oterm
Text-based terminal client for Ollama with MCP tool support.
Overview
oterm is a terminal UI for chatting with Ollama models, with persistent sessions, per-chat system prompts and model parameters. It supports MCP tools and image input for multimodal models.
- Multiple sessions
- MCP tools
- Image attachments
- Per-chat parameters
Our verdict
What we like
- Best TUI for Ollama
- Simple pip or brew install
Watch out for
- Ollama only
Works with these providers
Keys from these providers work in this app. Usage is billed by the provider at its list price.
BYOK Key Safety Score
Key handling in oterm
Grade A
Your key is stored on your device and requests go directly to the provider.
- Key storage40/40
Key stays on your device; requests go direct to the provider.
- Auditable code25/25
Open source: anyone can verify how keys are handled.
- Self-hosting8/15
Runs as a local app, but not as a self-hosted service.
- Offline option10/10
Supports local models, so no key is needed at all for private work.
- Provider choice2/10
1 provider option, which lets you pick the provider whose data terms you trust.
Whatever the score, give each app its own key, set a monthly spend limit with your provider, and revoke keys you no longer use. Read the key-safety checklist.
oterm FAQ
- Does oterm support bring your own key?
- Yes. oterm accepts your own API key from Ollama. Usage is billed by the provider at its API rates.
- Where does oterm store my API key?
- On your device. Requests go directly from oterm to the provider. Its BYOK Tools Key Safety Score is 85/100.
- Is oterm free?
- Open source: Free & open source. API usage is billed separately by your model provider.
- Is oterm open source?
- Yes. The source code is at https://github.com/ggozad/oterm.
- Can oterm run local models?
- Yes. It can connect to local runtimes such as Ollama or LM Studio, so no API key is needed for private or offline use.
- Which platforms does oterm support?
- CLI.
Community reviews
No reviews yet.
Alternatives to oterm
All command line →LLM (Simon Willison)
Command Line
CLI and Python library for interacting with any LLM.
Fabric
Command Line
Open-source framework of crowdsourced AI prompts for the CLI.
AIChat
Command Line
All-in-one LLM CLI with chat REPL, RAG, agents and a local server.
Open Interpreter
Command Line
Let language models run code on your computer from a terminal.
ShellGPT
Command Line
Command-line productivity tool for generating shell commands and answers.
Mods
Command Line
AI on the command line from Charm, built for pipelines.