# bytedance/trae-agent

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

Repository: https://github.com/bytedance/trae-agent
Canonical: https://ross.abutalabs.com/products/trae-agent
Homepage: https://www.trae.ai/
Language: Python
License: MIT
License Family: permissive
Topics: agent, llm, software-engineering
Last push: 2026-02-05T11:21:00+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 66, release rhythm 35, longevity 31
- inputs: {"age_days": 446, "days_push": 209, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12058, forks 1342 (observed 2026-08-28T04:10:51.500329+00:00)

## What it is
Trae Agent is an LLM-based CLI agent from ByteDance for general-purpose software engineering tasks, executing workflows via tools like file editing and bash execution across multiple LLM providers. Its transparent, modular architecture is designed to be research-friendly for studying and extending AI agent capabilities.

## Use cases
- automate bug fixes from natural language instructions
- run an AI coding agent from the terminal
- compare LLM providers for software engineering tasks
- research agent architectures and run ablation studies
- record and analyze agent trajectories for debugging
- refactor codebases with an interactive AI assistant

## When to choose
- you need a CLI coding agent with multi-LLM provider support
- you want a transparent, modifiable agent framework for research
- you need trajectory logging of agent actions for analysis

## When to avoid
- you need a fully polished commercial AI IDE experience
- you want a GUI-based coding assistant
- you cannot provide API keys for an LLM provider

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, cli, developer-tools
- domain: large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: coding-agent, software-engineering, multi-llm, trajectory-recording, research-friendly, ai-agents, command-line

## Member repositories
- bytedance/trae-agent (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:51.500329+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:14:58.331945+00:00, confidence not recorded.
  - readme: https://github.com/bytedance/trae-agent (fetched 2026-08-28T04:10:51.500329+00:00, sha 6ec347cc0341)
  - homepage: https://www.trae.ai/ (fetched 2026-08-29T08:12:28.779673+00:00, sha 2c379b41d6e4)
- Data as of 2026-08-30T08:39:29.467469+00:00.