Your Local AI Assistant

A powerful command-line interface and REPL for interacting with local Ollama models.
Featuring tool execution, screen vision, memory management, and RAG capabilities.

Get Started View on GitHub
Interactive Mode
Interactive REPL Session with Markdown
Non-Interactive Mode
Non-Interactive Mode for Quick Tasks

Key Features

Interactive REPL

A modern terminal-based chat interface with rich Markdown support.

Slash Commands

/newStart a fresh session context
/historyView list of past sessions
/model-set <name>Switch active Ollama model
/clearClear the current screen
/exitClose the application

Non-Interactive Mode

Execute single-shot tasks directly from your shell.

CLI Args

-p "..."Prompt to execute immediately
--rag <db>Use specific RAG database
# Example ollama-agent -p "Summarize README.md" --rag docs_db

Deep RAG

Contextual Retrieval Augmented Generation using local vector stores.

Management Commands

/rag-create <name>Initialize a new knowledge base
/rag-add <path>Ingest file or directory
/rag-load <name>Activate a specific DB

Mem0 Memory

Long-term persistence powered by Mem0 and Qdrant.

The agent automatically stores and retrieves user preferences and context across sessions.

Actions

mem0_add_memoryTool to explicitly save facts
mem0_searchTool to recall information

Screen Vision

Give your agent eyes. Capture and analyze your screen contents.

Supported on Linux (X11/Wayland).

Syntax

@dp0Capture primary display
@dp1Capture second monitor
# Example prompt "Look at @dp0 and help me fix this error message"

Task Automation

Define reusable workflows in YAML to automate complex queries.

Task Commands

/tasksList available tasks
/task-run <id>Execute a specific task
/task-createInteractive task builder
# ~/.ollama-agent/tasks/analyze.yaml title: Code Analysis model: codellama prompt: | Analyze the current file for security vulnerabilities and suggest improvements.

MCP Support

Extend capabilities with Model Context Protocol servers.

Edit ~/.ollama-agent/mcp_servers.json to add servers.

{ "mcpServers": { "filesystem": { "command": "npx", "args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user"] } } }

Tool Execution

The agent can interact with your system to perform real-world actions.

Built-in Capabilities

execute_commandRun shell commands securely
# Example prompt "Find all Python files in src/ modified in the last 24h"

Getting Started

Requirements

Ensure you have Ollama running with a tool-capable model (like llama3.1) and an embedding model.

ollama pull gpt-oss:20b
ollama pull nomic-embed-text

Installation

pipx install git+https://github.com/arrase/ollama-agent.git

Interactive Mode

Start the chat interface to begin a session.

ollama-agent

One-off Commands

Execute a single prompt directly from your shell.

ollama-agent -p "Find large files in /var/log and summarize them"