Great for prototyping. I wouldn't let it touch production without review, but for getting to a working demo in an afternoon it's unbeatable.
Ollama
Run open models locally and in coding agents

About Ollama
Ollama lets developers run open models locally and use them with coding agents such as Claude Code, Codex, OpenCode, and VS Code. It supports switching models without changing the surrounding workflow.
Local models run on the user's machine, while cloud models are hosted in the US, Europe, and Singapore. Ollama states that prompts are not tracked or used for training, and that locally run data does not leave the machine.
The local offering is free. The Pro plan costs $20 per month and includes $60 of usage, with extra usage available; a Max plan includes $300 of usage.
It's the boring choice, which is the highest praise infrastructure can get. ollama run and you're done. The new agent integrations mean my coding tools talk to the local box without me doing anything.
Surprisingly good at understanding vague requests. I typed half a sentence and it figured out exactly what I meant. Minor: the docs could use more examples.
Similar tools
ECC
— Open agent harness for coding workflows, GitHub automation, and securityOpen agent harness for coding workflows, GitHub automation, and security
Hermes Agent
— Open-source self-hosted AI agent with persistent memoryOpen-source self-hosted AI agent with persistent memory
DeepSeek Harness
— A modular, plugin-based framework for building and running agentsA modular, plugin-based framework for building and running agents
Firecrawl
— Context API for searching, scraping, and interacting with the webContext API for searching, scraping, and interacting with the web

Claude Code
— An AI coding agent for terminal, IDE, web, and SlackAn AI coding agent for terminal, IDE, web, and Slack
Open WebUI
— Self-hosted interface for connecting and extending AI modelsSelf-hosted interface for connecting and extending AI models