Best AI & LLM tools
3502 tools in the AI & LLM category across every type.
Skills
finetuning
Fine-tune models on Azure AI Foundry with SFT, DPO, or RFT training methods.
azure-ai
Azure AI services skill for Search, Speech, OpenAI, and Document Intelligence in coding agents
azure-aigateway
Configure Azure API Management as an AI Gateway for governing AI models, MCP tools, and agents
azure-hosted-copilot-sdk
Build, deploy, and modify GitHub Copilot SDK apps on Azure with SDK-aware scaffolding and BYOM support
image-to-video
Animate still images with the right model for your intent—HappyHorse, Wan, or Seedance on RunComfy.
nano-banana-2
Generate images with Google Nano Banana 2 (Gemini flash-tier) via RunComfy CLI — optimized prompting patterns included.
wan-2-7
Generate text-to-video with Wan 2.7's audio lip-sync and multi-reference motion control via RunComfy CLI
gpt-image-edit
Edit images with OpenAI GPT Image 2 on RunComfy—preserves identity and handles multilingual text in images.
flux-2-klein
Generate images with Flux 2 Klein (BFL's fast distilled model) via RunComfy CLI — optimized prompting patterns included.
happyhorse-1-0
Generate native 1080p text-to-video with synchronized audio via HappyHorse 1.0 on RunComfy
lark-openapi-explorer
Discover and call native Feishu/Lark OpenAPIs not covered by existing CLI commands or skills
ai-video-generation
Generate AI videos via CLI — smart model routing across HappyHorse, Kling, Seedance, Veo, Wan, Hailuo, and Dreamina.
ai-image-generation
Generate & edit images with 11+ AI models via one CLI command — smart model routing for text-to-image and image-to-image.
ai-avatar-video
Generate AI avatar and talking-head videos with lip-sync via RunComfy CLI — OmniHuman, HappyHorse, Seedance, Wan 2-7
face-swap
Swap faces or characters into images and video using the RunComfy CLI — routes across 5 models by intent.
controlnet-pose
Pose-conditioned image and video generation via RunComfy CLI—transfer motion, control character stance, or apply depth/canny conditioning.
ai-music
Generate AI music via RunComfy CLI—route to ElevenLabs premium vocals or cheap open-weights ACE Step, plus audio editing.
ace-step
Generate, inpaint, and outpaint music with ACE Step on RunComfy—tag-driven composition at $0.0002–0.0003/s.
ai-avatar-video
Create AI avatar and talking head videos via inference.sh CLI with built-in TTS and lipsync.
ai-video-generation
Generate AI videos with 40+ models (Veo, Seedance, HappyHorse, Wan, Grok) via inference.sh CLI.
ai-image-generation
Generate images with 50+ AI models including FLUX, GPT-Image-2, Gemini, and Grok via inference.sh CLI.
airunway-aks-setup
Set up AI Runway on AKS from bare cluster to running model in six steps.
analyze-project
Read-only analysis of deep learning repositories to understand structure, configs, and suspicious patterns.
ai-research-explore
Auditable deep learning research exploration with idea gating, fair comparison, and governed experiments.
explore-code
Auditable exploratory code modifications for deep learning research on isolated branches with rollback tracking.
ai-research-reproduction
README-first deep learning repository reproduction with auditable evidence and standardized outputs.
run-train
Execute and document deep learning training runs with reproducibility and status tracking.
explore-run
Bounded exploratory runs for deep learning research with fair-comparison caveats and candidate ranking.
mcp-builder
Build high-quality MCP servers that enable LLMs to interact with external services through well-designed tools.
ai-seo
Optimize content to be cited by AI search engines and LLMs like ChatGPT, Perplexity, and Google AI Overviews.
developing-genkit-js
Develop AI-powered applications using Genkit in Node.js/TypeScript with flows, tools, and multi-provider support.
developing-genkit-dart
Generates code and documentation for building AI agents in Dart using the Genkit SDK.
higgsfield-soul-id
Train a personalized face model for identity-faithful image and video generation.
firebase-ai-logic-basics
Integrate Gemini API into web apps with Firebase AI Logic for multimodal inference and structured output.
developing-genkit-go
Develop AI-powered applications in Go with Genkit—generation, flows, tools, and structured output across model providers.
claude-api
Reference for Claude API, models, pricing, streaming, tool use, MCP, agents, caching, and token counting.
google-agents-cli-eval
Evaluate and optimize ADK agents with built-in metrics, LLM-as-judge scoring, and failure analysis.
solana-dev
End-to-end Solana dApp development: wallet connection, Anchor programs, client generation, testing, and on-chain lookups.
ai-sdk
Build AI-powered features with Vercel's AI SDK—agents, chatbots, RAG, and text generation.
firebase-ai-logic
Integrate Gemini API into web apps with Firebase AI Logic—multimodal inference, structured output, and client-side AI without a backend.
developing-genkit-python
Develop AI-powered applications using Genkit in Python with flows, tools, and multi-model support.
self-improving-agent
Universal self-improving agent that learns from all skill experiences using multi-memory architecture.
agent-tools
Run 250+ AI apps via CLI—image generation, video, LLMs, search, 3D, Twitter automation.
infsh-cli
Run 250+ AI apps via inference.sh CLI—image generation, video, LLMs, search, 3D, Twitter automation.
baoyu-image-gen
Multi-provider AI image generation with text-to-image, reference images, batch processing, and aspect ratio control.
baoyu-danger-gemini-web
Generate images and text via reverse-engineered Gemini Web API with vision and multi-turn support.
firecrawl-knowledge-base
Build organized, LLM-ready knowledge bases from web content using Firecrawl.
huashu-nuwa
Auto-generate runnable AI character skills by distilling thinking frameworks from people or fuzzy needs.
mmx-cli
Generate text, images, video, speech, and music via MiniMax AI from the terminal.
prompt-engineering-patterns
Master advanced prompt engineering patterns to optimize LLM performance and reliability.
gpt-image-2
Full OpenAI-compatible GPT Image 2 coverage for text-to-image, edits, and streaming responses.
agents-sdk
Build stateful AI agents on Cloudflare Workers with persistent state, workflows, and real-time communication.
gemini-api-dev
Build applications with Gemini API hosted models, multimodal content, function calling, and structured outputs.
Agent Development
Build autonomous agents for Claude Code plugins with structured system prompts and triggering conditions.
proactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve.
tavily-best-practices
Production-ready Tavily API integration guide for LLM-powered web search, content extraction, and research in agentic workflows.
backtesting-frameworks
Build robust backtesting systems that avoid look-ahead bias, survivorship bias, and transaction costs.
grimoire-polymarket
Query Polymarket markets and manage CLOB orders via the Grimoire CLI wrapper.
seedance2-api
End-to-end AI video generation from storyboard to final output using Seedream 4.5 and Seedance 2.0
dbs-deconstruct
Deconstruct fuzzy business concepts to atomic clarity using Wittgenstein and Austrian economics.
MCP Servers
AI orchestration platform with 100+ agents, swarm coordination, and self-learning memory for enterprise development.
PraisonAI
Build autonomous, self-reflecting AI agents and connect them to any MCP server in minutes.
Honcho
Memory infrastructure for stateful agents: store conversations, let Honcho reason in the background, query peer representations and context.
ai.klavis/strata
One MCP gateway that lets AI agents progressively use thousands of tools without blowing up the context window.
Let AI agents build, script, and debug Unity games directly inside the Editor and in-game.
Let Claude and other LLMs watch videos locally with intelligent frame extraction, transcription, and searchable memory.
Memory layer for AI trading agents—record trades, recall similar setups, track strategy performance with tamper-evident audit trails.
Solana MCP by Vybe
Browse Solana wallets, trades, markets, and onchain data via live API calls through Claude and Cursor.
ai.smithery/ref-tools-ref-tools-mcp
Token-efficient AI documentation search and retrieval for coding agents and LLMs.
Vestige
Local-first memory for AI agents that traces failures to their root cause, no cloud required.
Compartment
Durable, encrypted agentic memory that runs fully offline on your computer with no API keys or cloud.
haiku.rag
Local-first agentic RAG with hybrid search, reranking, and multimodal document retrieval—answer questions about your documents with citations.
Adds research-backed Chain-Pattern Interrupts so AI agents pause, reflect, and avoid reasoning lock-in.
ai.smithery/docfork-mcp
Up-to-date library documentation for AI coding agents — now shut down (offline since June 14, 2026).
Cut LLM context usage 60-90% with smart caching, compression, and a knowledge graph that remembers what your agent figured out.
Long-term, multimodal memory for AI agents with character-aware profiles and mem0-compatible API
Entroly
Drop-in context compression and cost optimization for AI agents—reduce tokens without losing critical evidence.
AI-powered image generation with Google Gemini models—Flash speed meets 4K quality
Turn your team's Slack, Discord, Teams & Mattermost chats into a self-maintaining, queryable knowledge graph and wiki.
Ephemeral neural network swarm orchestration with WebAssembly acceleration and 84.8% SWE-Bench solve rate
Local RAG server for searching private documents without sending them to an API.
Context Engine
Compress logs, retrieval chunks, and code context into structured LLM-ready signal for agents and AI coding.
DeepSeek MCP Server
Official MCP server exposing DeepSeek V4 chat, FIM completion, model listing, and balance endpoints.
VisualTorch
Visualize PyTorch neural network architectures as static diagrams or animated GIF reveals in multiple styles.
Self-hosted, markdown-based knowledge-graph memory for AI agents — persistent, decaying, self-improving retrieval with zero cloud dependency.
Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers using tree-search and knowledge-graph reasoning.
Local-first persistent memory layer for AI agents with semantic search and multi-agent support.
Correction-first agent memory that learns how you think, with precision KPI tracking and 5 cognitive layers—local-only by default.
Apollo MCP Server
Expose GraphQL operations as MCP tools for AI models to access and orchestrate your APIs.
Persistent cognitive memory for AI agents—semantic search, Hebbian learning, knowledge graphs, zero LLM calls.
io.github.ohad6k/emulo
Mine your AI coding logs into a personal profile your agents load before every task.
Google's AP2 protocol for AI agent-to-agent payment authorization, audit, and spend control.
Give AI agents real-time ML fraud risk scoring and decisioning via Sift.
Fiat-to-stablecoin onramp/offramp, wallets, and transfers for Latin American commerce.
HTTP-native micropayments protocol by Coinbase — agents pay USDC on Base/Solana via 402 responses.
Ebbinghaus-based persistent memory for Claude—memories decay with time, strengthen on recall.
YourMemory
Persistent, self-improving memory for AI agents with biological decay and consolidation—your AI remembers across sessions.
io.github.l33tdawg/sage
Persistent, consensus-validated institutional memory for AI agents with Byzantine-resilient infrastructure.
Payment layer for AI agents. Call thousands of paid APIs on Solana and Base with automatic x402 settlement.
io.github.plur-ai/plur
Local-first, open memory for AI agents—read, correct, delete engrams shared across Claude, Cursor, and other MCP tools.
Persistent memory for AI agents using spreading activation — no vector DB, no API calls, fully offline.
Claude Code plugin + MCP server for ComfyUI: generate images, manage workflows, models, and VRAM with natural language control.
Local-first AI memory control plane with knowledge graphs, 7-layer retrieval, and governance controls for agent teams.
llmtrim
Local proxy that compresses LLM API traffic to cut token costs by 31-74% without changing answers.
io.github.RLabs-Inc/gemini-mcp
Integrate Google's Gemini 3 with Claude via 30+ tools: image/video generation, research, code execution, TTS, and web search.
Opik MCP Server
Interact with Opik prompts, traces, datasets and metrics through Claude, Cursor, or VS Code.
Persistent, local-first memory for AI coding agents. Works with Claude, GPT, Gemini, Cursor—no cloud, no vendor lock-in.
OMEGA Memory
Local-first persistent memory for AI agents. Works with Claude, GPT, Gemini, Cursor—no cloud, no vendor lock-in.
Glif
Generate images, video, and audio with Glif's media-generation agent—no API keys, just OAuth sign-in.
MCP server that retrieves GitHub Copilot customization files from the awesome-copilot repository.
Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows that evolve from failures
Query multiple LLMs simultaneously—OpenAI-compatible APIs and CLI agents—for diverse perspectives, voting, debates, and consensus.
Piia Engram
Local-first AI work identity layer—portable context across Claude Code, Cursor, Codex, and other MCP tools.
Dynamically expose focused tool subsets from multiple MCP servers based on agent personas and tasks.
Forge Orchestrator
Orchestrate Claude Code, Codex, and Gemini on shared repos with file locking and multi-tool coordination.
Generate and edit images with AI-powered prompt optimization across Gemini, OpenAI, and BytePlus Seedream.
ContextLattice
Local-first memory and context orchestrator for AI agents with durable continuity, explainable retrieval, and verified learning.
OpenFate Bazi MCP
Accurate Bazi/Four Pillars calculation with True Solar Time, Da Yun, and branch interactions for AI agents.
io.github.houtini-ai/lm
Offload routine coding tasks from Claude to a local LLM or cloud API, cutting token spend and keeping complex reasoning on Claude.
Plugins
agent-orchestration
Optimize multi-agent systems with workflow improvements and context management.
context-management
Persist and restore context for long-running conversations and multi-session workflows
dgx-spark-ops
NVIDIA DGX Spark environment setup and ML workload optimization for Grace Blackwell systems
llm-application-dev
Build LLM applications with LangGraph, RAG, vector search, and AI agent architectures
llm-finetuning
Eval-gated LLM fine-tuning with LoRA, preference optimization, and quantized export
machine-learning-ops
Automate ML model training, tuning, deployment, and experiment tracking workflows
math-olympiad
Solve competition math with adversarial verification to catch proof errors self-checking misses.
DeepEval
Add LLM evaluation, tracing, and dataset management to AI applications with DeepEval.
huggingface-skills
Hugging Face Hub operations and skill management via hf CLI
atomic-agents
Build, debug, and audit Atomic Agents Python applications with skills and diagnostic subagents.
NVIDIA Skills
Discover and integrate NVIDIA skills for GPU acceleration, CUDA, AI agents, and specialized workflows.
aws-agents
Build, deploy, and operate AI agents on AWS with Bedrock, MCP tools, and production hardening.
sagemaker-ai
Build, train, and deploy AI models with Amazon SageMaker directly in your coding assistant.
ai-engineer
Implement AI/ML features, language models, and intelligent automation for rapid deployment.
Implement AI ethics frameworks and governance policies for enterprise applications
angelos-symbo
Create and convert prompts using SYMBO symbolic notation system.
vision-specialist
Expert guidance on vision models, OCR, barcode detection, and visual AI tasks.
tavily
Real-time web search, extraction, and crawling for AI applications
langfuse
Open-source LLM observability platform for tracing, prompt management, and evaluation
pydantic-ai
Build production-grade AI agents with Pydantic AI tools, structured output, and streaming support
MLflow Skills
Instrument, trace, evaluate, and iterate on AI agents with MLflow.
Operate Oracle AI Data Platform Workbench in natural language—37-skill agent for Spark SQL, lakehouse ops, pipelines, and AI agents.
north-star
System prompt that removes confirmation-seeking, scarcity thinking, and best-practice ceiling constraints from Claude.
togetherai-skills
Agent skills for Together AI inference, training, embeddings, and multimodal processing.
datarobot-agent-skills
DataRobot skills for AI/ML workflows including model training, deployment, and monitoring.
AWS Startup Advisor
Personalized AWS guidance for startups: architecture, cost, security, migration, and AI stack rewrites.
anthropic-docs
Auto-updated reference skills for Claude, Anthropic API, MCP, and platform features.
xros
Executable research OS: compile investigations into verifiable specs, falsify claims, and run multi-agent verification with mechanical checks.
pixeltable
Build multimodal AI applications with tables, computed columns, and 25+ AI provider integrations.
boltz
Predict protein structures, screen molecules, and design binders using Boltz computational biology models.
Agents
Elite context engineering specialist for dynamic multi-agent workflows, vector databases, and intelligent memory systems.
ai-engineer
Design and deploy production-ready AI systems from model selection through monitoring and optimization.
ml-data-expert
Expert ML/Data Science avec Python pour pipelines de données, modèles ML/AI, et déploiement en production.
ai-engineer
Design, build, and optimize LLM-powered applications, RAG systems, and agentic workflows for production.
langchain-expert
Expert LangChain pipeline construction, document processing, and performance optimization.
ai-engineer
Build production-ready LLM applications, RAG systems, and intelligent agents with vector search and enterprise AI integrations.
data-scientist
Analyze data patterns, build predictive models, and extract statistical insights to drive business decisions.
ml-engineer
Design, build, and manage end-to-end ML systems from development through production deployment and monitoring.
openai-api-expert
Expert OpenAI API integration with secure authentication, error handling, and cost optimization.
Elite context engineering specialist for dynamic multi-agent AI systems, vector databases, and intelligent memory orchestration.
llm-architect
Design and deploy production LLM systems with optimized inference, fine-tuning, RAG, and multi-model orchestration.
prompt-engineer
Master prompt engineer architecting sophisticated LLM interactions and agentic workflows with advanced techniques and ethical safeguards.
pytorch-expert
Expert in building, training, and optimizing PyTorch deep learning models with best practices.
data-scientist
Expert data scientist for advanced analytics, machine learning, and statistical modeling across the full data science workflow.
Deploy, optimize, and serve ML models at scale with production-grade inference infrastructure.
scikit-learn-expert
Master scikit-learn for model selection, feature engineering, and hyperparameter tuning.
eval-judge
LLM judge for plugin skill quality assessment using anchored rubrics across 4 dimensions.
mcp-developer
Build, debug, and optimize Model Context Protocol servers and clients connecting AI systems to external tools and data sources.
tensorflow-expert
Build, optimize, and deploy machine learning models with TensorFlow expertise.
image-generator
Executes image generation requests via MCP tool integration.
ml-engineer
Build production ML systems with automated pipelines, model serving, and continuous monitoring.
llm-finetuning-architect
Gate-keeper for fine-tuning decisions: validates eval baselines and routes to the right method before any training begins.
mlops-engineer
Design and implement production-grade ML infrastructure, CI/CD pipelines, and model versioning systems for reliable, automated ML platforms.
Independent eval gatekeeper: builds golden sets and graders before training, gates checkpoints after.
nlp-engineer
Build production NLP systems with transformer models, text pipelines, and multilingual support.
Executes fine-tuning lifecycle: dataset prep, training script generation, run monitoring, and model export via Unsloth.
prompt-engineer
Design, optimize, and test production prompts for maximum LLM effectiveness and cost efficiency.
ml-engineer
Build and deploy production ML systems with PyTorch, TensorFlow, and modern ML infrastructure.
quant-analyst
Develop quantitative trading strategies, financial models, and risk analytics with mathematical rigor and backtesting validation.
mlops-engineer
Build scalable ML infrastructure, pipelines, and production systems across cloud platforms with MLflow, Kubeflow, and modern MLOps tools.
Design, train, and deploy RL agents for robotics, gaming, and autonomous decision-making systems.
prompt-engineer
Expert prompt engineer optimizing LLM performance through advanced techniques like chain-of-thought, constitutional AI, and production-ready systems.
quant-analyst
Build and backtest quantitative trading strategies with risk metrics and portfolio optimization.
vector-database-engineer
Design and optimize vector search systems for RAG, semantic retrieval, and recommendation engines.
Rules
AutoML and hyperparameter optimization rules for Python ML projects using Ray Tune, Optuna, PyCaret, and time-series libraries
Google Agent Development Kit rules for building, deploying, and evaluating multi-agent systems with tools, memory, and artifacts.
Python LLM & ML development with strict typing, modern tooling, and production-ready patterns
PyTorch and scikit-learn for chemistry ML with best practices for data handling, model evaluation, and reproducibility.
SQL-native AI functions and hybrid vector+keyword search for RAG applications within Snowflake.
TensorFlow best practices for building, training, and deploying neural networks at scale.
TypeScript development with multi-provider LLM integration, functional programming, and composable APIs.