magpie
Point every coding agent and chat client at one self-hosted gateway, then choose which model answers from a single browser console. Add providers by preset or custom OpenAI-compatible URL, or sign in with the subscriptions you already pay for. Routing groups bundle several models into one name and move to the next member when a quota runs out, so the calling agent never sees the error. Create a gateway key per client, cap each with daily token or cost budgets, restrict its models, and watch usage counted separately. The Usage pages chart tokens, cost, request counts, cache hit rate, and a yearly heatmap, split by model, provider, or agent, with CSV export. A Routing view replays how each request was routed, with timing for masking, connecting, and the vendor. Masking swaps passwords, API keys, and tokens for placeholders before a prompt leaves your server and restores them in the answer. The browser page is protected by a key you set at launch. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Backstage
Adopted by over 3,400 companies and backed by 34,000 GitHub stars, Backstage is the open-source developer portal framework created by Spotify and now hosted by the Cloud Native Computing Foundation. The centralized Software Catalog registers every service, library, data pipeline, website, and ML model in your organization using YAML metadata files stored alongside code in GitHub, GitHub Enterprise, or GitLab, tracking ownership, lifecycle status, and dependency relationships across your entire ecosystem. Software Templates provide self-service infrastructure provisioning where developers fill out a form and Backstage automatically scaffolds new repositories, CI/CD pipelines, and cloud resources following your organization's standardized best practices. TechDocs renders Markdown documentation directly alongside the services it describes using a docs-like-code approach powered by MkDocs, with the TechDocs Addon Framework for extending the reading experience. The Search Platform indexes content across the catalog, TechDocs, Confluence, and Stack Overflow through configurable search backends. Kubernetes monitoring built specifically for service owners rather than cluster admins displays pod health, logs, and deployment status across any cloud provider or managed Kubernetes service. The plugin ecosystem includes over 230 open-source integrations covering CI/CD systems like GitHub Actions and GitLab Pipelines, monitoring platforms like Datadog and Grafana, cloud providers including AWS and Azure, plus specialized plugins for security scanning, cost management, API documentation, PagerDuty incident management, and Lighthouse website auditing. 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.
New API
New API is a Go-powered LLM gateway that funnels over 40 AI providers, from OpenAI and Anthropic to Google Gemini, Azure, AWS Bedrock, DeepSeek, and Mistral, through a single OpenAI-compatible endpoint with intelligent routing and enterprise cost controls. Bidirectional format conversion translates between OpenAI Chat Completions, Claude Messages, and Gemini GenerateContent APIs transparently, so clients call any provider using their preferred format while the gateway handles the rest. Routing logic supports weighted random channel selection, priority-based failover, and automatic retry on provider errors to maximize uptime. The React admin dashboard shows usage charts, token consumption tracking, per-model cost breakdowns, and real-time request monitoring. Multi-tenant architecture includes three role levels, token-based authentication, per-user quota management, and a three-phase billing system with tiered pricing via a custom expression language. Multimodal support covers text completion, vision, embeddings, text-to-speech, speech-to-text, image generation, and creative task providers like Midjourney-Proxy and Suno-API. The interface ships in five languages including English, Chinese, Japanese, and French. Docker deployment runs with SQLite or MySQL for persistence. 45,000+ GitHub stars. AGPL-3.0 licensed.
CCX
CCX gives every coding agent and chat client one stable address, and the real model providers can come and go behind it. Point Claude Code, Codex, or any SDK at the gateway and it forwards requests to the first healthy channel in a failover sequence, then moves down the list when an upstream returns errors. Each channel carries its own keys, model allowlist, proxy, and custom headers, and the Add Channel dialog detects a base URL and keys from pasted text. The admin console tracks requests, availability, tokens, and cost over ranges from one hour to a year, with a chart per model and a live success rate beside each channel. Drag a channel to change its priority, park it in the standby pool, or open its log to see the status, timing, and key of every call. Separate tabs cover Claude Messages, OpenAI Chat, Images, Vectors, Codex, and Gemini, and a dark theme and language switch are built in. Access is guarded by a proxy key and an optional admin key. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Respan Gateway
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.
Dockhand
Dockhand is a Docker management platforms, offering a modern alternative to Portainer with free OIDC SSO and vulnerability scanning that competitors gate behind paid tiers. Real-time container management provides start, stop, restart, and remove operations with live resource monitoring across CPU, memory, and network usage on a dashboard with real-time metrics. The visual Docker Compose editor enables stack creation and modification with syntax highlighting, while Git integration deploys stacks directly from repositories with webhooks and auto-sync for GitOps workflows. Vulnerability scanning powered by Grype and Trivy analyzes container images against CVE databases, with configurable auto-update scheduling that can trigger updates based on vulnerability severity criteria. The Hawser Go agent enables management of remote Docker hosts in Standard mode for LAN environments or Edge mode using outbound WebSocket connections for hosts behind NAT, firewalls, or dynamic IPs without exposing inbound ports. Interactive terminal sessions provide shell access into running containers, while the file browser enables uploading, downloading, and editing files directly within containers. Image management includes registry browsing, pull operations, and layer inspection alongside network and volume administration. The security-focused architecture builds its own OS layer from scratch using Wolfi packages via apko with every package explicitly declared. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSL 1.1 licensed, converting to Apache 2.0 in 2029.
Dockge
Created by the developer behind Uptime Kuma and carrying over 23,000 GitHub stars, Dockge brings the same clean, reactive design philosophy to Docker Compose stack management with a web interface that makes Portainer's compose handling feel like editing YAML in a terminal over SSH. The interactive editor provides syntax highlighting, inline validation, and a live preview of your compose.yaml files while keeping every stack stored as a standard file on disk in /opt/stacks by default, meaning you can seamlessly switch between the web UI and the docker compose CLI without lock-in or proprietary database formats. Real-time WebSocket updates stream pull progress, container start/stop transitions, and build output directly to the browser with no polling delays. The built-in web terminal opens a shell session inside any running container for quick debugging, while the docker-run-to-compose converter transforms single-container run commands into proper compose.yaml definitions with one click. Multi-agent support introduced in version 1.4.0 connects multiple Docker hosts to a single Dockge dashboard, enabling centralized management of stacks distributed across different servers. Image update detection shows which stacks have newer versions available, and one-click updates pull the latest images and recreate containers without manual intervention. The stack is a single Docker container running on Node.js with Socket.IO for reactivity and stores no external database. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Kite
With nearly 3,000 GitHub stars and 14 releases since its June 2025 launch, Kite delivers a lightweight Kubernetes dashboard that replaces the fragmented workflow of switching between kubectl, Lens, and separate monitoring tools with a unified multi-cluster management platform. The dashboard automatically discovers clusters from kubeconfig files and supports independent Prometheus configurations per cluster, providing real-time CPU, memory, and network charts alongside live pod log streaming with filtering and search. A built-in web terminal opens shells directly into pods and nodes without kubectl port-forward, while the Monaco-based YAML editor offers syntax highlighting and validation for in-place resource editing. The integrated AI agent, powered by OpenAI or Anthropic models via native Go SDK integrations, translates natural language into precise client-go API calls — querying cluster health, analyzing pod logs, scaling deployments, patching resources, and cleaning up failed jobs — all operating strictly within the logged-in user's RBAC permissions. Enterprise governance includes OAuth 2.0 single sign-on, multi-factor authentication, FIDO2 passkeys, granular role-based access control with per-namespace permissions, and comprehensive audit logging. Helm chart management enables browsing, installing, and upgrading releases directly from the UI, while the Docker registry integration provides quick image tag selection. Deploy via a single Docker container with SQLite or use the official OCI Helm chart with PostgreSQL or MySQL for production. 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.
Tugtainer
Tugtainer delivers a visual command center for Docker environments that automates container image updates, monitors registry releases, and manages application lifecycles across multiple servers without command-line intervention. System administrators can inspect running containers across all connected hosts, trigger immediate image pulls, and configure automated cron schedules for recurring health and registry checks. Flexible update policies allow teams to flag production databases as notification-only while automatically updating stateless web applications whenever new image tags publish. When updating linked services, the platform analyzes Docker Compose project definitions and custom dependency labels to stop and restart containers in strict dependency order, preventing broken network links and orphaned volume mounts. Administrators can authenticate private container registries, browse image layers and tags, and view real-time container log streams directly within the browser console. Automated pruning jobs continuously reclaim server disk space by deleting obsolete, untagged images and dangling build layers after successful deployments. Multi-channel alerting integrates with over fifty notification providers, delivering real-time update summaries and error warnings directly to Discord, Telegram, Slack, and email webhooks. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Antirion
Your apps keep using the OpenAI SDK while Antirion, a self-hosted AI gateway, decides which provider answers, what each team may spend, and what gets logged. Clients speak the OpenAI, Anthropic, Gemini, or Bedrock APIs, and Antirion translates between them, so a Claude deployment can answer an OpenAI-style call, streams included. Add providers such as Amazon Bedrock, Vertex AI, Mistral, Groq, DeepSeek, or a vLLM server, then publish them as named Models. Routing rules send traffic by team or project with fallback chains, weighted splits, least-cost or least-latency targets, retries, hedging, and circuit breakers. Budgets and rate limits in dollars or tokens apply per organization, team, project, and key, with projections and alerts before money runs out. Guardrails check for personal data, secrets, keywords, and regex matches, then block, redact, flag, or divert. Exact and semantic caching answers repeated prompts without calling a provider. The request log records every attempt, route, token count, cost, and guardrail verdict, with Prometheus metrics and OTLP traces. An MCP gateway and A2A proxy put tools and agents behind the same keys. Sign in with OIDC, SAML, or GitHub, provision users with SCIM, and review every change in the audit log. Changes you choose can require a change request or a second person's approval, and the Playground sends requests from the console. 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.
GPT Load
GPT Load has become the go-to self-hosted AI gateway for teams managing multiple LLM provider credentials behind a single URL. The Go-built proxy transparently preserves native API formats for OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, and Google Gemini — applications swap one base URL and keep their existing SDK integration untouched. Twenty built-in channels cover official APIs (OpenAI, Anthropic, Gemini, xAI), cloud platforms (Azure OpenAI, AWS Bedrock, Google Vertex AI), model services (DeepSeek, Moonshot AI, SiliconFlow, Zhipu AI, Alibaba Cloud, Volcengine, OpenRouter, Groq), and subscription accounts (Codex, Claude, Antigravity, Grok) using the same credential management, scheduling, and health system. The intelligent key pool rotates among valid credentials using atomic counters for fair high-concurrency distribution, automatically blacklists failing keys after configurable thresholds, and recovers them via scheduled health checks — all transparent to clients. Weighted load balancing distributes traffic across multiple upstream endpoints while per-credential proxies route individual keys through different egress paths. The Vue 3 management dashboard provides real-time statistics, group configuration, key testing, request logs with full debugging context, per-model cost estimates, and route inspection. Docker deployment exposes the management interface and proxy on port 3001 with SQLite by default, MySQL or PostgreSQL optional, and Redis for distributed leader-follower cluster scaling. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Archestra
Archestra delivers the enterprise AI infrastructure layer that organizations need when managing multiple LLM providers, MCP servers, and AI agents across teams becomes unmanageable. The LLM gateway routes requests across Anthropic, OpenAI, Azure, Bedrock, and DeepSeek with virtual API keys, per-team cost limits, and dynamic model routing — giving every developer one token for Claude Code, Cursor, or Codex while finance tracks spend per department. The MCP gateway authenticates tool calls with OAuth 2.1 and On-Behalf-Of tokens so each tool executes as the calling user, not a shared service account, eliminating credential sprawl. The private MCP registry lets teams publish custom tool servers with approval flows promoting servers from dev through staging to production, each environment maintaining its own credentials and network egress policies. The Kubernetes operator manages MCP server lifecycle — deploying containers, scaling, health-checking, and routing gateway traffic to local servers automatically. The agent runtime supports scheduled triggers, email and webhook invocations, sub-agent delegation, reusable skills, and sandboxed code execution with a K8s-native filesystem. Deterministic guardrails including Dual-LLM verification and Lethal Trifecta protections prevent dangerous tool calls before execution. Built-in OpenTelemetry traces and Prometheus metrics provide full observability without additional tooling. Docker deployment exposes the Admin UI on port 3000 and API on port 9000 with a single command. 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.
Runtipi
Runtipi makes any Linux server a personal app platform where installing services like Plex, Nextcloud, or Home Assistant takes a single click from a curated store of 265+ applications. With 9,500+ GitHub stars and 50 contributors, the React frontend backed by NestJS orchestrates Docker Compose projects for each installed app, automatically generating environment files, compose configurations, and Traefik reverse proxy labels for domain routing and SSL certificate provisioning via Let's Encrypt. The integrated Traefik reverse proxy handles all incoming traffic routing, HTTPS termination, and forward-auth protection for securing applications behind Runtipi's authentication layer without manual configuration. One-click updates notify administrators of new app versions and apply container image upgrades with automatic pre-update backup creation, while the restore feature rolls back application data to any saved snapshot. Custom app stores extend the ecosystem through Git repositories following the Runtipi app definition format, enabling organizations and communities to maintain private catalogs alongside the official store. The Docker Compose override system preserves user customizations across updates, allowing advanced modifications without losing changes. Architecture-aware filtering detects ARM64 or x86 platforms and displays only compatible applications. All apps deploy as standard Docker containers, and compose files can be exported for independent operation without lock-in. 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.
Wealthfolio
Wealthfolio is a portfolio tracker offering a complete wealth management platform where financial data never leaves your infrastructure. Built on Rust with an Axum HTTP server, Diesel ORM, and SQLite storage, paired with a React 19 and Vite frontend, version 3.6 tracks stocks, ETFs, mutual funds, crypto, and cash savings across unlimited accounts with unified holdings. The performance engine calculates time-weighted returns (TWR), internal rate of return (IRR), volatility, maximum drawdown, and benchmark comparisons against the S&P 500 and custom indices, scoped per-account or across the entire portfolio. Net worth tracking monitors assets including real estate, vehicles, collectibles, and precious metals alongside liabilities, with stale-valuation warnings for items not updated in 90+ days. The spending module categorizes transactions automatically, supports multi-currency credit cards, builds budgets with monthly targets and rollovers, and generates narrative insights. A built-in AI assistant answers portfolio questions, suggests asset classifications, and imports transactions conversationally — bring your own API key from OpenAI, Anthropic, or use local LLMs. The addon system provides sandboxed extensions with granular permission declarations across 16 capability domains. CSV import maps broker exports with per-broker recipes for Interactive Brokers, Schwab, Fidelity, and dozens more. Market data streams from Yahoo Finance with automatic currency conversion. 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.
Ferro Labs AI Gateway
Thirty model providers, one OpenAI-compatible endpoint: Ferro Labs AI Gateway routes every request from your applications to the provider that should answer. Eight routing strategies cover fallback chains, weighted load balancing, lowest latency, lowest cost, content-based rules, A/B tests, and conditional targets, each with retries and circuit breakers. Guardrail plugins filter blocked words, redact personal data, scan for leaked secrets, block prompt injection, validate response schemas, and enforce rate limits and per-key spend budgets. Identical prompts can come back from a response cache, and tool servers connect through MCP so the gateway can run the tool-call loop itself. The console opens with a getting-started checklist, then charts traffic, token throughput, latency percentiles, and cost by model. Providers, routing targets, and plugins each get their own page, a playground sends test chats through the real routing path, and request logs plus an audit trail record who changed what. Scoped admin and read-only keys give every operator separate access, and configuration history allows a rollback. OpenTelemetry traces and Prometheus metrics feed existing dashboards. 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.
Yacht
Docker deployment reimagined as an app store: browse a visual catalog of applications, click to deploy with sensible defaults, and customize ports, volumes, and environment variables only when you need to. Point Yacht at any Portainer-compatible template JSON URL and it parses every application into a browsable, searchable interface with pre-configured settings ready for one-click launch. The template framework is fully decentralized — anyone can host template files on GitHub, a personal server, or any URL, creating a community-driven ecosystem of deployment packages without central gatekeeping. Template variables prefixed with ! automatically substitute server-level settings, so !config resolves to your configured path across every deployment without repetitive manual editing. The Python backend handles container lifecycle — start, stop, restart, kill, removal — while streaming real-time logs, providing browser-based shell access, and monitoring resource statistics through the Vuetify dashboard. Docker Compose stacks sit alongside individual containers in the same management interface. Advanced editing lets you modify port mappings, volumes, environment variables, and restart policies on running containers without redeployment. The develop branch introduces agent-managed remote host support for expanding management to additional Docker hosts. Authentication can be disabled for environments behind external proxies like Authelia or Traefik forward auth. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. CC-BY-4.0 licensed.
BitRouter
BitRouter is a context-aware LLM router that learns which model delivers the cheapest successful outcome per workflow step, cutting agent costs by up to 80% while maintaining 96% quality versus all-frontier baselines. Point any agent runtime at http://localhost:4356 with a one-line OPENAI_BASE_URL change and BitRouter routes to OpenAI, Anthropic, Google, Groq, DeepSeek, Mistral, Moonshot, MiniMax, Nvidia, and any OpenAI-compatible endpoint simultaneously, normalizing authentication, streaming, and cross-protocol translation between wire formats. The act-observe-evaluate-learn loop traces every hop with cost, tokens, and latency attribution, scores each decision against a versioned policy-lock.yaml, then tightens routes automatically with no LLM judge in the path. Native MCP gateway auto-discovers tools from connected servers and makes them routable and governed alongside model calls. Agent Client Protocol integration enables the TUI to manage Claude Code, Codex, OpenCode, OpenClaw, Gemini, and Copilot sessions in real time with inline tool-call approval and live streaming. Built-in guardrails inspect, redact, or block risky content before requests leave your network. Virtual keys scope API access per agent or user without exposing upstream credentials. Per-agent spend caps and loop guards contain runaway cost automatically. Multi-account failover reroutes mid-run so rate limits never re-pay completed work. Ships as a single Rust binary via npm or Cargo. 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.
Zomboid Control Panel
Friends are joining your Project Zomboid server, a mod just broke, and the log is scrolling faster than anyone can read. Zomboid Control Panel puts the fix in a browser tab. Start, stop, restart, and save the server from a dashboard that shows status, uptime, players online, host memory and CPU, disk space, and mods waiting for updates. A setup wizard installs a fresh Build 41 or Build 42 server through SteamCMD, or connects to one that already exists locally or over RCON. The mod manager tracks Workshop items, flags updates, imports Steam collections, scans for file conflicts, duplicate mod IDs, and missing dependencies, and sorts the load order. A structured INI editor covers server settings, sandbox options, spawn points, and regions, with a raw view for power users. Player pages handle kicks, bans, whitelists, access levels, and notes, and the live world map shows who is where. Events and weather controls trigger storms, hordes, and sounds. A scheduler runs timed restarts with countdown warnings, backups keep restorable world snapshots, and a Discord bot relays chat and answers slash commands. Admin, technician, moderator, and custom roles, plus OpenID Connect sign-in, decide who touches what. Community servers with several moderators, friends-only worlds, and hosts managing multiple servers from one panel all fit. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.