Skip to content
Agentmart
Submit a tool

AI agent tools for model inference

In this catalog, a model inference tool is one that calls, hosts or routes requests to language, vision or embedding models. Our enrichment pass tags 173 listings with it: 34 MCP servers, 39 agent skills, 59 plugins, 14 agent frameworks, 23 AI agents and 4 no-code agent builders. By listing rank, the top MCP server is Pollinations, the top agent skill is claude-api and the top plugin is BAML v0. 15 of the 173 are published by the vendor behind the product, and 102 were active in the last 30 days. 7 of the 34 MCP servers run only as remote servers, with nothing to install locally. Each entry below links to its listing page, with grades, install commands and sources.

Updated Oct 26, 2026 · Built from catalog data; how we rank and grade

What the job is

Tagged listings
173
By type
34 MCP servers, 39 agent skills, 59 plugins, 14 agent frameworks, 23 AI agents and 4 no-code agent builders
Published by the vendor
15 of 173
Active in the last 30 days
102 of 173
Open source
138 of 173
MCP servers that run only remotely
7 of 34
Hosts named by the MCP servers
Claude Code (33), Cursor (33), VS Code (33)

Building blocks by type

The top entries of each type, by listing rank. Open a listing for its install command, grades and sources.

MCP servers 34 tagged

  1. 1
    Pollinations

    pollinations

    Access Pollinations models and API capabilities through agent tools.

    • Most GitHub stars here (5,238)
    • Remote server, no local install
    • Active in the last 30 days

    ★ 5.2KLast active Oct 24, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  2. 2
    Grandet

    hanzohanzhe

    Cheapest API for any model across official, inference and relay providers; find free credits

    • Remote server, no local install
    • Active in the last 30 days

    ★ 692Last active Oct 19, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  3. 3
    SuperCompress

    Supercompress

    Compress coding-agent context ~64%.

    • Runs locally or as a remote server
    • Active in the last 30 days
    • Open source (MIT)

    ★ 137Last active Oct 22, 2026Local (stdio), Remote (HTTP)Claude Code, VS Code, Codex, Cursor +2

  4. 4
    Rubber Duck

    nesquikm

    Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more

    • Active in the last 30 days
    • Open source (MIT)

    ★ 180Last active Oct 13, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  5. 5
    OpenRouter Multimodal

    stabgan

    Chat with 300+ LLMs via OpenRouter.

    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 101Last active Oct 22, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

Search MCP servers for model inference → All connectors

Agent skills 39 tagged

  1. 1
    claude-api

    anthropicsOfficial

    Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.

    • Published by the vendor
    • Largest repository here (183,466 stars)
    • Active in the last 30 days

    ★ 183.5KLast active Oct 9, 2026Claude Code, Claude apps, Codex, Cursor +6

  2. 2
    hf-cli

    huggingfaceOfficial

    Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub.

    • Published by the vendor
    • Repository has 11.2K stars
    • Active in the last 30 days

    ★ 11.2KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6

  3. 3
    gemini-api-dev

    google-geminiOfficial

    Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation…

    • Published by the vendor
    • Repository has 4.3K stars
    • Active in the last 30 days

    ★ 4.3KLast active Oct 13, 2026Claude Code, Claude apps, Codex, Cursor +6

  4. 4
    plano-advanced-patterns

    katanemo

    Design advanced Plano architectures.

    • Repository has 7.1K stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 7.1KLast active Oct 24, 2026Claude Code, Claude apps, Codex, Cursor +6

  5. 5
    codonfm-finetune

    NVIDIA BioNeMo <bionemofeedback@nvidia.com>

    Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning.

    • Repository has 3.7K stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 3.7KLast active Oct 9, 2026Claude Code, Claude apps, Codex, Cursor +6

Search agent skills for model inference → All skills

Plugins 59 tagged

  1. 1
    BAML v0

    Boundary

    BAML v0 is a DSL for AI applications.

    • Most GitHub stars here (9,431)
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 9.4KLast active Oct 24, 2026VS Code, Cursor, Windsurf, VSCodium

  2. 2
    GitHub Copilot API Gateway

    Suhaib Bin Younis

    Free & open-source universal API Gateway for all VS Code language models.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 128Last active Oct 24, 2026VS Code, Cursor, Windsurf, VSCodium

  3. 3
    Ungate

    orchidfiles

    Use Claude, GPT, or MiniMax subscriptions in Cursor instead of paying for API tokens

    • Active in the last 30 days
    • Open source (MIT)

    ★ 219Last active Oct 24, 2026VS Code, Cursor, Windsurf, VSCodium

  4. 4
    DeepSeek V4 for Copilot Chat

    Vizards

    Use DeepSeek V4.1 Flash in Copilot Chat with native vision, Vision Proxy, reasoning, and agent tools.

    • 1.5K GitHub stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 1.5KLast active Oct 16, 2026VS Code, Cursor, Windsurf, VSCodium

Search plugins for model inference → All plugins

Agent frameworks 14 tagged

  1. 1
    Genkit

    Google

    Open-source Firebase framework for AI features and agent workflows in JavaScript, Go, Python and Dart, with model plugins.

    • 6.5K GitHub stars
    • Most weekly downloads here (95.8K)
    • Active in the last 30 days

    ★ 6.5K↓ 95.8K/wkLast active Oct 23, 2026

  2. 2
    LangChainGo

    LangChainGo

    Go implementation of LangChain for writing LLM-based programs from composable building blocks.

    • 9.7K GitHub stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 9.7KLast active Oct 22, 2026

  3. 3
    OGX (formerly Llama Stack)

    OGX

    OpenAI-compatible agentic API server for inference, vector stores, files and skills, on any model or infrastructure.

    • 8.4K GitHub stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 8.4K↓ 14.2K/wkLast active Oct 24, 2026

  4. 4
    ART

    OpenPipe

    Open-source reinforcement learning framework that trains LLM agents on multi-step tasks using GRPO.

    • Most GitHub stars here (10,819)
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 10.8K↓ 2.5K/wkLast active Oct 22, 2026

Search agent frameworks for model inference → All harnesses & sdks

AI agents 23 tagged

  1. 1
    opensquilla

    TokenRhythm

    Token-efficient agent with a local router that picks the cheapest capable model for each turn.

    • 7.1K GitHub stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 7.1KLast active Oct 23, 2026

  2. 2
    openclaude

    Twigpine

    Open-source coding agent CLI that works with cloud and local model providers through one terminal workflow

    • Most GitHub stars here (34,131)
    • Active in the last 30 days

    ★ 34.1KLast active Oct 24, 2026

  3. 3
    ANUS

    anus-dev

    Terminal coding agent that sends each request to whichever free model is answering today.

    • 6.6K GitHub stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 6.6KLast active Oct 1, 2026

  4. 4
    atomic-agent

    AtomicBot-ai

    Open-source local-first agent that runs browser and file tasks on local or cloud models.

    • 3.4K GitHub stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 3.4KLast active Oct 23, 2026

  5. 5
    Mobile-Agent

    Alibaba X-PLUG

    Tongyi Lab GUI agent family for operating mobile and desktop interfaces, built on GUI-Owl models.

    • 9.3K GitHub stars
    • Open source (MIT)

    ★ 9.3KLast active Jul 7, 2026

Search AI agents for model inference → All agents

No-code builders 4 tagged

  1. 1
    Writer AI Studio

    Writer

    Control plane for models, data, guardrails and observability, plus Agent Builder v2 for deploying dockerized agent apps.

  2. 2
    Langdock

    Langdock

    Europe-hosted platform for rolling out model-agnostic chat, custom agents, workflows and an API across an organization

  3. 3
    MindStudio

    MindStudio

    No-code builder for AI agents with a free plan, 200+ models without API keys, and self-hosting on its Business plan

Search no-code builders for model inference → All no-code builders

Questions

What are the top tools for model inference?
By listing rank, the top MCP server is Pollinations, the top agent skill is claude-api and the top plugin is BAML v0. Rank weighs adoption, freshness, documentation and publisher identity; money never changes it.
How many tools does the catalog list for model inference?
173 listings are tagged for it: 34 MCP servers, 39 agent skills, 59 plugins, 14 agent frameworks, 23 AI agents and 4 no-code agent builders. Tags come from an automated enrichment pass over the top-ranked listings, so tools outside that pass are not counted.
Which AI apps do the MCP servers work with?
Of the 34 MCP servers, 33 list Claude Code, 33 list Cursor and 33 list VS Code as a supported host. Open a listing for its install command and the other hosts it names.
Which of these are published by the vendor itself?
15 of the 173 are published by the vendor behind the product, including claude-api, hf-cli and gemini-api-dev.

173 listings are tagged for this use case; the lists above show the top entries.

Related