OpenAnalyst CLI
The Universal AI Agent for Your Terminal. Default TUI, backend-only CLI, and hosted session APIs in one release flow.
Quick Install
Single command install on macOS, Linux, and Windows. No runtime dependencies.
8 Providers
OpenAnalyst, Claude, GPT, Gemini, Grok, OpenRouter, Bedrock, and Stability in one interface.
Full Terminal UI
Full-screen TUI with scrollable chat, sidebar, vim-mode, and inline interactive prompts.
Multi-Agent
Orchestrate parallel agents, autonomous loops, and swarm task decomposition.
Overview
OpenAnalyst CLI is an independent AI agent runtime that connects to major LLM providers through one interface. It ships with a default full-screen TUI, backend-only --notui mode, hosted session APIs, multi-provider streaming, tool execution, and session persistence across local and remote usage.
Why OpenAnalyst?
| Capability | OpenAnalyst CLI | Other CLI Tools |
|---|---|---|
| Providers | 8 first-class (OpenAnalyst, Anthropic, OpenAI, Gemini, xAI, OpenRouter, Bedrock, Stability) | Typically 1–2 |
| Mid-conversation switching | Session persists across providers | Not supported |
| Terminal UI | Full Full-screen TUI (default) | Basic REPL |
| Multi-agent | Built-in parallel orchestration | Limited or none |
| Multimedia | /image, /voice, /speak, /vision, /diagram | Rarely supported |
| Slash commands | 65+ | 5–15 typical |
| Binary | Native binary, zero runtime deps | Often needs Node/Python |
Key Features
Universal Provider Support
Connect to OpenAnalyst, Anthropic Claude, OpenAI GPT, Google Gemini, xAI Grok, OpenRouter (350+ models), and Amazon Bedrock — all with live model discovery and streaming.
Full Terminal UI
Scrollable chat with inline tool cards, startup banner, status line with spinner and token counts, vim-mode input, permission dialogs, and mouse navigation.
Multi-Agent Orchestration
Spawn sub-agents for parallel tasks, run autonomous agent loops with think→act→observe→verify cycles, and dispatch Mixture of Experts for complex problems.
65+ Slash Commands & 22 Tools
Git operations, multimedia generation, web scraping, planning, analysis, Playwright browser control, and more — all from your terminal.
Permission System & Sandboxing
Three permission modes (read-only, workspace-write, full-access) with inline approvals and filesystem sandboxing.
Single Native Binary
Native binary with zero runtime dependencies. Fast startup, low memory, and works on macOS, Linux, and Windows.
Documentation Pages
Getting Started
Installation →
Install on macOS, Linux, or Windows. Launch the TUI by default or run backend-only with --notui.
Quick Start →
Login, launch the TUI, and run your first prompt in 2 minutes.
Authentication →
Interactive login, API keys, credentials file, and provider resolution.
Core Concepts
LLM Providers →
8 providers, live model catalogs, model aliases, mid-conversation switching, and feature matrix.
Terminal UI →
TUI layout, keybindings, vim mode, tool call cards, voice input, agent panel.
Slash Commands →
65+ commands for session, git, multimedia, web scraping, analysis, and agents.
Built-in Tools →
22 tools: file ops, search, web, bash, PowerShell, notebooks, and more.
Advanced
Multi-Agent System →
Sub-agents, swarms, autonomous loops, MOE, model routing, effort budgets.
Configuration →
Settings hierarchy, permissions, hooks, environment variables, file structure.
MCP Integration →
Model Context Protocol: transports, server config, tool discovery, popular servers.
Runtime Architecture →
Sessions, streaming events, tools, persistence, and hosted deployment at a high level.