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.
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.
CPA Usage Keeper
Somewhere between the third coding agent and the fifth model subscription, nobody can say where the tokens went. CPA Usage Keeper keeps the receipts for a CLIProxyAPI gateway, saving every request locally with scheduled backups so history survives restarts. The Overview page shows requests, success rate, tokens, cache hit rate, and estimated cost with sparklines and a calendar heatmap, and Realtime plots time to first token against total latency and shows rolling cache levels and model speed. Analysis breaks usage down by API key, model, credential, or provider with donut charts and ranked lists. The Request Events log filters by model, source, and status, adjusts its columns, and exports records. Credentials cards show success rates, remaining five-hour and weekly quotas, priorities, and enable switches, and quota history charts how many tokens and dollars each percentage point costs over a cycle. Individual API keys can be given a read-only usage view. Deployment uses a Docker Compose file that bundles CPA with Keeper or runs Keeper beside an existing gateway, and the interface switches between English and Chinese and between light and dark themes. Check the dashboard before the invoice arrives and see exactly who spent what. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Higress
Send every AI request through one gateway that holds your model providers, API keys, and access rules. The web console starts with a first-run admin setup, then an LLM Provider page where OpenAI-compatible endpoints, Anthropic Claude, Azure OpenAI, Tongyi Qianwen, Moonshot, Zhipu, and other services are added with their tokens. AI Route Config maps path prefixes and model match rules to weighted target services, with token failover and first-packet timeouts to keep traffic moving when a key fails. Consumer Management issues key, OAuth2, and JWT credentials, and each route can limit access to named consumers. Plugin Management lists ready-made AI plugins for caching, context limits, data masking, prompt templates, prompt decorators, load balancing, and intent checks, plus traffic and security plugins that can be configured per route. MCP Management hosts MCP servers behind the same authentication and rate limits so agents call tools through one governed address. Service Sources import backends from Nacos, Zookeeper, Consul, Eureka, static addresses, or domains, and domain and certificate pages handle HTTPS, including free automatic certificates from Let's Encrypt. An LLM proxy for a product team, a shared model endpoint for several agents, or a replacement for an ingress controller all fit this 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.
Manifest LLM Gateway
Manifest LLM Gateway is a self-hosted gateway that puts every model you pay for behind one OpenAI- and Anthropic-compatible endpoint. Connect provider API keys, reuse subscriptions like ChatGPT Plus or Claude Max, or point it at Ollama and LM Studio on your own hardware. Send a request with the model set to auto and your routing rules choose the target by model, header, complexity, or task type, with fallbacks that take over the instant a model fails. Each agent or app gets its own harness, a named connection with a private key, spending limits, and notifications when usage climbs. The Requests view logs every call and every retry attempt, with status, cost, tokens, and the full request and response body readable as a conversation. Autofix repairs a malformed request, for example one using a renamed parameter, and resends it before your app ever sees an error. A Playground tests models from the dashboard, a command line tool and MCP server handle setup from a terminal or an AI assistant, and an n8n node plugs it into automations. Over 35 provider connections cover more than 300 models. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
KeiRouter
One endpoint, 130+ models from 90+ providers: KeiRouter is a self-hosted AI gateway, so apps, coding tools, and agents connect once and stop juggling provider keys. Your code speaks OpenAI Chat, OpenAI Responses, Anthropic Messages, or native Gemini, and KeiRouter translates to whichever upstream you want, including AWS Bedrock, Azure AI Foundry, Vertex, Snowflake Cortex, and self-hosted runtimes like Ollama and vLLM. Fallback chains keep requests moving when a provider goes down or hits a rate limit, using priority, round-robin, latency, or cost ordering, so coding sessions do not stop mid-task. Five token savers compress prompts on the way in and trim responses on the way out, with a live dashboard showing savings recovered. A response cache answers repeated prompts instantly for zero marginal cost, with optional semantic matching. Per-key budgets and rate plans set USD, token, RPM, and concurrency limits with auto-cutoff, stopping surprise bills. Guardrails scan for PII, prompt injection, toxicity, and banned topics at global, provider, model, chain, and key scopes, with a monitor showing what got blocked and what it cost. The dashboard tracks usage by provider and model, latency, a live console tracing each request through its fallbacks, and provider health. You can import from 9router or OmniRoute, white-label the portal for your team, and run replicas on Postgres and Redis for high availability. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
GoModel
Instead of scattering provider credentials and vendor-specific SDK logic across dozens of microservices, engineering teams route every LLM call through GoModel, an open-source AI gateway that unifies 34 model providers behind OpenAI-compatible and Anthropic-compatible endpoints. Pointing existing OpenAI or Anthropic SDKs at the gateway unlocks chat completions, the Responses API, Anthropic Messages, embeddings, batch jobs, and realtime audio across OpenAI, Anthropic, Gemini, Bedrock, Azure, Groq, DeepSeek, Ollama, and vLLM. Platform operators publish virtual model aliases that distribute traffic via weighted round-robin or lowest-cost routing while rotating multiple API keys per provider and failing over through circuit breakers during upstream outages. Sticky session routing keeps multi-turn agent conversations on the same target to preserve warm prompt caches, while exact-match and vector semantic caching via Qdrant, pgvector, Pinecone, or Weaviate cut duplicate token costs. Versioned workflows and pre-dispatch guardrails enforce prompt injection rules, rate limits, and hard USD spend budgets across hierarchical tenant user paths before requests are dispatched. The built-in admin dashboard offers live audit logs, per-tenant cost analytics, LiteLLM key migration, an interactive request playground, Model Context Protocol tool aggregation, and OpenTelemetry and Prometheus metrics. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
OpenGateLLM
One endpoint, every model you run, and a government-grade paper trail for each request. OpenGateLLM sits in front of your AI infrastructure as the single door: applications call one OpenAI-compatible API, and the gateway decides which backend answers, a self-hosted vLLM cluster, an Ollama box in the corner, a Hugging Face TEI embeddings service, or a hosted provider when you allow one. You publish friendly model names as routers and attach real provider APIs behind them, then load-balance across those backends by shuffle or least-busy so a second GPU node starts earning its keep the moment you register it. Chat completions, embeddings, reranking, OCR, and audio transcription each get their standard endpoint, so existing OpenAI SDK code, LangChain, and LlamaIndex projects point at a new base URL and keep working. Governance is built in rather than bolted on: organizations, users, and roles control who may call which model, API keys authenticate every request, and rate limiting keeps one enthusiastic team from eating the whole cluster. Usage monitoring follows every inference, and carbon footprint estimates attach to models through their hosting zone and parameter counts. Retrieval-augmented generation against Elasticsearch or Qdrant plugs into the same surface. No chat history is stored, which is rather the point when the data is yours. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Tingly Box
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.
Obsidian Arc
Teams and communities sign in to a private AI chat site, and one admin console routes and meters every request. Users pick a model from the menu and chat with streamed answers, visible reasoning, projects that share a system prompt, searchable history, archives, and an Image Lab for generated pictures. Administrators connect providers that speak the OpenAI or Anthropic protocols, map several models onto each, and place users in groups with their own allowances counted in requests, tokens, or credits per five hours, week, or month. A developer endpoint accepts API keys and serves chat completions, Anthropic messages, responses, images, and a model list, so coding assistants and scripts can share the same pool. The dashboard charts requests, tokens, and spend by model and by person, and Availability probes idle models and trips a circuit breaker after repeated failures. Registration can be open, invite-only, or closed, with invite codes, email rules, authenticator-app two-step sign-in, and GitHub, Google, or OpenID Connect login. Announcements, a feedback inbox, an optional leaderboard, a guest trial chat, and scheduled backups to S3-compatible storage round out the operator toolkit. A company AI portal, a classroom, a research group, or a paid community with trial codes can all run on it. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
AIHelms
Every employee gets one AI key, and every dollar of model spending gets a name next to it. AIHelms is an admin console and user portal that sits in front of your model providers, so a team can use Claude, DeepSeek, GPT, and local models through one entry point, with IT keeping control. Administrators onboard providers, publish models, and balance traffic across several deployments of the same model, with both OpenAI and Anthropic request formats accepted. Each AI identity carries a model allow-list, quota, rate limits, and an expiry date. Budgets can be set per person, department, project, or model, with soft alerts and hard cut-offs. Internal settlement prices sit beside real provider costs, so departments can be billed with or without a markup. Dashboards show adoption, daily calls, token use, and top users, and weekly or monthly efficiency reports drill down by department. A built-in marketplace registers, approves, and distributes MCP servers and agent Skills, and an AI policy scan flags risky Skills before anyone installs them. Audit logs record every administrator action. Employees see their key, endpoint, models, and monthly spend in the portal. 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.
Bifrost
Bifrost is an open-source AI gateway that unifies 23+ LLM providers into a single OpenAI-compatible endpoint with automatic failover, semantic caching, and built-in cost governance, so one provider going down never takes your production AI application with it. Point your existing OpenAI or Anthropic SDK at Bifrost's local endpoint and gain access to OpenAI, Anthropic, AWS Bedrock, Google Vertex, Azure, Groq, Mistral, and Ollama without changing application code. Define fallback chains that automatically switch providers when one returns errors or exceeds latency thresholds, keeping response times stable during outages. The built-in web dashboard at port 8080 lets you configure providers, create virtual API keys, monitor live request traffic, and review analytics without editing configuration files. Semantic caching combines exact hash matching with vector similarity search via Weaviate, serving cached responses for identical or paraphrased prompts in sub-millisecond time to cut costs on repetitive workloads. The MCP gateway connects AI agents to external tools like filesystems, databases, and web APIs, exposing them to clients such as Claude Desktop and Cursor with per-key allow-lists. Four-tier budget hierarchy at customer, team, virtual key, and provider levels enforces spend caps, rate limits, and model restrictions across your organization. Extend functionality through custom Go plugins for analytics, monitoring, or security middleware. Native Prometheus metrics and OpenTelemetry distributed tracing give operations teams full production observability. 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.
LLM Gateway
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.
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.
CLIProxyAPI Dashboard
CLIProxyAPI Dashboard puts a web console in front of CLIProxyAPI so you manage AI providers, keys, quotas, and containers through forms instead of YAML files. Connect Claude Code, Codex, xAI, Antigravity, Kimi, and Devin accounts with OAuth, then add Gemini CLI, GitHub Copilot, Kiro, and Cursor through plugins you install and configure from the settings store. Any OpenAI-compatible endpoint can join as a custom provider with model mappings, and admins can mark a provider as shared so the whole team uses it. You create, revoke, and track API keys with per-user ownership, manage dashboard users and admin rights, and stream live logs beside container health. Quota views track rate limits per provider and per model, and Telegram alerts fire when remaining quota drops below your threshold. Usage analytics break down request counts, provider share, model statistics, error rates, and estimated cost. Configuration syncs to OpenCode automatically, model configurations travel as share codes, and backups can be created, scheduled, previewed, and restored from settings. One-click updates refresh the dashboard and proxy images, containers start and stop from the panel, and automatic TLS keeps the console reachable under your domain. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT 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.
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.
Inference Gateway
Inference Gateway puts a single OpenAI-compatible API endpoint in front of OpenAI, Anthropic, Groq, Cohere, Ollama, DeepSeek, Google, Mistral, MiniMax, Moonshot, Nvidia, and llama.cpp, so your application code never changes when you switch models or providers. The Go binary starts on port 8080 and normalizes authentication, streaming protocols, and response formats across all backends transparently. Native Model Context Protocol support auto-discovers tools from connected MCP servers and injects them into LLM requests without client-side management, enabling server-side tool execution across any provider that supports function calling. Agent-to-Agent protocol integration allows distributed agent communication through a declarative Agent Definition Language that generates production-ready Go or Rust servers from a single YAML manifest. The dedicated Kubernetes Operator manages Gateway, Agent, MCP, and Orchestrator custom resources with automatic HPA scaling, OIDC authentication, and service discovery that rebuilds MCP configurations when the discovered server set changes. Prometheus metrics and OpenTelemetry tracing provide full request-level observability across the entire inference pipeline. Middleware controls enable per-request provider selection, model routing, and fallback strategies. Official SDKs in Go, Python, TypeScript, and Rust provide typed client interfaces with streaming support. Docker Compose deployment requires only environment variables for API keys. A CNCF Sandbox applicant. 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.