90/100
otelite
Lightweight OpenTelemetry receiver and local dashboard for LLM development — single binary, zero dependencies
Curated collection
Best AI Tools Directory
Compare 4,813 quality-filtered AI tools—LLMs, coding agents, image generators, and automation—using public popularity, activity, and licensing data.
Explore quality-filtered AI tools for chat, coding agents, image generation, RAG, and automation. Rankings use public popularity and project activity—not paid placements.
Compare your options
Popular comparisons
- Langchain-Chatchat vs best-of-ml-python
- PentestGPT vs best-of-ml-python
- best-of-ml-python vs PocketFlow
- best-of-ml-python vs inkos
- best-of-ml-python vs crawl4ai
- best-of-ml-python vs agents
- xgboost vs best-of-ml-python
- Langchain-Chatchat vs PentestGPT
- Langchain-Chatchat vs PocketFlow
- Langchain-Chatchat vs inkos
- Langchain-Chatchat vs crawl4ai
- Langchain-Chatchat vs agents
90/100
claude-brain
Sync your Claude Code brain across machines — memory, skills, agents, rules, and settings with intelligent semantic merge. Git-based, auto-sync hooks.
90/100
zapcode
TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool calling.
90/100
ros2_mcp
Advanced MCP Server ROS 2 bridging AI agents straight into robotics
90/100
Hexis
Centrally manage AI-agent skills, tools, context, permissions, and identity across your entire org. Self-hosted, Git-backed and MCP-native.
90/100
ml-quant-trading
PyTorch research stack for ML multi-factor trading: 213 factors, bias correction, portfolio optimization, and vectorized backtesting.
90/100
speak-like-you-eat
Translate AI garbage to human language. A Pi package for plain-language rewrites.
90/100
solvent-agent
Offline-first demo of a self-funding analyst agent: earns via Stripe, fulfils with NVIDIA Nemotron, pays vendor bills within guardrails, never works at a loss.
90/100
mloda
mloda.ai - Open Data Access for AI and ML. Plugin-based. Traceable. Framework-agnostic.
90/100
llm-router
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
90/100
Remit
数模Agent（数模 Agent）/ 数学建模 AI 助手：多智能体协作完成题意分析、文献检索、建模、代码执行与论文写作，支持人工审核和断点恢复。Local-first multi-agent workben
90/100
agents-shipgate
The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces
90/100
commonplace
The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.
90/100
llm_context_benchmarks
📊 LLM Context Benchmarks - A comprehensive benchmarking tool for testing LLMs with varying context sizes using Ollama. Features dual benchmark modes (API/CLI
90/100
PrismFlowAgent
全栈资讯处理与 AI Agent 系统。它能够自动化地从全球多源渠道抓取高质量资讯，利用顶级大语言模型进行深度总结，并将其分发至多种终端
90/100
AI-Agents-public
Production-grade agent skills and Custom GPT prompts for ChatGPT, Claude Code, and Codex. 140 skills, 28 agents, Agent Skills spec compliant.
90/100
elements
NVIDIA Design System and UI Agent Harness for AI/ML Factories, Robotics, and Autonomous Vehicles
90/100
DeepSec
DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time
90/100
meta-configurator
MetaConfigurator is a JSON Schema Editor and Form Generator with AI assistance. It can also generate Code and Documentation from schemas.
90/100
mcp-open-library
A Model Context Protocol (MCP) server for the Internet Archive's Open Library API that enables AI assistants to search for book and author information.
90/100
build-world
Build interactive 3D worlds with high-quality assets from Thrixel and your AI agent of choice.
90/100
Agent-Git
Agent Git: Agent Version Control, Open-Branching, and Reinforcement Learning MDP for Agentic AI. A Standalone Agentic AI Infrastructure Layer for LangGraph Ecos
90/100
airgapped-offfline-rag
Secure, locally-run Retrieval-Augmented Generation system for document-based question-answering, utilizing Llama 3, Mistral, and Gemini models with a user-frien
90/100
burn
See what's burning your Kubernetes budget