ChatOllama

ChatOllama is an open-source command-line app for running AI agents with local Ollama models or hosted models from OpenAI, Anthropic and others.

ChatOllama is an open-source app for running AI agents from the terminal, installed as the chatollama-agent command. It works with OpenAI, Anthropic, Google Gemini, DeepSeek and OpenRouter through API keys, and with Ollama for models running on the user's own machine. At startup it discovers the available models, and the /models and /model commands switch between them, with the last choice saved as the default. The agent can read, list, search and edit files in the folder where it was started, with path checks that keep it inside that folder and version checks that guard against stale edits. It does not run shell commands, and conversations and API keys are not saved.

ChatOllama at a glance

Best for: Software engineer
Runs on: CLI, open source
Pricing: Free and open source (MIT); model providers charge for API use
Released: February 2024
Category: AI chat assistant
Website: github.com/sugarforever/chat-ollama

Key features

Agent CLI that runs on Node.js 24 or newer
Supports OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter and Ollama
Model discovery with /models and quick /model switching
File tools to read, list, search, write and edit workspace files
Workspace limits that reject paths outside the start folder
Offline demo mode to test the tool loop without an API key

Use it for

Chat with a local Ollama model about files in a project folder
Switch between hosted and local models from one terminal app
Let an agent make exact, checked edits to text files

Companions

Tools that articles about ChatOllama recommend using with it, each with its job.

Ollama — Built to work with Ollama.
LangChain — Framework for custom agents with memory and tools on local models.
Chroma — Local vector database for embeddings and semantic search.
Cline — Open source, any model, with approval on every step
OpenHands — Runs autonomous agents locally, in the cloud, or inside your VPC with complete control.

Alternatives to ChatOllama

Open WebUI — Run AI on your own terms with complete data privacy and self-hosting control.
Maid — Run models locally on-device or connect to remote providers securely.
Nakama — Run isolated team AI agents with chat, tools, memory, and channel integrations.
Gollama — Provides a direct Go interface for local and remote Ollama servers.
Clai — Query twelve models and local Ollama directly from your terminal using unix pipes.
LM Studio — Runs open source language models locally with real-time voice transcription.
llmspy.org — Self-host access to 530+ AI models across 24 providers with built-in tools.
IntelliBar — Connects to multiple AI models and local models without subscription fees.
LibreChat — Unifies multiple AI models and tools in one customizable, open-source platform.
SelfClaw — It aggregates multiple AI models with automatic fallback and search.
AnythingLLM — Runs fully on-device with no accounts, API keys, or token limits required.
RikkaHub — Integrates a Linux workspace for AI agents on Android devices.

All ChatOllama alternatives