Best Free AI Tools

Moonshot AI's latest Kimi K2.7-Code and K2.6 models. Features a 1 trillion parameter MoE architecture. Specialized for long-horizon software engineering and agent swarms.

Alibaba's AI chat assistant and model family, accessible via web and mobile app, offering multiple model tiers.

Bytedance's AI chatbot. Intuitive interface and good general capabilities.

Open-source self-hosted AI agent that runs locally and autonomously executes tasks. Connects to WhatsApp, Telegram, Slack, Discord and other messaging platforms, with browser control, system access, and persistent memory. Developed by Peter Steinberger. Intro

Anthropic's AI coding assistant with strong long‑context understanding, complex code refactoring and agent capabilities. Available in the terminal CLI, VS Code/Cursor/JetBrains IDE plugins, standalone desktop app, and web app; tasks can also continue from the Claude iOS app or browser. Intro

OpenAI's lightweight coding agent. Supports the terminal CLI, VS Code/Cursor/Windsurf IDE extensions, Codex Web, and a Codex App/desktop app experience; it can understand and modify code directly. Intro

Google's agent-first AI coding platform built around Gemini 3, the successor to Gemini CLI. Delivered as a heavily modified VS Code-based IDE (Editor and Manager views, built-in browser/terminal) and also supports terminal interaction via the `gemini` CLI. Features autonomous agents with multi-step edit/run/verify capabilities and verifiable Artifacts (plans, screenshots, recordings). Also supports Claude 5 (Fable), Claude Sonnet 4.6, Claude Opus 4.6, and GPT-OSS-120B. Intro

An autonomous AI agent for machine learning research by Karpathy. It can formulate hypotheses, modify training code, run experiments, and evaluate results autonomously to find performance improvements.

An open-source, autonomous AI agent by Hugging Face designed to function as a specialized Machine Learning Engineer. It handles the end-to-end ML lifecycle, including researching papers, writing code, running experiments, and shipping models to the Hugging Face Hub. Intro

A powerful tool to route Claude Code requests to different models and customize any request. Supports multi-provider routing, request/response transformation, dynamic model switching, CLI model management, and GitHub Actions integration.

Agent-Oriented Programming for Building LLM Applications, Open-sourced by Alibaba

AutoGen is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks.

Autonomous financial research agent designed to perform deep analysis by thinking, planning, and learning through iteration. Specialized for the financial domain. Intro

Open Source AI Agents for your codebase in minutes. Use pre-built agents for Q&A, Testing, Debugging and System Design or create your own purpose-built agents.

Mastra is an opinionated TypeScript framework that helps you build AI applications and features quickly. It gives you the set of primitives you need: workflows, agents, RAG, integrations and evals

Open-source AI agency toolkit with 70+ specialized agent personas across engineering, design, marketing, sales, and more. Features ready-to-use agent personalities, workflow templates, and multi-tool support for Claude Code, Cursor, Aider and other AI dev tools.

A framework for building high-performance AI agents, developed by ByteDance. It provides a flexible and efficient way to orchestrate complex agent workflows with built-in support for various LLMs.

Claude Code plugin that enables using OpenAI Codex for code reviews and task delegation directly within Claude Code workflow. Provides /codex:review, /codex:adversarial-review and other commands

An open-source framework that makes all software agent-native — auto-generates production-ready CLIs for any application via a 7-phase pipeline, enabling AI agents to control any desktop software. Supports 16+ AI agent platforms including Claude Code, OpenClaw, Codex and includes CLI-Hub for community CLI discovery.

Open-source AI memory system that stores full conversations and project data locally without cloud dependencies. Organizes memories into a hierarchical "palace" structure, achieves 96.6% recall on LongMemEval benchmarks (highest scoring), supports MCP integration and works offline with local LLMs.