Ollama
FreeOllama lets you run open-weight language models on your own machine with a single command. It handles model downloads, GPU acceleration and local serving, exposing an API compatible with common OpenAI-style clients. The library includes models for chat, coding, vision and embeddings, from laptop-friendly options to larger models for workstations. Because everything runs locally, prompts and data never leave your computer — useful for confidential work, offline use and experimentation without per-token costs. It runs on macOS, Linux and Windows, and integrates with tools like Open WebUI. It is the simplest way to start with local LLMs, though large models need substantial RAM and a capable GPU.
Key features
- One-command local model serving
- OpenAI-compatible API
- Chat, coding, vision and embedding models
- Runs offline with full data privacy
- macOS, Linux and Windows support
Reviews
No reviews yet — be the first!
Log in to leave a review.
Related tools
Tools similar to this one — same category or shared tags.
NextName
NextName started as a place to research domains without bouncing between five tabs. You search a name, or a prefix or suffix, and see availability, WHOIS, DNS records, and a quick SSL summary, then compare what different registrars charge. It also helps you explore TLDs you might not have thought of. Core research works in the browser with no account. If you want to automate any of that, the HTTP APIs are documented at /docs/api. Built for indie makers, developers, and anyone who buys domains regularly. I use it when picking a name so I can check if a domain is free, peek at WHOIS and DNS, see SSL status, compare registrar prices, and browse TLDs in one place.
AutoGPT
AutoGPT began as an open-source autonomous agent project and now ships a hosted platform built around named AI specialists. You pick an expert for content, sales, research or administration, brief it in plain language, and connect the accounts it may use. A coordinating assistant called Otto routes requests to the right specialist and can pull several into one job. Experts run on schedules, and each has its own spending approval threshold. A workflow builder remains available for defining steps by hand, and the whole platform can still be self-hosted with Docker.
n8n
n8n is a workflow automation tool you can run in the cloud or host yourself. Workflows are built on a visual canvas with more than 1,000 nodes, and each run counts as one execution no matter how many steps it contains. The AI agent node, MCP server trigger and chat hosting place language models inside ordinary business automations, connected to databases, CRMs and internal APIs. Code steps support JavaScript and Python when the visual builder runs out of room. The Community Edition is free to self-host, and cloud plans are priced by monthly executions.
CrewAI
CrewAI provides both an open-source Python framework and a hosted studio for building multi-agent systems. In the studio you describe a process in plain language or sketch it on a canvas, and the builder assembles agents with roles, tools and an order of steps. Workflows export as a Python project, an MCP server or a UI component, and connect to GitHub for version control. The runtime records every model and tool call for tracing, and adds approval gates, PII redaction and role-based access for teams that need oversight before agents reach production systems.
Zed
Zed is an open-source code editor built for speed, with a native interface and GPU-accelerated rendering. It includes an agent panel that can read your project, edit files, and run commands, plus edit predictions that suggest the next change as you type. Zed connects to hosted models through a Pro subscription or to your own keys from Anthropic, OpenAI, Google, Bedrock, Ollama, and other providers. It also runs external agents such as Claude Agent and Codex CLI through the Agent Client Protocol. Multiplayer editing lets several developers share one workspace in real time.
Warp
Warp is a terminal built for coding agents, available as a desktop app and a command-line agent. You can run its agent in any terminal, launch cloud agents that work on a repository without your machine, and review what they changed. The terminal keeps command history, blocks, and workflows in a searchable drive, and indexes your codebase so the agent can find relevant files. It supports frontier and open-weight models, or you can bring your own API keys and inference endpoint. Paid plans include a monthly pool of agent usage at API rates, with add-on spending controls.