#202 · Primary category: AI Coding Assistants
trae-agent
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Project last updated:02/05/26
GitHub Stars
12.1K
Forks
1.3K
Contributors
52
License
MIT
Why we included this project
Trae Agent is a command-line tool that translates natural language requests into concrete coding work on your own machine, from bug fixes and unit tests to refactoring and documentation. It can route to OpenAI, Anthropic, Gemini, OpenRouter, Ollama, or Doubao, so you can match the backend to your budget or latency requirements. Because the codebase is deliberately modular and readable, it works as both a daily driver and a research subject: the project publishes a technical report, records full execution trajectories, and is structured so you can inspect or extend the agent loop. Teams that want an auditable, configurable coding agent will appreciate the YAML-driven setup, and developers curious about how agents are built can treat the source as a live reference.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.