Kode CLI is an open-source terminal-based AI coding assistant developed by shareAI-lab. Built with a specialized terminal UI and completion engine, it provides interactive coding assistance directly within developer workflows. In day-to-day operation, Kode CLI runs as a rich terminal interface featuring autocompletion for files, slash commands (such as /help and /model), and specialized sub-agents. Users interact through interactive prompts that support @mentions for targeting specific workspace files or delegating tasks to dedicated sub-agents located in the workspace configuration. Kode CLI differentiates itself through its unified completion and context injection engine. Instead of relying purely on whole-directory scans or generic prompts, it allows granular control over multi-agent workflows and context retrieval with dedicated thinking and reply visual distinctions in the terminal UI. Kode CLI is released as an open-source project on GitHub under standard community licensing. It operates with user-provided API keys or configured model endpoints.
Unified Context & Mentions — Supports @file and @agent mentions directly within the prompt to inject specific files and specialized sub-agents into context. - Interactive Slash Commands — Includes built-in slash command navigation such as /help and /model for runtime tool and configuration management. - Multi-Agent Orchestration — Loads and coordinates workspace-defined sub-agents configured in project agent directories. - Advanced Terminal Completion — Provides intelligent Tab-cycling completion across file paths, PATH binaries, slash commands, and agent references. - Visual Thinking Distinction — Clearly separates model reasoning steps and internal thought processes from final code outputs and conversational replies.
Use cases
Use Case: Targeted Multi-File Refactoring A developer needs to update API call conventions across multiple repository modules. By utilizing @file autocompletion in Kode CLI, the developer loads targeted files into context and issues refactoring commands without overloading the model's context window with irrelevant codebase files.
Use Case: Delegated Sub-Agent Code Reviews When auditing security or code quality, a developer invokes a specialized sub-agent via @agent-xxx syntax. Kode CLI coordinates the agent context and generates structured analysis and code patches within the terminal session.
Use Case: Interactive Terminal Debugging A developer investigates runtime errors by executing system commands and feeding logs into Kode CLI. The developer leverages PATH command completion and interactive slash commands to inspect variables, switch models, and apply fixes directly to source files.
Who it is for
Kode CLI is designed for software engineers and DevOps practitioners who prefer terminal-native workflows and want granular control over model context via file and agent mentions. It is less suitable for developers seeking a purely GUI-based IDE extension or completely hands-off autonomous background agents.
Install guide
Installation Install Kode CLI globally using npm or clone the repository directly (standard Node.js installation method): bash npm install -g kode-cli # Or build from source: git clone https://github.com/shareAI-lab/Kode-CLI.git cd Kode-CLI npm install npm run build
First Run Configure your environment with your model API key and start the interactive CLI: bash export ANTHROPIC_API_KEY="your-api-key-here" # Or OPENAI_API_KEY depending on your configured provider kode
Example Session Inside the Kode CLI interface, reference workspace files or agents using @ mentions: bash > @src/auth/jwt.ts Check token validation logic and add expiration checks > /model > @agent-reviewer Run a security audit on the latest changes
OpenCode — OpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.…
goose — goose is an open-source, general-purpose AI agent built in Rust, hosted under the vendor-neutral Agentic AI Foundation (AAIF) at the…
SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
OpenHands — OpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environment…
Plandex — Plandex is an open-source terminal-based AI coding agent designed to handle complex, multi-file engineering tasks in large codebases. Created by…
Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…