Model Gateways & Routing
Proxies that route requests across LLM providers. As of 2026-11-21, 431 indexed products match this subcategory (198 with full profiles); 167 were published in the last 90 days, against 85 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, OmniRoute leads, holding 11% of the stars of the 352 products here with their own repository. The most common form is MCP servers (70% of indexed products).
SubcategorySegment label: Lagging the catalogue DER
Segment statistics
Whole catalogue (all 431 indexed products, not only profiled ones). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized for its level, with launches growing more slowly than the catalogue’s. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.054, attention is spread as if across about 18 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 303 | 70.3% | 74 |
| Infrastructure | 39 | 9.0% | 38 |
| Plugins | 21 | 4.9% | 18 |
| Agent skills | 17 | 3.9% | 17 |
| Agent projects | 17 | 3.9% | 17 |
| Frameworks | 11 | 2.6% | 11 |
| IDE extensions | 8 | 1.9% | 8 |
| Libraries | 7 | 1.6% | 7 |
| SaaS products | 2 | 0.46% | 2 |
| Developer tools | 2 | 0.46% | 2 |
| AI APIs | 2 | 0.46% | 2 |
| Rules packs | 1 | 0.23% | 1 |
| Platforms | 1 | 0.23% | 1 |
3 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Multi-provider AccessOne API for many model providers. | 248 | 118 | 94 | Crowded, slowing |
| LLM Caching & Rate LimitsCaching responses and enforcing token budgets. | 74 | 40 | 33 | Established |
| Model RoutingPicking the right model per request with fallbacks. | 47 | 18 | 16 | Lagging the catalogue |
Top 40 products by GitHub stars
Search the directoryProfiled products only (198 of 431), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | OmniRouteNever stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors | Agent project | cheaper-inference | 89k | today | MIT | ||
| 2 | dsh-our-free-model在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费,不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap. | Agent project | Ebony-Vinyl | 83k | today | — | ||
| 3 | LiteLLMPython SDK and proxy server that expose 100+ model providers through an OpenAI-compatible API with keys, budgets, rate limits, fallbacks and logging. | Infrastructure | BerriAI | 64k | today | MIT | ||
| 4 | gooseOpen-source, local general-purpose AI agent (desktop app and CLI) for coding, research, writing and automation that works with any LLM and is extended through MCP extensions, YAML recipes and subagents. | Platform | Agentic AI Foundation (originally Block) | 57k | 1d ago | Apache-2.0 | ||
| 5 | nanobotYour lightweight open-source personal agent. | MCP server | HKUDS | 50k | today | MIT | ||
| 6 | Kong AI GatewaySet of AI plugins for the Kong API gateway that proxy and govern LLM traffic with prompt guards, semantic caching, routing and MCP traffic controls. | Infrastructure | Kong | 44k | 1d ago | Apache-2.0 | ||
| 7 | CodewhaleAn open-source coding agent for your terminal, written in Rust. It works with any model, can split one task across several agents, and every line of it is yours to read. | Agent project | codewhale-hq | 41k | today | MIT | ||
| 8 | LangfuseOpen-source LLM engineering platform for tracing, prompt management, evaluations and datasets, self-hosted or Langfuse Cloud. | Developer tool | ClickHouse (Langfuse) | 38k | today | MIT | ||
| 9 | mcp-for-blenderCommunity plugin to control Blender 3D with any LLM of your choice. Not affiliated with the official Blender Foundation. | MCP server | ahujasid | 35k | 3d ago | MIT | ||
| 10 | 9routerUnlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits. | Agent project | decolua | 33k | 5d ago | MIT | ||
| 11 | gpt-researcherAn autonomous agent that conducts deep research on any data using any LLM providers | MCP server | assafelovic | 31k | 9d ago | Apache-2.0 | ||
| 12 | Auto-claude-code-research-in-sleepARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent. | MCP server | wanshuiyin | 20k | 2d ago | MIT | ||
| 13 | Portkey AI GatewayGateway that routes requests to many LLM providers with retries, fallbacks, load balancing, caching and guardrails; open-source core plus hosted control plane. | Infrastructure | Palo Alto Networks (Portkey) | 13k | 1d ago | MIT | ||
| 14 | InsForgeThe all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end. | Agent project | InsForge | 13k | 1d ago | Apache-2.0 | ||
| 15 | OpenLLMRun any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud. | Infrastructure | bentoml | 13k | 5d ago | Apache-2.0 | ||
| 16 | mcp-useOpen-source library for connecting any LLM to MCP servers and building custom MCP agents and servers in Python or TypeScript. | Library | Manufact | 11k | today | MIT | ||
| 17 | tykOpen Source API and AI Gateway supporting REST, GraphQL, TCP, gRPC and MCP (Model Context Protocol) | MCP server | TykTechnologies | 11k | today | — | ||
| 18 | BifrostGo-based LLM gateway exposing many providers through one OpenAI-compatible API with failover, load balancing, governance and an MCP gateway. | Infrastructure | Maxim AI | 9.9k | today | Apache-2.0 | ||
| 19 | llm-gatewayOpen Source LLM Gateway 🦚 | Infrastructure | mnfst | 7.7k | 4d ago | MIT | ||
| 20 | planoPlano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic. | Infrastructure | katanemo | 7.1k | 28d ago | Apache-2.0 | ||
| 21 | ANUSA free coding agent in your terminal. It runs on the smartest free model that is up today. | Agent project | anus-dev | 6.6k | 1mo ago | MIT | ||
| 22 | KunLocal-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI. | Agent project | KunAgent | 6.4k | 5d ago | — | ||
| 23 | agentgatewayRust data plane for agent traffic that proxies MCP, A2A and LLM calls with authentication, authorisation policies and telemetry. | Infrastructure | Linux Foundation | 6.3k | today | Apache-2.0 | ||
| 24 | HeliconeProxy-based LLM observability that logs requests, costs and latency with one-line integration, plus an AI gateway. | Developer tool | Mintlify (Helicone) | 6.3k | 4d ago | Apache-2.0 | ||
| 25 | monidMonid - OpenRouter for agent tools. Join our community at https://discord.gg/rQzztcgJV8 | Agent project | monid-ai | 6.2k | 4d ago | MIT | ||
| 26 | youtube-automation-agent🎬 Open-source, self-hosted AI agent that runs a YouTube channel end to end: researches topics, writes scripts, generates narration, visuals and video, optimizes SEO, and publishes after your approval, then learns from analytics. Works with Gemini, OpenAI, OpenRouter, DeepSeek and more. | Agent project | darkzOGx | 5.3k | 1d ago | MIT | ||
| 27 | council-of-high-intelligenceStructured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode. | Framework | 0xNyk | 4.9k | 5d ago | MIT | ||
| 28 | ContextForge MCP GatewayGateway and registry that federates MCP servers, A2A agents and REST APIs behind one endpoint with auth, rate limiting and observability. | Infrastructure | IBM | 4.9k | 1d ago | Apache-2.0 | ||
| 29 | OB1Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS. | Agent project | NateBJones-Projects | 4.8k | today | — | ||
| 30 | all-agentic-architectures35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard. | Agent project | FareedKhan-dev | 4.8k | 5d ago | MIT | ||
| 31 | gptmeYour agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top! | Agent project | gptme | 4.5k | today | MIT | ||
| 32 | Claude APIAPI for Claude models with tool use, extended thinking, prompt caching, a remote MCP connector and server-side tools such as web search and code execution. | API | Anthropic | 4.1k | 1d ago | Apache-2.0 | ||
| 33 | ableton-mcpControl Ableton Live with any LLM: create tracks, arrange clips & compose music via MCP | MCP server | ahujasid | 3.4k | 2mo ago | MIT | ||
| 34 | FuxiFuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers. | Agent project | fuxicodex | 3.2k | 1mo ago | — | ||
| 35 | VCPToolBoxVCP 部署在 AI 模型 API 与前端应用之间,是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架,将原本“无状态、无记忆、无工具调用能力”的大语言模型,彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。 | Framework | lioensky | 2.5k | 1d ago | — | ||
| 36 | Agent RouterKubernetes-native AI gateway built on Envoy Gateway that exposes models through an OpenAI-compatible API and tools through an MCP gateway, with rate limiting and access control. | Infrastructure | Agentic AI Foundation (Linux Foundation) | 2.4k | 1d ago | Apache-2.0 | ||
| 37 | claude-real-videoLet any LLM watch a video locally — and search everything it has ever watched. | MCP server | HUANGCHIHHUNGLeo | 2.3k | 1d ago | MIT | ||
| 38 | company-research-agentAn agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages OpenRouter on the backend for rapid inference with any leading model. | Framework | guy-hartstein | 2.3k | 18d ago | Apache-2.0 | ||
| 39 | future-agiOpen-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0. | Infrastructure | future-agi | 2.3k | today | Apache-2.0 | ||
| 40 | CoreCoderMinimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder. | Agent project | he-yufeng | 1.9k | 1d ago | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| Azure | 3 | 0.7% |
| GitHub | 3 | 0.7% |
| Google Cloud | 3 | 0.7% |
| Vercel | 3 | 0.7% |
| Blender | 2 | 0.5% |
| Discord | 2 | 0.5% |
| Solana | 2 | 0.5% |
| Telegram | 2 | 0.5% |
| AWS | 1 | 0.2% |
| Gmail | 1 | 0.2% |
| Grafana | 1 | 0.2% |
| GraphQL | 1 | 0.2% |
| Kubernetes | 1 | 0.2% |
| Netlify | 1 | 0.2% |
| PostgreSQL | 1 | 0.2% |
Launches per month
New Model Gateways & Routing products per monthSRC
Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-11 | 2 |
| 2024-12 | 1 |
| 2025-01 | 2 |
| 2025-02 | 2 |
| 2025-03 | 6 |
| 2025-05 | 4 |
| 2025-06 | 1 |
| 2025-07 | 2 |
| 2025-08 | 1 |
| 2025-09 | 7 |
| 2025-10 | 2 |
| 2025-11 | 2 |
| 2025-12 | 4 |
| 2026-01 | 9 |
| 2026-02 | 20 |
| 2026-03 | 25 |
| 2026-04 | 23 |
| 2026-05 | 26 |
| 2026-06 | 25 |
| 2026-07 | 36 |
| 2026-08 | 28 |
| 2026-09 | 34 |
| 2026-10 | 73 |
| 2026-11 | 46 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
| Opportunity | Competition | Confidence | Score |
|---|---|---|---|
| Coverage gap: Model RoutingModel Routing | High | Low | 57.3 |
| Coverage gap: LLM Caching & Rate LimitsLLM Caching & Rate Limits | High | Low | 54.1 |
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .