Find free and open source AI tools worth using.

Firecrawl is a web data API for searching, scraping, and interacting with the web at scale. It extracts content as clean Markdown or structured data for AI agents and apps, and is open source with a hosted service.

An open-source, code-first Python framework for building, evaluating, and deploying sophisticated AI agents with flexibility and control. ADK is model-agnostic, deployment-agnostic, and compatible with other frameworks.

OpenViking is an open-source context database for AI agents. It unifies agent memory, knowledge RAG, and skills, organizing context as a navigable filesystem for retrieval and reuse.

Model Context Protocol (MCP) is an open-source standard for connecting AI applications to external systems. It enables access to data sources, tools, and workflows. This repository offers reference MCP servers and SDK examples.

The OpenAI Agents SDK is a lightweight, provider-agnostic Python framework for building multi-agent workflows. It provides agents, handoffs, guardrails, tools, sessions, tracing, and support for realtime and voice agents.

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud, offering dense and MoE architectures, advanced visual reasoning, long context, and expanded OCR.

Qwen3 is the large language model series from Alibaba Cloud's Qwen team. It offers dense and Mixture-of-Experts models with thinking and non-thinking modes, multilingual, long-context, reasoning, coding, and agent capabilities.

LangChain is the agent engineering platform and provides create_agent, a minimal, highly configurable agent harness for composing an agent from model, tools, prompt, and middleware.

Codex CLI is a coding agent from OpenAI that runs locally on your computer. It is a lightweight terminal-based agent, and Codex is also available in IDEs, as a desktop app, and as a cloud-based agent called Codex Web.

Hunyuan3D is an all-in-one AI creation platform for 3D content. It supports text-to-3D, image-to-3D, 3D animation, texture generation, sketch-to-3D, and 3D characters, with low-poly advantages. It targets high-resolution textured 3D assets

Gemini CLI is an open-source AI agent that brings Gemini directly into the terminal. It supports built-in tools, MCP extensions, GitHub workflows, automation, and multiple authentication options.

n8n is a fair-code workflow automation platform with native AI capabilities. It combines visual building with custom code, connects to 1,500+ integrations, and can be self-hosted or used in the cloud for AI agents and business process

Unsloth is an open-source framework for running and training LLMs. It provides a local UI to run and train LLMs and diffusion models, supporting GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

Cherry Studio is an open-source, free, and powerful AI desktop client. It includes AI agents, AI chat, AI image generation, knowledge base, and more, supports all major LLMs, runs on Windows/macOS/Linux, stores data locally, and is built

Browser Use is a simple remote browser for AI agents. It offers hosted agents and managed browser infrastructure for AI startups and automation teams, with support for protected sites via SDK, REST, or CDP. It reports 82% on Internal Bench

SpaceXAI's terminal-based AI coding agent with a full-screen TUI. It understands your codebase, edits files, executes shell commands, searches the web, and manages long-running tasks. Works interactively, headlessly for scripting/CI, or

T3 Code is the open-source control plane for coding agents, orchestrating Claude Code, Codex, Antigravity, OpenCode, Cursor, and Grok from one surface.

OpenCode is an open-source AI coding agent that runs in your terminal, featuring built-in agents for development and planning, and a desktop app in beta.

Open-source AI coding agent that runs in your IDE, terminal, and desktop. Supports Plan/Act modes, MCP integration, and works with every major model provider. Trusted by 11M+ developers.

Mem0 is a drop-in memory infrastructure for AI agents and apps, providing persistent context that enables continuous learning from past user interactions for enhanced intelligence and personalization.

Open WebUI is a self-hosted AI platform that is extensible, feature-rich, and user-friendly. It supports Ollama and OpenAI-compatible APIs, providing a provider-agnostic interface for local and cloud-based models.

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Whisper is a general-purpose speech recognition model trained on a large dataset of diverse audio. It performs multilingual speech recognition, speech translation, and language identification.

SWE-agent lets your language model autonomously use tools to fix GitHub issues, find cybersecurity vulnerabilities, or perform custom coding tasks. Built by Princeton and Stanford researchers, it achieves state-of-the-art results on

Self-hosted daemon for Claude Code, Codex, Copilot, OpenCode, and Pi. Agents run on your machine with your full dev environment. Connect from phone, desktop, or web.

ego lite is a browser designed for AI agents to run automation in parallel with your own browsing. It provides isolated Spaces for agents, inherits your Chrome data, and uses code-based tools for faster, cheaper runs. Zero cost, zero

LLM inference in C/C++ with minimal setup and state-of-the-art performance on a wide range of hardware, locally and in the cloud.

Orca is an open-source Agent Development Environment (ADE) for shipping with coding agents. Run Claude Code, Codex, Gemini, Cursor CLI, and other CLI agents in parallel across isolated worktrees, with terminals, diffs, browser, and CLI in

OpenHands is an open-source, model-agnostic platform for cloud coding agents. It automates real engineering work securely and transparently, enabling teams to build faster with full control.

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

Lightpanda is a headless browser engine written in Zig, built from scratch for AI agents and automation. It executes JavaScript without graphical rendering, offering fast, scalable web automation with a minimal memory footprint—9x faster

NanoClaw is a secure, lightweight personal AI agent that runs in containers. It connects to WhatsApp, Telegram, Slack, Discord, and more, with memory, scheduled jobs, and runs on Anthropic's Agents SDK. Built to be understood and

Hermes Agent is the agent that grows with you. It creates skills from experience, improves them during use, and builds a deepening model of who you are across sessions. Runs anywhere, from a $5 VPS to serverless, and integrates with

LobeHub is a work-and-lifestyle space to find, build, and collaborate with agent teammates. It treats agents as the unit of work, providing infrastructure where humans and agents co-evolve. Organize your entire AI team with hiring,

A source-available workspace where humans and AI coding agents work as one team. Assign issues to agents like teammates—they pick up work, report progress, and hand back for review. Self-hostable, works with 26 agent CLIs, no lock-in.