PluginBench
Category

Best AI & LLM tools

4508 tools in the AI & LLM category across every type.

How to choose

What these tools are for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare them

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

Each tool's page shows how to set it up: per-client config for MCP servers, a copyable install command for skills and plugins, and the source definition for agents and rules.

Skills

MCP Servers

AI orchestration platform with 100+ agents, swarm coordination, and self-learning memory for enterprise development.

68k
TypeScript
MIT
View repository →
PRPraisonAI logo

PraisonAI

Active

Build autonomous, self-reflecting AI agents and connect them to any MCP server in minutes.

8.3k
Python
MIT
View repository →
HOHoncho logo

Honcho

Active

Memory infrastructure for stateful agents: store conversations, let Honcho reason in the background, query peer representations and context.

6.7k
Python
AGPL-3.0
View repository →

One MCP gateway that lets AI agents progressively use thousands of tools without blowing up the context window.

5.8k
Python
Apache-2.0
View repository →
TRtreg.to logo

treg.to

Active

OpenRouter for tools and data—compare catalog providers and call them from one hosted MCP endpoint.

3.9k
Python
View repository →

Let AI agents build, script, and debug Unity games directly inside the Editor and in-game.

3.4k
C#
Apache-2.0
View repository →

Let Claude and other LLMs watch videos locally with intelligent frame extraction and audio transcription.

2.0k
Python
MIT
View repository →

Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.

1.4k
Python
MIT
View repository →

Browse Solana wallets, trades, markets, and onchain data via live API calls through Claude and Cursor.

1.2k
View repository →

Token-efficient AI documentation search and retrieval for coding agents and LLMs.

1.2k
TypeScript
MIT
View repository →

Autonomous spec-to-product coding agent with verified completion and 36 MCP tools.

997
Shell
View repository →
AGAgent Swarm logo

Open-source operating system for AI work: orchestrate multi-agent teams with persistent memory, Docker workers, and integrations.

845
TypeScript
MIT
View repository →
VEVestige logo

Vestige

Active

Local-first memory for AI agents that traces failures back to their root cause, no cloud required.

607
Rust
AGPL-3.0
View repository →
COCompartment logo

Durable, encrypted agentic memory that runs fully offline on your computer.

594
Python
Apache-2.0
View repository →
HAhaiku.rag logo

haiku.rag

Active

Local-first agentic RAG with hybrid search, reranking, and multimodal document retrieval with citations.

581
Python
MIT
View repository →
KRKronos logo

Kronos

Active

AI-powered stock research assistant for China A-shares, Hong Kong, and US markets with Kronos time-series forecasting

568
Python
Apache-2.0
View repository →

Adds research-backed Chain-Pattern Interrupts so AI agents pause, reflect, and avoid reasoning lock-in.

494
TypeScript
MIT
View repository →

Up-to-date library documentation for AI coding agents — now shut down (offline since June 14, 2026).

489
TypeScript
MIT
View repository →

Cut AI context usage 60-90% with smart caching, compression, and a persistent knowledge graph—no account needed.

487
JavaScript
MIT
View repository →
GRGrayMatter logo

Persistent agent memory as a single Go binary: knowledge graph, TUI observability, zero infra.

475
Go
MIT
View repository →

Long-term, multimodal memory for AI agents with character-aware profiles and mem0-compatible API

469
Python
Apache-2.0
View repository →
ENEntroly logo

Entroly

Active

Drop-in context compression and cost optimization for AI agents—reduce tokens without losing evidence.

437
Python
Apache-2.0
View repository →

AI-powered image generation with Google Gemini models—Flash speed meets 4K quality

392
Python
MIT
View repository →

Turn your team's Slack, Discord, Teams & Mattermost chats into a self-maintaining, queryable knowledge graph and wiki.

387
Python
Apache-2.0
View repository →

Ephemeral neural network swarm orchestration with WebAssembly acceleration and 84.8% SWE-Bench solve rate

374
Rust
MIT
View repository →

Local RAG server for searching private documents without sending them to APIs

369
TypeScript
MIT
View repository →
COContext Engine logo

Context Engine

Maintained

Compress logs, retrieval chunks, and code context into structured LLM-ready signal for agents and AI coding.

357
Python
MIT
View repository →

Official MCP server exposing DeepSeek V4 chat, FIM completion, model listing, and balance endpoints.

344
TypeScript
MIT
View repository →
VIVisualTorch logo

Visualize PyTorch neural network architectures as static diagrams or animated GIF reveals in multiple styles.

325
Python
MIT
View repository →

Self-hosted, markdown-based knowledge-graph memory for AI agents — persistent, decaying, self-improving retrieval with zero cloud dependency.

312
TypeScript
Apache-2.0
View repository →

Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers using tree-search and knowledge-graph reasoning.

312
Python
View repository →

Local-first persistent memory layer for AI agents with semantic search and multi-agent support.

306
Python
Apache-2.0
View repository →

Correction-first agent memory that learns how you think, with precision KPI tracking and 5 cognitive layers—local-only by default.

305
TypeScript
MIT
View repository →
TETetrees MCP logo

Own, grow, and trade portable AI agent intelligence via TAIP/1 Packs and MCP.

304
TypeScript
MIT
View repository →

Expose GraphQL operations as MCP tools for AI models to access and orchestrate your APIs.

295
Rust
MIT
View repository →

Persistent cognitive memory for AI agents—semantic search, Hebbian learning, knowledge graphs, zero LLM calls.

273
Rust
Apache-2.0
View repository →

Mine your AI coding session logs into a you.md profile so agents understand how you actually work.

268
Python
MIT
View repository →

DEPRECATED: Google AP2 agent-to-agent payment protocol server with no live endpoint.

267
JavaScript
MIT
View repository →

Give AI agents real-time ML fraud risk scoring and decisioning via Sift.

267
JavaScript
MIT
View repository →

Fiat-to-stablecoin onramp/offramp, wallets, and transfers for Latin American commerce.

267
JavaScript
MIT
View repository →

DEPRECATED: HTTP micropayments protocol by Coinbase for agentic commerce (no live endpoint).

267
JavaScript
MIT
View repository →

Ebbinghaus-based persistent memory for Claude—memories decay with time, strengthen on recall.

263
Python
View repository →
YOYourMemory logo

Persistent, self-improving memory for AI agents with biological decay and consolidation—your AI remembers across sessions.

263
Python
View repository →

Arbitrage detection and paper trading for prediction markets on Kalshi and Polymarket.

258
Python
Apache-2.0
View repository →

Persistent, consensus-validated institutional memory for AI agents with Byzantine-resilient infrastructure.

244
Go
Apache-2.0
View repository →
GFgflow-cli logo

gflow-cli

Active

CLI and MCP server to drive Google Veo video and Imagen image generation from your terminal or agent.

243
Python
MIT
View repository →

Payment layer for AI agents. Call thousands of paid APIs on Solana and Base with automatic x402 settlement.

240
TypeScript
MIT
View repository →

Local-first, open memory for AI agents—learn once, remember everywhere across Claude, Cursor, and other tools.

240
TypeScript
Apache-2.0
View repository →

Persistent memory for AI agents using spreading activation — no vector DB, no API calls, fully offline.

237
Python
MIT
View repository →

Claude Code plugin + MCP server for ComfyUI: generate images, author workflows, manage models in natural language.

235
TypeScript
MIT
View repository →

Access Alibaba Cloud DashScope Qwen models for chat, embeddings, and model discovery via MCP.

218
JavaScript
Apache-2.0
View repository →

Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture for 3D agents.

218
JavaScript
Apache-2.0
View repository →

Set autopilot scopes and daily SOL spend caps, then propose, execute, and undo agent actions on-chain.

218
JavaScript
Apache-2.0
View repository →

Route chat completions across multiple LLM providers via the three.ws multi-provider API.

218
JavaScript
Apache-2.0
View repository →

IBM watsonx.ai Granite MCP server for chat, text generation, embeddings, and tokenization.

218
JavaScript
Apache-2.0
View repository →

Pay-per-use IBM Granite AI models for chat, code, embeddings, and analysis via USDC blockchain payments.

218
JavaScript
Apache-2.0
View repository →

Pay-per-use IBM Granite AI models (chat, code, embeddings, forecasting) via x402 protocol on Base or Solana.

218
JavaScript
Apache-2.0
View repository →

Deploy AI agents on-chain on Solana with 3D avatars and an EIP-8004 identity.

218
JavaScript
Apache-2.0
View repository →

Resolve .sol names and reverse-lookup wallets for AI agents on Solana.

218
JavaScript
Apache-2.0
View repository →

3D avatars, agent memory, and on-chain identity for AI agents—generate, customize, and embed interactive 3D models.

218
JavaScript
Apache-2.0
View repository →

Plugins

Optimize multi-agent systems with workflow improvements and context management.

Claude
Codex
40k
View repository →

Persist and restore context for long-running conversations and multi-session workflows

Claude
Codex
40k
View repository →

NVIDIA DGX Spark environment setup and ML workload optimization for Grace Blackwell systems

Claude
Codex
40k
View repository →

Build LLM applications with LangGraph, RAG, vector search, and AI agent architectures

Claude
Codex
40k
View repository →

Eval-gated LLM fine-tuning with LoRA, preference optimization, and quantized export

Claude
Codex
40k
View repository →

Automate ML model training, tuning, deployment, and experiment tracking workflows

Claude
Codex
40k
View repository →

Solve competition math with adversarial verification to catch proof errors.

Claude
37k
View repository →
DEDeepEval logo

DeepEval

Active

Add LLM evaluation, tracing, and dataset management to AI applications with DeepEval.

Claude
Cursor
19k
View repository →

Access Hugging Face Hub operations and machine learning resources through Claude Code.

Claude
Cursor
11k
View repository →

Build, debug, and audit Atomic Agents Python applications with skills and diagnostic subagents.

Claude
6.3k
View repository →

Discover and integrate NVIDIA skills for GPU acceleration, CUDA, AI agents, and specialized workflows.

Claude
Codex
Cursor
3.5k
View repository →
AWaws-agents logo

Build, deploy, and operate AI agents on AWS with Bedrock, MCP tools, and production hardening.

Claude
Codex
Cursor
2.8k
View repository →

Personalized AWS guidance for startups: architecture, cost, security, migration, and AI stack optimization.

Claude
Codex
Cursor
2.8k
View repository →
SAsagemaker-ai logo

Build, train, and deploy AI models with Amazon SageMaker directly in your coding assistant.

Claude
Codex
906
View repository →

Implement AI/ML features, language models, and intelligent automation for rapid deployment.

Claude
690
View repository →

Implement AI ethics frameworks and governance policies for enterprise applications

Claude
690
View repository →

Create and convert prompts using SYMBO symbolic notation system.

Claude
690
View repository →

MCP expert subagent for Model Context Protocol integration and debugging

Claude
690
View repository →

Expert guidance on vision models, OCR, barcode detection, and visual AI tasks.

Claude
690
View repository →
TAtavily logo

tavily

Active

Real-time web search, extraction, and crawling for AI applications

Claude
486
View repository →
LAlangfuse logo

langfuse

Active

Tracing, prompt management, and evaluation tools for LLM applications via Langfuse.

Claude
Codex
Cursor
292
View repository →
PYpydantic-ai logo

Build production-grade AI agents with Pydantic AI tools, structured output, and streaming support

Claude
139
View repository →

Instrument, trace, evaluate, and iterate on AI agents with MLflow.

Claude
79
View repository →

Operate Oracle AI Data Platform Workbench in natural language—37-skill agent for Spark SQL, lakehouse ops, pipelines, and AI agents.

Claude
48
View repository →

Agent skills for Together AI inference, training, embeddings, and multimodal processing.

Claude
Cursor
36
View repository →
NOnorth-star logo

System prompt that overrides RLHF defaults: removes confirmation-seeking, scarcity thinking, and best-practice ceilings.

Claude
33
View repository →

DataRobot skills for AI/ML workflows including model training, deployment, and monitoring.

Claude
Codex
Cursor
27
View repository →

Personalized AWS guidance for startups: architecture, cost, security, migration, and AI stack rewrites.

Claude
Codex
Cursor
16
View repository →

Auto-updated reference skills for Claude, Anthropic API, MCP, and platform features.

Claude
15
View repository →
XRxros logo

xros

Active

Executable research OS: compile investigations into verifiable methodology specs and run multi-agent verification workflows.

Claude
Codex
11
View repository →
BOboltz logo

boltz

Active

Predict protein structures, screen molecules, and design binders using Boltz computational biology models.

Claude
5
View repository →
PIpixeltable logo

Build multimodal AI applications with tables, embeddings, and 25+ AI provider integrations.

Claude
Codex
Cursor
5
View repository →

Agents

Elite context engineering specialist for dynamic multi-agent AI orchestration, vector databases, and intelligent memory systems.

inherit
40k
via wshobson/agents
AIai-engineer logo

Design, build, and optimize end-to-end AI systems from model selection through production deployment.

inherit
25k
via VoltAgent/awesome-claude-code-subagents

Expert ML & Data Science agent for building end-to-end machine learning pipelines with Python.

4.4k
via vijaythecoder/awesome-claude-agents
AIai-engineer logo

ai-engineer

Abandoned

Design, build, and optimize LLM-powered applications, RAG systems, and agentic workflows for production.

sonnet
1.7k
via lst97/claude-code-sub-agents

Expert LangChain pipeline construction, document processing, and optimization

claude-sonnet-4-20250514
1.0k
via 0xfurai/claude-code-subagents
AIai-engineer logo

Build production-ready LLM applications, RAG systems, and intelligent agents with enterprise-grade architecture.

inherit
40k
via wshobson/agents

Senior data scientist for exploratory analysis, predictive modeling, and statistical insights from datasets.

sonnet
25k
via VoltAgent/awesome-claude-code-subagents
MLml-engineer logo

ml-engineer

Abandoned

End-to-end ML lifecycle management: from model development to production deployment, monitoring, and automated retraining.

sonnet
1.7k
via lst97/claude-code-sub-agents

Expert guidance on OpenAI API integration, authentication, optimization, and best practices.

claude-sonnet-4-20250514
1.0k
via 0xfurai/claude-code-subagents

Elite context engineering specialist for dynamic management, vector databases, and multi-agent AI orchestration.

inherit
40k
via wshobson/agents

Design and deploy production LLM systems with optimized inference, fine-tuning, RAG, and safety mechanisms.

inherit
25k
via VoltAgent/awesome-claude-code-subagents
PRprompt-engineer logo

Master prompt engineer architecting sophisticated LLM interactions and optimizing AI system performance.

sonnet
1.7k
via lst97/claude-code-sub-agents

Expert in building, training, and optimizing PyTorch deep learning models.

claude-sonnet-4-20250514
1.0k
via 0xfurai/claude-code-subagents

Expert data scientist for advanced analytics, machine learning, statistical modeling, and data-driven business insights.

inherit
40k
via wshobson/agents

Deploy, optimize, and serve ML models at scale with production-grade infrastructure and real-time performance.

sonnet
25k
via VoltAgent/awesome-claude-code-subagents

Master scikit-learn for machine learning: model selection, feature engineering, and hyperparameter tuning.

claude-sonnet-4-20250514
1.0k
via 0xfurai/claude-code-subagents
EVeval-judge logo

LLM judge for plugin skill quality assessment using anchored rubrics across 4 dimensions.

sonnet
40k
via wshobson/agents

Build, debug, and optimize Model Context Protocol servers and clients connecting AI systems to external tools and data sources.

sonnet
25k
via VoltAgent/awesome-claude-code-subagents

Expert TensorFlow development: build, optimize, and deploy ML models at scale.

claude-sonnet-4-20250514
1.0k
via 0xfurai/claude-code-subagents

Executes image generation requests with minimal overhead.

inherit
40k
via wshobson/agents
MLml-engineer logo

Build production ML systems with automated pipelines, model serving, and continuous monitoring.

sonnet
25k
via VoltAgent/awesome-claude-code-subagents

Fine-tuning strategist who gates training on eval baselines and routes to the right method—often recommending against training entirely.

opus
40k
via wshobson/agents

Design and implement production-grade ML infrastructure, CI/CD pipelines, and operational monitoring systems.

sonnet
25k
via VoltAgent/awesome-claude-code-subagents

Independent eval gatekeeper: builds golden sets and graders before training, gates checkpoints after.

sonnet
40k
via wshobson/agents
NLnlp-engineer logo

Build production NLP systems with transformer models, text pipelines, and multilingual support.

sonnet
25k
via VoltAgent/awesome-claude-code-subagents

Executes fine-tuning lifecycle: dataset prep, training launch, monitoring, and model export per training brief.

sonnet
40k
via wshobson/agents

Design, optimize, and test production LLM prompts for maximum effectiveness and cost efficiency.

sonnet
25k
via VoltAgent/awesome-claude-code-subagents
MLml-engineer logo

Build and deploy production ML systems with PyTorch, TensorFlow, and modern ML infrastructure.

inherit
40k
via wshobson/agents

Develop quantitative trading strategies, financial models, and risk analytics with mathematical rigor and backtesting validation.

inherit
25k
via VoltAgent/awesome-claude-code-subagents

Build scalable ML infrastructure, pipelines, and production systems with MLflow, Kubeflow, and cloud MLOps tools.

inherit
40k
via wshobson/agents

Design, train, and deploy reinforcement learning agents for robotics, gaming, and autonomous decision-making systems.

sonnet
25k
via VoltAgent/awesome-claude-code-subagents

Expert prompt engineer optimizing LLM performance through advanced techniques like chain-of-thought, constitutional AI, and production-ready systems.

inherit
40k
via wshobson/agents

Build financial models, backtest trading strategies, and analyze market data with risk metrics and portfolio optimization.

inherit
40k
via wshobson/agents

Expert vector database design, embedding optimization, and semantic search for RAG and similarity systems.

inherit
40k
via wshobson/agents

Rules

AutoML and hyperparameter optimization rules for Python ML projects using Ray Tune, Optuna, PyCaret, and time-series libraries

["**/*.py" +4
41k
via PatrickJS/awesome-cursorrules

Design patterns and best practices for building agents, tools, and workflows with Google's Agent Development Kit.

["**/*.py" +6
41k
via PatrickJS/awesome-cursorrules

Python LLM & ML development guide with modern tooling, type safety, and workflow best practices.

**/*
41k
via PatrickJS/awesome-cursorrules

PyTorch and scikit-learn for chemistry ML with best practices for molecular data.

**/*
41k
via PatrickJS/awesome-cursorrules

SQL-callable AI functions and hybrid vector+keyword search for RAG within Snowflake.

**/*
41k
via PatrickJS/awesome-cursorrules

TensorFlow and deep learning best practices for building, training, and deploying neural networks

["**/*.py" +4
41k
via PatrickJS/awesome-cursorrules

TypeScript LLM development with functional programming, multi-provider architecture, and composable APIs.

**/*
41k
via PatrickJS/awesome-cursorrules
Best AI & LLM tools | PluginBench