Kode Agent
An open-source AI coding assistant that lives in your terminal, capable of understanding codebases, editing files, running commands, and orchestrating multi-model workflows.
At a Glance
Fully free and open-source under Apache License 2.0. Install via npm and bring your own API keys.
Engagement
Available On
Alternatives
Listed Apr 2026
About Kode Agent
Kode is a powerful open-source AI assistant that runs in your terminal and supports multi-model collaboration for complex development workflows. It can understand your codebase, edit files, run shell commands, and delegate tasks to specialized subagents — all from a single CLI. Built with TypeScript and licensed under Apache 2.0, Kode supports 20+ AI models and providers, making it a flexible AI development workbench rather than a single-model assistant.
- Multi-Model Collaboration — Configure unlimited AI model profiles (OpenAI, Anthropic, Alibaba, etc.) and switch between them with
Option+Mor the/modelcommand without restarting sessions. - Subagent System — Use
@run-agent-nameto delegate tasks to specialized subagents defined in Markdown files; agents can run in parallel for complex workflows. - Expert Model Consultation — Use
@ask-model-nameto consult specific AI models for specialized analysis without affecting the main conversation flow. - AGENTS.md Standard Support — Natively reads and generates AGENTS.md project documentation files, with legacy
.claudeandCLAUDE.mdcompatibility. - MCP Server Integration — Connect to Model Context Protocol servers via
.mcp.jsonor.mcprcconfig files to extend tools and context. - Skills & Plugin Marketplace — Install agent skills from any git repository using the
add-skillCLI or manage plugin marketplaces withkode plugincommands. - Smart Completion System — Fuzzy matching with hyphen-awareness, abbreviation support, and a curated database of 500+ Unix commands for intelligent terminal completions.
- Safe & YOLO Modes — Runs in YOLO mode by default for maximum productivity; use
kode --safeto require manual approval for file writes and shell commands. - Cost Tracking — Use
/costto view per-model token usage and costs across multi-model sessions. - Docker Support — Build and run Kode in a container with volume mounts for your project directory and configuration files.
- Shareable Model Config — Export and import model profiles and pointers as YAML files for team sharing via
kode models export/import. - ACP Protocol — Run Kode as an Agent Client Protocol server (
kode --acp) for integration with clients like Toad/Zed.
Community Discussions
Be the first to start a conversation about Kode Agent
Share your experience with Kode Agent, ask questions, or help others learn from your insights.
Pricing
Open Source
Fully free and open-source under Apache License 2.0. Install via npm and bring your own API keys.
- Full CLI access
- Multi-model collaboration
- Subagent system
- MCP server integration
- Skills and plugin marketplace
Capabilities
Key Features
- Multi-model collaboration with unlimited configurable AI providers
- Subagent system for task delegation and parallel orchestration
- Expert model consultation via @ask-model-name mentions
- AGENTS.md standard support with legacy .claude compatibility
- MCP server integration for tool and context extension
- Skills and plugin marketplace support
- Smart fuzzy completion with 500+ Unix command database
- Safe mode with manual approval for file writes and shell commands
- Per-model cost tracking and usage statistics
- Docker support
- Shareable YAML model configuration
- ACP (Agent Client Protocol) server mode
- YOLO mode for maximum productivity
- Linux system sandbox via bwrap
- Image paste support on macOS
- Output styles for system-prompt behavior switching