AI skills and agents for developers

GLM-5.3-Flash-NVFP4

nvidia · Kit

Gives you NVIDIA's NVFP4 quantized copy of ZAI's GLM-5.3-Flash, a multimodal model for reasoning, coding and agent tasks. Meant for developers who deploy on Bl…

gemma-4-31B

google · Kit

Reads text and images and writes text, for developers and researchers who want Google DeepMind's largest dense open-weights Gemma 4 model for coding, reasoning…

DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000

diffbot · Kit

Serves a 3-bit compressed copy of DeepSeek-V4.1-Flash-1017 on two 96 GB RTX PRO 6000 Blackwell cards with vLLM, for developers who host a large coding and agen…

Spark-X2.6-1.7B-GGUF

XHToken · Kit

Runs a small 1.7B on-device language model from XHToken as 4-bit GGUF files, for chat, coding and agent tasks in English and Chinese, with adjustable thinking…

Qwen3.5-4B-3D-Coder-MTP-Repacked

prithivMLmods · Kit

A repacked copy of ccore's Qwen3.5-4B-3D-Coder, a small model tuned to write coding answers and Three.js 3D scenes, with GGUF files that support multi-token pr…

GLM-5.3-Flash-Coder-RCO-152E-GGUF

lapadatbogdan · Kit

Runs a pruned GLM-5.3-Flash coding and agent model on a home PC, as GGUF files in five quant sizes. It keeps 152 of 288 experts per layer, cutting a 321B model…

gemma-4-31B-it-GGUF

unsloth · Kit

Runs Google's Gemma 4 31B instruction-tuned model locally from Unsloth's GGUF files, with text and image input and a long context. Suits developers who want a…

Sabi-Noema

sabicap · Kit

A 27B agentic text model built on Qwen3.8-27B with open-source RL environments, reporting higher terminal and coding-agent scores, for developers building codi…

Gemma4-12B v2 Coding + Agentic Edition

yuxinlu1 · Kit

A GGUF fine-tune of Google's Gemma 4 12B instruction model for coding and tool-using agent work, sized to run offline on a machine with about 4.5 GB of free me…

Inkling

thinkingmachines · Kit

Reads text, images and audio and writes text, as a huge open multimodal model for coding assistants, agents and chatbots. For developers with multi-GPU servers…

GLM-5.3-Flash-GGUF

unsloth · Kit

Runs Unsloth's GGUF copy of the GLM-5.3-Flash text model on your own hardware, a large open model its authors aim at coding and agent work. For people with ple…

DeepHat-V1-7B

DeepHat · Kit

A 7B coding model tuned for cybersecurity and DevOps work, fine-tuned from Qwen2.5-Coder-7B. For security and operations engineers who want a small local model…

Apex-35B-V1.0

Apexintelligence-AI · Kit

A text model for coding, tool use, question answering, search and research tasks, built on Qwen3.6-35B-A3B with about 3B parameters used per token. For develop…

Qwen3.6-35B-A3B-MTP-GGUF

unsloth · Kit

Runs Qwen3.6-35B-A3B locally from Unsloth's GGUF files with multi-token prediction for faster decoding in llama.cpp. Suits developers who want a local agentic…

flint-GGUF

unsloth · Kit

Runs Flint, a 39.8B mixture-of-experts model for coding agents that uses about 2.5B parameters per token, from Unsloth GGUF files. For developers who run codin…

Beam-1.0-501B-A23B

reflection · Kit

An open instruction-tuned text model from Reflection with 501B parameters, 23B active at a time and a 1M-token context, aimed at coding, tool use and reasoning…

Qwopus3.8-27B-Coder-Flash-GGUF

Jackrong · Kit

Helps with coding and tool-using agent work as a GGUF fine-tune of Qwen3.8-27B, trained on about 200,000 code, agent and reasoning examples. For developers who…

MiMo-V2.6-Pro-RL

XiaomiMiMo · Kit

Works with text, images, video and audio in one 1.02T-parameter model that has a 1M token context. The flagship of Xiaomi's MiMo-V2.6 series, trained with larg…

Qwen2.5-Coder-7B-Instruct-GGUF

Qwen · Kit

Runs a 7B instruction-tuned coding model from Qwen on your own machine, packed as GGUF files in eight quantization levels. Made for developers who want code he…

MiniCPM5-2B

openbmb · Kit

Generates text with a dense 2B-class model made for on-device and local use, covering coding, math, long context, tool use and agent tasks in English and Chine…

whisper-large-v3-turbo

openai · Kit

OpenAI's faster Whisper model for speech recognition and speech translation, with 809M parameters and only 4 decoding layers. For developers and anyone who tra…

MiMo-V2.6-Distill-Qwen-9B

XiaomiMiMo · Kit

A 9B agentic model from Xiaomi MiMo, fine-tuned from Qwen3.5-9B for coding, agent tasks, visual coding and cybersecurity, released as a starting point for rese…

Spark-X2.6-4B-GGUF

XHToken · Kit

A compact 4B language model in GGUF form for on-device use, tuned for coding, agents and long context, with three thinking levels from none to high. Works in E…

Ornith-1.5-35B-A3B-GGUF

ornith-ai · Kit

Runs a 35B mixture-of-experts text model tuned for coding and agent work, using only about 3B parameters per token. This repository holds its GGUF files for lo…

Inkling-Small

thinkingmachines · Kit

Reads text, images and audio and replies in text, for developers building assistants, coding tools and agents. A sparse mixture-of-experts model with 276B para…

Sharp-Spark-X2.6-4B-GGUF

peculiar-ragdoll · Kit

Runs a 4B coding model with long context on a graphics card with 6 GB of memory. These GGUF quants of Spark-X2.6-4B come in three sizes and use a coding-weight…

Ripple-65B-Preview-GGUF

AtomicChat · Kit

GGUF quantized files of the 65B Ripple Preview agentic-coding model, for running locally with llama.cpp. For people who run large open models on their own hard…

Alpie Seed 9B

169Pi · Kit

Reads text, images and video and handles reasoning and coding with a 9B open-weight model built on Qwen3.5-9B, with GGUF builds for light hardware. For develop…

Qwen3.6-35B-A3B

Qwen · Kit

Helps with coding, repository-level reasoning and image-plus-text input using a 35B mixture-of-experts model that activates 3B parameters. For developers runni…

Qwen3.8-27B GGUF (ShapeLearn Quantized)

byteshape · Kit

Runs Qwen3.8-27B as GGUF files quantized by ByteShape's ShapeLearn, in five GPU-sized options with vision input and MTP speculative decoding in llama.cpp. For…

Spark-X2.6-4B

XHToken · Kit

A 4.1B language model for coding, agent work and long context in English and Chinese, with three thinking levels. For developers building agents that run on th…

Ornith-1.5-9B-GGUF

ornith-ai · Kit

Offers GGUF files of Ornith-1.5-9B, a 9B dense model trained through a self-improvement loop, for single-GPU use. Aimed at developers who want a small model wi…

Nanbeige4.3-33B

Nanbeige · Kit

A 33.1B open model for agentic coding and professional cowork tasks, built as the flagship teacher of the Nanbeige4.3 series. For developers and agent builders…

Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

ISTA-DASLab · Kit

A coding-focused GGUF build of Qwen3.8-Flash-Next with half its experts removed, cutting 354 GB at BF16 to 58.4 GB while keeping image input. For people with l…

Recursive Flint

RecursiveSI · Kit

A 39.8B mixture-of-experts language model for coding agents that investigates codebases, fixes bugs, adds features and writes tests. For developers who run the…

Qwen3.8-27B-DSpine-b16-GGUF

aj9o9 · Kit

A GGUF draft model that speeds up Qwen3.8-27B in llama.cpp through speculative decoding, reaching about 125 tokens per second on code and math on one RTX 3090.…

AREX-2

BAAI · Kit

Improves its own solutions over several rounds of propose, measure, reflect and revise, using a 27B model from BAAI. For agent researchers and developers worki…

Nex-N2.6

nex-agi · Kit

Handles computer use, coding and long tool-driven tasks as a multimodal agentic model built on GLM-5.3-Flash, in FP8 weights of about 321B parameters. For team…

Unlimited-OCR-2

baidu · Kit

Baidu's 3.3B document parsing model for long documents, using SR-SWA attention to keep decoding cost nearly flat, with Transformers and SGLang routes. Suits te…

LongCat-2.5

meituan-longcat · Kit

Meituan LongCat's multimodal mixture of experts model for long agent tasks and coding, with about 1.6 trillion total parameters and 48 billion active per token…

Multi-Agent AI - Coding

bstraehle · Kit

A Gradio demo of several AI agents built with Microsoft AutoGen that work together on a coding task. Use it in the browser on Hugging Face or run a copy on you…

3D World Generator WebGPU

ReallyFloppyPenguin · Kit

Turn a text description into an interactive 3D world, delivered as one HTML file that uses Three.js. A small coding model runs in your browser through WebGPU.

infersize

prajwalpujari16 · Kit

A browser tool that estimates the GPU memory an LLM needs, compares GPUs, sizes speculative decoding latency and estimates cloud cost per million tokens, befor…

stuntd

pollix · Kit

A browser demo that answers questions two ways, with the base Laya model zero-shot and with a small head that stuntd trained for each decision, across support…

Sygma ASR Arabic

abedbanna · Kit

A test bench that records or takes Arabic speech and compares Sygma's decoding with the base model's greedy output, with word error rates. For speech researche…

DeepSite v2

ongudidan · Kit

A coding platform powered by DeepSeek AI that generates applications from your requests. For developers, data scientists and AI engineers who want generative A…

DeepSeek-V4.1-Flash-1017

deepseek-ai · Kit

An image and text model for reasoning, coding and agent tasks with a 1M-token context window, updated from DeepSeek-V4.1-Flash. Made for developers who build a…

Qwen3.8-27B

Qwen · Kit

Reads text, images and video and replies in text, with a 27B open model tuned for coding, research and multi-step agent work. Suits developers who run models t…

Ripple-65B Preview

ricursiveAI · Kit

Runs terminal coding agents on a 65B dense language model that reads up to 1,048,576 tokens of context. Made for developers and researchers who want open Apach…

deepseek-stack

aicodeking · Skill

Helps DeepSeek V4.1 Flash and V4 Pro plan, check their work and stop at a set point, so a cheaper model behaves more like a costly one. It suits developers usi…

Microsoft Agent Skills

microsoft · Skill

Microsoft’s library of skills, agent personas and MCP setups for coding agents on Azure and Microsoft Foundry: one skill per SDK in five languages, plus deploy…

Cloudflare Skills

cloudflare · Skill

Cloudflare’s own 22 skills for coding agents that build on Cloudflare: Workers, Durable Objects, the Agents SDK, the cf and Wrangler tools, Turnstile and Cloud…

Platform Design Skills

ehmo · Skill

ehmo’s eight design skills for coding agents: iPhone, iPad, Mac, Apple Watch, Vision Pro, Apple TV, Android and the web. They hold rules from Apple’s HIG, Mate…

ClickHouse Agent Skills

ClickHouse · Skill

ClickHouse’s official skills for coding agents. They review table designs and queries against written rules, advise on architecture, troubleshoot Node.js clien…

AI Design Skills

elayadesign · Skill

Elaya’s two free design skills for AI coding tools. One builds a landing page from intake questions to conversion copy and a fixed visual system. The other des…

Emil Kowalski Design Engineering Skills

emilkowalski · Skill

Emil Kowalski’s seventeen skills for coding agents that build interfaces. They build, review and audit animations, remove motion an app does not need, and cove…

SigmaStudioz Agent Skills

sigmastudioz · Skill

Lex from SigmaStudioz’s six skills for coding agents. Three shape engineering work: domain-driven changes, timeboxed spikes and outcome reviews. Three are visu…

squirrelscan skills

squirrelscan · Skill

squirrelscan’s two skills for coding agents, MIT licensed. One teaches your agent to run the squirrel website audit program, and the other drives the loop of a…

Cheap Agent

muaaz9329 · Kit

Moves routine coding in Claude Code or Codex to a low-cost model that must prove its work with a test, so your main model's usage lasts longer.

Agentic Resource Registry

AgenticResourceRegistry · Kit

Keeps a team's coding agent skills, hooks, prompts and agent files in one self-hosted registry, with review of new entries and usage insight. Suits engineering…

Diffinery

codician-team · Kit

Hosts Git repositories, pull requests, code review and GitHub Actions workflows on your own Cloudflare account, with guarded accounts for AI coding agents.

imbo

Bearisbug · Kit

Sends messages between coding agent sessions, so a question from one agent lands inside another's running session, on your computers or a teammate's. For devel…

Harness Leaderboard

joelniklaus · Kit

Compares nine coding agents running the same open model, with three attempts per task, confidence intervals and public trajectories. For developers choosing wh…

Open 3D Skills

Moh4696 · Skill

Teaches a coding agent to build 3D and animated websites with eight skills, from three.js scenes and scroll films to transparent video, cursor-following charac…

kanzo

emanuele-em · Kit

Runs a kanban board in your browser and an MCP server from one small program, so you and your coding agents share one task list. It needs no account and no ser…

BAMA

daveebbelaar · Skill

Gives your coding agent 21 skills that clone an app you like, plan it and build it as a native Mac app in Swift and SwiftUI, with local data.

Garden Skills

ConardLi · Skill

ConardLi’s six free skills for AI coding agents: code-rendered motion video, click-through web presentations, web design, GPT Image 2 prompts and images, beaut…

Graphify

graphify-labs · Skill

Converts codebases, documentation, and technical files into a searchable knowledge graph for AI coding assistants. It uses local AST parsing to map relationshi…

Ponytail

dietrichgebert · Skill

Guides AI coding agents to write minimal code by prioritizing existing repository components and standard libraries. It adds auditing, code review, and trackin…

Spec Kit

github · Kit

Provides a toolkit of templates and processes to guide AI coding agents through feature development, bug fixing, and project assessment.

Spotify Portal AI Plugins

spotify · Kit

Integrates software catalog searches, service briefings, and operational actions into AI coding agents like Claude Code, Cursor, and Codex. It helps engineers…

Chrome DevTools for agents

ChromeDevTools · Kit

The Chrome DevTools team’s free MCP server and CLI that let your coding agent control and inspect a live Chrome. It records performance traces, reads network r…

CopilotKit

CopilotKit · Kit

CopilotKit’s open source frontend stack for AI agents, from the makers of the AG-UI protocol. Bring your own agent or use the built-in one, and give your users…

OpenCode

anomalyco · Kit

An open source AI coding agent for the terminal, the desktop and the web. It connects to many model providers and to local models. Mindket’s setup notes cover…

Agno

agno-agi · Kit

Agno’s open-source platform for building agents and running them as services. Your coding agent sets up a template with AgentOS, an API, an MCP server and Post…

Agent Skills

addyosmani · Skill

Addy Osmani’s open-source set of engineering skills for AI coding agents. Each skill is a Markdown workflow with steps, checks and exit criteria. The setup not…

OpenHands Agent Canvas

OpenHands · Kit

OpenHands’ open source, self-hosted control center for coding agents. One browser app runs the OpenHands agent, Claude Code, Codex, Gemini CLI, Pi or OpenCode…

Open Interpreter

openinterpreter · Kit

The new Rust version of Open Interpreter, a coding agent for your terminal, built on OpenAI’s Codex. You bring the model, from ChatGPT or an API key to Kimi K3…

Context Mode

mksglu · Kit

mksglu’s free, local plugin that keeps tool output out of your coding agent’s context window. Raw output stays in a sandbox and a SQLite index, and only the an…

T3 Code

pingdotgg · Kit

T3 Tools’ open source control app for the coding agents on your own computer. You control Claude Code, Codex, Cursor and others from one desktop, web or phone…

Billion Context

ranxianglei · Kit

ranxianglei’s local proxy for long coding-agent sessions. It folds old conversation into summaries that can be unfolded later, so one session can run for days…

ECC by affaan-m

affaan-m · Skill

Affaan Mustafa’s plugin of agents, skills, commands and hooks that gives Claude Code, Codex and other coding agents a routine of planning, test-first work, fre…

Claude-Mem by thedotmack

thedotmack · Kit

Alex Newman’s memory plugin for Claude Code and other coding agents. It records what the agent does in each session, turns that into short searchable notes and…

Superpowers

obra · Skill

Jesse Vincent’s skills that give your coding agent a working method: it asks what you want, gets a design approved, writes a step-by-step plan, then builds it…

Impeccable

pbakaus · Skill

Paul Bakaus’s design skill for coding agents, with 24 commands such as polish, bolder, critique and audit for steering and reviewing UI work. A rule-based dete…

Cloudflare security-audit skill

cloudflare · Skill

Cloudflare’s coding-agent skill that runs a six-phase security audit of your codebase, with a fresh agent trying to disprove each lead and every finding writte…

REA: Reverse Engineer Anything

morluto · MCP server

Pick

An MCP server and CLI by morluto that lets your coding agent study binaries, desktop and Android apps, websites and firmware on your own computer, and back eac…

Context7

upstash · MCP server

Upstash’s hosted MCP server that hands your coding assistant current docs and code examples for the library and version you ask about.

Turns a rough request into a precise task for Claude Code or any coding agent: goal, files, checks and limits.

Brief Claude Code or Codex on a coding job in a folder you shared, then check what it built in the browser