Trae Agent

ByteDance's MIT-licensed CLI coding agent for software engineering tasks.

Open Source Coding & Development
Visit Website ↗ by ByteDance

What is Trae Agent?

Trae Agent is ByteDance's open-source command-line coding agent, released under MIT and separate from the closed Trae IDE. It is a modular, research-friendly agent for general software-engineering tasks with multi-LLM support (OpenAI, Anthropic, Gemini, Ollama and more), trajectory recording, and YAML configuration. Note: the canonical repo is bytedance/trae-agent; the bytedance-seed/traeagent URL is dead.

Key features

  • Modular CLI agent architecture
  • Multi-LLM support (OpenAI, Anthropic, Doubao, Gemini, Ollama)
  • Trajectory recording for debugging
  • YAML-based configuration
  • Interactive and headless modes

Pros

  • MIT licensed from a major lab
  • Research-friendly modular design
  • Strong SWE-bench lineage

Cons

  • Repo activity has slowed (last push ~8 months ago)
  • ByteDance ownership is a governance question for some orgs
  • Needs your own model API keys

Trae Agent at a glance

PricingOpen Source
CategoryCoding & Development
Platformswindows, macos, linux
CompanyByteDance
Official websitegithub.com
coding-agentsclibytedancemulti-llmopen-source

How to choose the right Coding & Development tool

The right coding tool depends on where you write code and how much of your codebase it can understand. IDE integration is the first filter — a tool that lives in your editor, sees your project files and respects your stack will help far more than a general chatbot you paste snippets into. Look for accurate completions, clear explanations of suggested changes, and strong refactoring and debugging support for your main languages. Privacy deserves real attention: check whether your code is used for training, and whether a self-hosted or enterprise option exists for sensitive projects. Price against the hours it actually saves — most developers feel the difference within the first week of real use.

Compare all Coding & Development tools →

Trae Agent FAQs

What is Trae Agent?

Trae Agent is ByteDance's open-source command-line coding agent, released under MIT and separate from the closed Trae IDE. It is a modular, research-friendly agent for general software-engineering tasks with multi-LLM support (OpenAI, Anthropic, Gemini, Ollama and more), trajectory recording, and YAML configuration. Note: the canonical repo is bytedance/trae-agent; the bytedance-seed/traeagent URL is dead.

What are the main features of Trae Agent?

Trae Agent offers Modular CLI agent architecture, Multi-LLM support (OpenAI, Anthropic, Doubao, Gemini, Ollama), Trajectory recording for debugging, YAML-based configuration and Interactive and headless modes.

How much does Trae Agent cost?

Trae Agent is open source, so the software itself is free to download, use and self-host. Your only costs are the infrastructure you run it on and any paid services you connect to it.

What are the pros and cons of Trae Agent?

Strengths of Trae Agent include MIT licensed from a major lab; Research-friendly modular design; Strong SWE-bench lineage. On the downside, Repo activity has slowed (last push ~8 months ago); ByteDance ownership is a governance question for some orgs; Needs your own model API keys.