Ross ROSS = Recommend OSS · open-source software intelligence for agents

Doriandarko/deepseek-engineer

A powerful coding assistant application that integrates with the DeepSeek API to process user conversations and generate structured JSON responses. Through an intuitive command-line interface, it can read local file contents, create new files, and apply diff edits to existing files in real time. observed · 2026-08-28

github.com/Doriandarko/deepseek-engineer · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

32/100

  • Activity 24
  • Release rhythm 35
  • Longevity 43

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 615
  • days_rel: n/a
  • days_push: 459
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

2238 stars · 362 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

DeepSeek Engineer is a Python command-line coding assistant that connects to the DeepSeek API and uses function calling to read, create, and edit local files from an interactive terminal conversation. It provides chain-of-thought reasoning visibility and rich, color-coded terminal feedback for AI-assisted software development.

Use cases

  • ai coding assistant in the terminal
  • have an llm read and edit my local files
  • refactor code with deepseek from the command line
  • scaffold new project files via conversation
  • review a source file and suggest improvements with ai
  • apply diff-style edits to existing code automatically

When to choose

  • you want a lightweight, open-source terminal coding agent powered by DeepSeek models
  • you prefer function-calling file operations over rigid structured JSON output
  • you want visible chain-of-thought reasoning while the assistant works
  • you need quick file reading, creation, and snippet-based editing from a chat interface

When to avoid

  • you need an IDE-integrated assistant with graphical diff views
  • you require provider-agnostic support beyond the DeepSeek API
  • you want fully autonomous multi-step agent workflows with sandboxing
  • your codebase must not be sent to a third-party LLM API

Facets

cli-tool · maturity active

agent-framework llm-inference chatbot developer-tools cli developer-tools artificial-intelligence large-language-models cli python cross-platform deepseek coding-assistant function-calling terminal-ui file-editing ai-agent command-line

1 source

Member repositories

RepositoryRoleHealth v2
Doriandarko/deepseek-engineermain32

For agents

markdown · JSON · MCP: product_card(name="Doriandarko/deepseek-engineer")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem