One command creates a LangChain agent starter
dcode-agent-kit creates the repeated starter structure needed for a new AI agent. It asks for the agent’s purpose, tools, model, and whether it may change files, then writes a runnable agent folder inside the current project. The generated folder includes `agent.py`, `model.py`, and a README, so there is less blank setup work and less time spent searching documentation.
`model.py` uses : `LLM_API_KEY`, optional `LLM_BASE_URL`, and `LLM_MODEL`. Any can be used, so the same agent can run through a hosted API or a local server such as llama.cpp, Ollama, vLLM, or LM Studio. The generated code is not tied to one model provider.
It is built on and released under the MIT license.
Key points
- One command creates a runnable agent folder in the current project.
- The generated files are `agent.py`, `model.py`, and a README.
- Model settings are controlled with , not hard-coded providers.
- allow both hosted APIs and s.
- The project uses and has an MIT license.