One OpenAI-compatible API fronts more than 250 models across 40 providers in LLM Gateway, with routing, cost analytics, and key management in a single dashboard. Existing OpenAI SDK code keeps working: change the base URL and model name to reach OpenAI, Anthropic, Google, xAI, DeepSeek, Groq, and dozens more. Every request lands in an activity log with its model, cache status, token counts, duration, and cost, and opening a request shows time to first token, throughput, and cached token usage. Spend splits by model, provider, project, and API key over 7 or 30 days, so the expensive endpoint stops hiding inside one monthly invoice. Scoped API keys carry spend caps and recurring limits, and requests stop automatically at the cap. Provider errors, timeouts, and rate limits trigger a retry on another provider for the same model before the caller hears about it. Coding agents and automation tools get their own usage views with requests, tokens, and spend per tool. Self-hosting runs the unified Docker image or a Kubernetes Helm chart on your own 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.

Give every agent your team runs the same front door, and the model chaos behind it becomes manageable. Tingly Box is a self-hosted gateway with a web console where providers, keys, routing rules, and team usage live in one place. Claude Code, OpenCode, Codex, Xcode, and other clients simply call the endpoint. A request arrives. The gateway reads your rules, weighs cost against speed against the policy you wrote, picks a model and a token, translates the protocol if the two ends disagree, and streams the answer back. Existing subscription quotas are spendable here, connected by OAuth beside ordinary API keys, and per-scenario profiles let quick edits and deep refactors land on different models by default. Team mode shares that endpoint properly. Model rules are managed centrally, each member receives a dedicated key, data stays isolated per user, and the usage dashboard shows exactly who consumed what. The gateway also speaks images, generating and editing through the same address with a playground for testing prompts before clients depend on them. Agents remain reachable after you leave the desk, driven through Telegram, DingTalk, Feishu, Lark, Weixin, or WeCom, with guardrails and an MCP gateway available as power-ups. Virtual models give new rules a safe target for testing and benchmarking before real traffic moves over. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MPL-2.0 licensed.

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.

One endpoint for every MCP server you run: MCPHub gathers local and remote Model Context Protocol servers behind stable URLs, so AI clients connect once and see what you allow. Claude Code, Cursor, and Cherry Studio can use four routes: everything at /mcp, a named group at /mcp/{group}, one server at /mcp/{server}, or semantic tool search at /mcp/$smart. Smart routing runs vector search on PostgreSQL with pgvector and an OpenAI-compatible key, so the model gets a shorter tool list. Servers attach over stdio, SSE, or streamable HTTP, OpenAPI services can be wrapped as MCP tools, and changes apply without downtime. In the other direction, MCP tools can be exported as an OpenAPI 3.0.3 spec for OpenWebUI and other OpenAPI clients. Bearer keys, OAuth 2.0 (client and server modes), and GitHub or Google sign-in in database mode control access, with per-user visibility for servers and groups. Encrypted per-user credentials let one shared server use each person's own key. Logs show tool-call activity, request status, and latency, health checks track each connection, and the dashboard controls which tools, prompts, and resources each server exposes. Large text tool results can be compressed, interactive MCP Apps are proxied through MCPHub routes, and a built-in market lets you browse a server catalog. Typical uses include a team-wide gateway, per-project groups, and direct single-server routes for debugging. 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.

Atlas turns OpenStreetMap data for a city, a country, or the whole planet into a maps backend your applications can search, route with, and query for nearby places, all on hardware you control: pick a region and it downloads and indexes that territory's data locally. Search behaves the way users expect, with autocomplete matches grouped into clusters across the installed dataset, numbered so dense areas stay readable, and a show-all action that frames the full result set. Routing returns directions for driving, cycling, and walking, and a map-matching endpoint snaps noisy recorded GPS tracks onto the real road network. Ask what is here at any coordinate and category pickers surface restaurants, stations, parking, and hundreds of other place types around it, while transit planning threads timetables into door-to-door journeys. The settings panel is the control room: toggle search, routing, points of interest, and transit independently, switch the active region, and watch live progress as new territory is ingested and merged in the background. Developers plug in through one consistent JSON API covering geocoding, reverse geocoding in batches, coverage checks, and every map capability, documented as a public OpenAPI reference. Because every dataset lives on the box, the map keeps answering during outages and inside private networks. 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.

Every prompt your application sends is a small buying decision, and OrcaRouter Lite makes it a smart one instead of a habit. Point your app at one OpenAI-compatible endpoint on your server, and each request is shopped across the providers whose keys you hold: OpenAI, Anthropic, Google, xAI, DeepSeek, and dozens more. Send model set to auto and the router picks the cheapest model that can actually do the job, checking whether the request needs tools, vision, or JSON mode before it commits your money. Prefer a different tradeoff and you can switch the whole gateway between balanced, cheapest, fastest, and quality strategies, with quality picks driven by real benchmark scores rather than vibes. Clients that speak Anthropic's or Gemini's native protocols connect directly too, so Claude Code, the OpenAI SDK, and google-genai all land on the same routing pipeline. Streaming responses flow through untouched, and every answer reports which model really served it. The built-in dashboard shows recent requests, spend, latency percentiles, unreachable providers, and a savings tile that tells you what your traffic would have cost if you had blindly used a flagship model for everything. Your provider keys stay encrypted on your own box, your analytics never leave it, and if every local provider has a bad day, the hosted OrcaRouter can step in as a failover safety net. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OpeniLink Hub turns a personal WeChat account into a programmable bot platform, with a web console, multi-bot management, and a one-click app marketplace that wires WeChat to Lark, Slack, GitHub, Notion, and twenty other services. Bind accounts by scanning a QR code, then watch every bot's status, expiry window, and message flow from one dashboard. Install marketplace apps without writing code: Lark gains 34 AI-callable tools across calendars, docs, tasks, and meetings, while GitHub brings 36 tools for issues, pull requests, and Actions. Every incoming message fans out in parallel over WebSocket for millisecond pushes, Webhook callbacks to your own servers, and an AI channel that answers through any OpenAI-compatible API. Message tracing follows each message from receipt to delivery, showing exactly which hop stalled when something breaks. Passkey sign-in with fingerprint or hardware keys keeps the console protected, with GitHub and LinuxDo OAuth as alternatives. Reminders, expense tracking, currency conversion, RSS digests, and cron-scheduled pushes run as installable apps, and expiry reminders warn you before the 24-hour reply window closes. Build your own integrations with official SDKs for Go, Node.js, Python, PHP, Java, C#, and Lua, or expose local CLI commands as chat-callable tools with the Runner app. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Before the maintenance window, know exactly where the traffic will go: Topolograph rebuilds your network the way its routing protocols see it and lets you break it safely on screen. Upload one router's LSDB output, from Cisco, Juniper, Arista, FRRouting, MikroTik, and a dozen other vendors, and the whole area's topology appears as an interactive graph, because the protocol already flooded it everywhere. Compute the shortest path between any two routers and see every equal-cost alternative with per-link loads, then fail a link or a node and watch SPF recalculate: which pairs moved to backup, which are left with none, and how the load shifted on every surviving link. Search the graph for prefixes, MAC addresses, or any network element, plan an MPLS TE path against real bandwidth attributes, and compare snapshots from different moments to answer what changed before the incident. Collectors can stream live OSPF, IS-IS, and BGP events over GRE, BGP-LS, or BMP so the timeline replays the network at the moment things broke, and a REST API, Python SDK, and MCP server let your own tooling and AI agents ask the same questions. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Routerly is the one front door for every AI model your apps use: point your OpenAI or Anthropic client at it, and it chooses the right model for each request, enforces your budget, and keeps the receipts. Nothing in your code changes except the base URL, and from that moment streaming chat completions and messages flow to OpenAI, Anthropic, Gemini, Mistral, Cohere, xAI or your own Ollama models behind a single token. Nine routing policies score every candidate in parallel: cheapest, fastest, healthiest, most capable, biggest context, least rate-limited, fairest, most budget left, and one that asks a small model to judge which model fits the task. When the winner errors or times out, the next candidate takes over automatically, and the recorded routing trace shows exactly why each model won or lost. Guardrails can block or log content that breaks your rules, and phone numbers, card numbers, SSNs, IBANs and emails can be scrubbed out before anything reaches a provider. Every call is logged with tokens, USD cost and latency, and hard limits per model, project and token reject overspending requests before a provider can charge for them. Projects keep separate tokens, model lists and budgets for each team or tool, role-based permissions decide who may change what, and alerts land in Slack, email, webhooks or PagerDuty when budgets or providers misbehave. 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.

With 3,900 GitHub stars, 140 contributors, and 380 releases since its 2022 launch, Grafana OnCall delivers developer-friendly incident response that routes alerts from any monitoring system to the right engineer at the right time through the right channel. The platform accepts alerts via unique API URLs from Alertmanager, Grafana Alerting, Zabbix, Datadog, Pagerduty-compatible sources, Jira, inbound email, and generic HTTP webhooks, then applies routing templates to direct each alert to the appropriate escalation chain. Escalation chains define notification sequences — notify the primary on-call via Slack, wait 5 minutes, escalate to SMS and phone, wait 10 minutes, page the secondary on-call and notify the engineering manager — continuing until acknowledgment or resolution. On-call schedules support multi-layer rotations with overrides, shift swaps, and timezone-aware handoffs rendered directly inside Grafana dashboards. ChatOps integration publishes alert groups to Slack channels and Telegram groups with interactive buttons for acknowledge, resolve, and silence actions. Template engines based on Jinja2 control alert grouping, appearance rendering, and behavioral automation. The REST API enables programmatic management of integrations, schedules, and escalation policies. Deploy via Docker Compose with PostgreSQL, Redis, and Celery workers alongside your existing Grafana instance. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GNU AGPL v3 licensed.