without adapters, while the HTTP JSON API provides RESTful access for modern applications. Over 20 full-text operators handle proximity search, quorum matching, field-start and field-end constraints, MAYBE operators, and regex patterns, backed by stemming, lemmatization, stopwords, synonyms, wordforms, and advanced morphology in 70+ languages. Vector search with HNSW indexing enables semantic similarity queries, and hybrid mode combines keyword relevance with vector distance in a single ranked result set using a cost-based query optimizer. Real-time indexing delivers sub-second document availability after insert, sharded tables distribute data across nodes, and Galera-based synchronous replication ensures high availability. Conversational search via CREATE CHAT MODEL and CALL CHAT integrates LLM-backed responses with KNN retrieval and conversation history directly inside the database. Client libraries ship for PHP, Python, JavaScript, TypeScript, Java, Go, Rust, and Elixir. Columnar storage via the Manticore Columnar Library handles analytical workloads on large datasets. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPLv3 licensed.

With over 77,000 GitHub stars, Crawl4AI is the most-starred open-source web crawler on GitHub and the go-to tool for converting the web into AI-ready data. Built on Python and Playwright, it transforms any website into clean Markdown with headings, tables, code blocks, and citation hints optimized for LLM ingestion, or extracts structured JSON via CSS selectors, XPath expressions, or direct LLM-based schema extraction through OpenAI, Anthropic, and Ollama providers. The self-hosted Docker server exposes a REST API on port 11235 with endpoints for crawling, streaming results, screenshots, PDF generation, JavaScript execution, and LLM-powered extraction. Version 0.9.x introduced secure-by-default operation with mandatory JWT authentication, strict request validation, declarative hooks replacing inline code, and bounded job queues. Adaptive crawling uses information foraging algorithms to determine when sufficient data has been gathered, while deep crawl mode traverses link graphs intelligently. The async browser pool manages concurrent sessions with stealth plugins, proxy rotation, custom headers, and session persistence for authenticated scraping. A built-in MCP server enables direct integration with Claude, ChatGPT, and Cursor for AI-driven web research workflows. Content filtering applies BM25 and TF-IDF relevance scoring to extract only pertinent sections from noisy pages. 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.

Web analytics tools ignore native mobile, desktop, and game apps; Aptabase was built for exactly those. If Firebase Analytics would force a privacy-policy footnote you don't want to write, this is the alternative - session-based metrics with no cookies, no IDFA or GAID, no device fingerprinting, and a daily-rotated salt that makes cross-day re-identification mathematically impossible. That design means GDPR, CCPA, and PECR compliance out of the box and "Data Not Collected" App Store privacy labels without ATT prompts. The SDK coverage is the widest in its category: eleven first-party libraries spanning Swift, Kotlin, Flutter, React Native, Tauri, Electron, .NET MAUI, NativeScript, Unity, Unreal Engine, and JavaScript for web - each MIT-licensed, following platform conventions, and accepting a custom host parameter that points at your instance. Integration is minutes: initialize with an app key, call trackEvent with optional properties, and the dashboard shows sessions, events, app versions, OS breakdowns, and country-level geography. The self-hosted stack is a .NET server over PostgreSQL for metadata and ClickHouse for high-volume event ingestion, giving cloud-parity features under an AGPL license. For indie iOS/Android apps, Electron and Tauri tools, and Unity or Unreal games, it replaces Firebase without the Google entanglement.

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.