Models & Gateways
Accessing, routing, serving and tuning language models. As of 2026-11-21, 1,115 indexed products match this category (601 with full profiles); 343 were published in the last 90 days, against 236 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, ponytail leads, holding 9% of the stars of the 950 products here with their own repository. The most common form is MCP servers (58% of indexed products).
CategorySegment label: Lagging the catalogue DER
Segment statistics
Whole catalogue (all 1,115 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 category 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 0.022, attention is spread as if across about 45 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 | 646 | 57.9% | 197 |
| Agent skills | 131 | 11.7% | 130 |
| Infrastructure | 78 | 7.0% | 75 |
| Rules packs | 73 | 6.5% | 23 |
| Plugins | 58 | 5.2% | 48 |
| Frameworks | 40 | 3.6% | 39 |
| Agent projects | 40 | 3.6% | 39 |
| IDE extensions | 21 | 1.9% | 22 |
| Libraries | 10 | 0.90% | 10 |
| Developer tools | 9 | 0.81% | 9 |
| AI APIs | 4 | 0.36% | 4 |
| Platforms | 3 | 0.27% | 3 |
| SaaS products | 2 | 0.18% | 2 |
3 subcategories
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.
| Subcategory | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Model Gateways & RoutingProxies that route requests across LLM providers. | 431 | 198 | 167 | Lagging the catalogue |
| Local & Open ModelsRunning, serving and fine-tuning open-weight models. | 388 | 230 | 115 | Lagging the catalogue |
| LLM DelegationHaving one agent consult or delegate to other models. | 374 | 228 | 81 | Lagging the catalogue |
Top 40 products by GitHub stars
Search the directoryProfiled products only (601 of 1,115), 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 | ponytailMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. | Agent skill | DietrichGebert | 196k | 23d ago | MIT | ||
| 2 | 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 | ||
| 3 | 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 | — | ||
| 4 | Prompt-Engineering-Guide🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents. | Agent project | dair-ai | 80k | 8mo ago | MIT | ||
| 5 | system_prompts_leaksLeaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily. | Agent project | asgeirtj | 72k | today | CC0-1.0 | ||
| 6 | humanizerAgent skill that removes signs of AI-generated writing from text | Agent skill | blader | 72k | 2d ago | MIT | ||
| 7 | 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 | ||
| 8 | 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 | ||
| 9 | cherry-studioYour AI workspace for models, agents, and productivity. | Agent skill | CherryHQ | 54k | today | AGPL-3.0 | ||
| 10 | nanobotYour lightweight open-source personal agent. | MCP server | HKUDS | 50k | today | MIT | ||
| 11 | CowAgentOpen-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install. | Agent project | zhayujie | 48k | today | MIT | ||
| 12 | 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 | ||
| 13 | awesome-copilotCommunity-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot. | Agent skill | github | 41k | 1d ago | MIT | ||
| 14 | 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 | ||
| 15 | nuwa-skill你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks. | Agent skill | alchaincyf | 39k | today | MIT | ||
| 16 | LangfuseOpen-source LLM engineering platform for tracing, prompt management, evaluations and datasets, self-hosted or Langfuse Cloud. | Developer tool | ClickHouse (Langfuse) | 38k | today | MIT | ||
| 17 | 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 | ||
| 18 | 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 | ||
| 19 | gpt-researcherAn autonomous agent that conducts deep research on any data using any LLM providers | MCP server | assafelovic | 31k | 9d ago | Apache-2.0 | ||
| 20 | claude-skills410 Claude Code skills & agent skills & plugins (120+ Agents, custom commands, 410+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills. | Agent skill | alirezarezvani | 30k | today | MIT | ||
| 21 | MLflowOpen-source ML/GenAI lifecycle platform whose GenAI features include OpenTelemetry-compatible tracing, evaluation and prompt registry for agents. | Developer tool | Databricks (Linux Foundation) | 29k | today | Apache-2.0 | ||
| 22 | promptfooCLI and library for declarative prompt/model test suites, side-by-side comparisons and automated red-teaming of LLM apps and agents. | Developer tool | OpenAI (Promptfoo) | 28k | today | MIT | ||
| 23 | distillyDistilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill(原同事 Skill). | Agent skill | titanwings | 27k | 1mo ago | MIT | ||
| 24 | OpikOpen-source platform for tracing, evaluating and monitoring LLM apps and agents, with LLM-as-judge metrics and prompt optimisation. | Developer tool | Comet | 23k | today | Apache-2.0 | ||
| 25 | MaxKB🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。 | MCP server | 1Panel-dev | 23k | today | GPL-3.0 | ||
| 26 | awesome-ai-engineering🚀 A curated collection of AI engineering resources, roadmaps, tools, and projects covering LLMs, RAG, AI Agents, MCP, fine-tuning, evaluations, and production AI systems. | Agent project | dipakkr | 23k | 1mo ago | MIT | ||
| 27 | agency-agents-zh🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具,覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体(小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计)。搭配编排器 agency-orchestrator,一句话即可让多位专家按 DAG 自动协作。 | Rules pack | jnMetaCode | 22k | 3d ago | MIT | ||
| 28 | elephant-goldfish-modelOpen-source plugin for designing and reviewing software with agents | Agent skill | 22k | 1d ago | Apache-2.0 | |||
| 29 | 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 | ||
| 30 | prompt-masterA Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention | Agent skill | nidhinjs | 16k | 1mo ago | MIT | ||
| 31 | docker-androidAndroid in docker solution with noVNC supported, video recording, mcp server and AI-agent | MCP server | budtmo | 16k | 2d ago | — | ||
| 32 | cc-haha本地优先的跨平台 Claude Code / AI Agent 桌面工作台:多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物;支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git worktrees, diffs, skills marketplace, multi-model, Computer Use, task-aware desktop pets; remote via WeChat, Feishu, DingTalk, Telegram, WhatsApp & H5. | Agent project | NanmiCoder | 16k | 1d ago | — | ||
| 33 | AI-Research-SKILLsComprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research. | Agent skill | Orchestra-Research | 15k | 1mo ago | MIT | ||
| 34 | BrowserOS🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia. | Agent project | browseros-ai | 14k | today | AGPL-3.0 | ||
| 35 | LEANN[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device. | Infrastructure | StarTrail-org | 14k | today | MIT | ||
| 36 | langchain4jLangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot. | Infrastructure | langchain4j | 13k | today | Apache-2.0 | ||
| 37 | 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 | ||
| 38 | 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 | ||
| 39 | 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 | ||
| 40 | Arize PhoenixSelf-hostable tracing and evaluation tool built on OpenTelemetry/OpenInference for inspecting LLM and agent runs, datasets and experiments. | Developer tool | Arize-ai | 12k | today | Elastic-2.0 |
Most common integrations
Third-party services named by products in this node, whole catalogue.
Launches per month
New Models & Gateways 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 | 4 |
| 2024-12 | 3 |
| 2025-01 | 7 |
| 2025-02 | 8 |
| 2025-03 | 12 |
| 2025-04 | 5 |
| 2025-05 | 10 |
| 2025-06 | 3 |
| 2025-07 | 3 |
| 2025-08 | 8 |
| 2025-09 | 11 |
| 2025-10 | 10 |
| 2025-11 | 11 |
| 2025-12 | 10 |
| 2026-01 | 19 |
| 2026-02 | 45 |
| 2026-03 | 79 |
| 2026-04 | 84 |
| 2026-05 | 61 |
| 2026-06 | 74 |
| 2026-07 | 92 |
| 2026-08 | 75 |
| 2026-09 | 79 |
| 2026-10 | 154 |
| 2026-11 | 89 |
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: Cross-model ConsultationCross-model Consultation | High | Low | 58.8 |
| Coverage gap: Model RoutingModel Routing | High | Low | 57.3 |
| Coverage gap: LLM Caching & Rate LimitsLLM Caching & Rate Limits | High | Low | 54.1 |
| Coverage gap: Model ServingModel Serving | High | Low | 52.1 |
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 .