Trae Agent

Modular LLM software engineering agent from ByteDance with a CLI, interactive mode and several model providers.

Agent by ByteDance

IndexedMIT★ 12,152

Write a review

Get started

Setup steps are in the repository. Website · Repository

About

Trae Agent is an LLM-based agent for general software engineering tasks, driven from a command-line interface that takes natural-language instructions. It uses tools such as file editing, bash and sequential thinking, and records trajectories of its actions for debugging. Configuration is YAML-based, supports OpenAI, Anthropic, Doubao, Azure, OpenRouter, Ollama and Google Gemini, and can add MCP servers. The README describes the project as still under active development and links an arXiv technical report.

Use cases: coding, code-generation, debugging

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: codingREADME
Autonomy: Autonomous: runs tasks end to end and reports backREADME
Where you use it: TerminalREADME
Hosting: You run itREADME
Models: openai, anthropic, google, azure-openai, openrouter, ollama, doubaoREADME
Interfaces: mcpREADME
Open source: YesREADME

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Signals

Stars: 12,152
Forks: 1,359
Open issues: 138
Last commit: Feb 5, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/bytedance/trae-agent
Website: www.trae.ai/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql

More from ByteDance

Cite this page

Trae Agent. Agent Mart. https://agentmart.dev/agents/trae-agent (last updated 2026-10-24)