Analysis updated 2026-05-18
Run an AI coding assistant powered by DeepSeek instead of Claude.
Reuse Claude Code's tool interface with a different, possibly cheaper, model.
Build local tooling like Git diffs and GitHub CLI support around DeepSeek.
| yol07777/edocpeed | aaravkashyap12/advise-project-approach | abu-rayhan-alif/django-saas-kit | |
|---|---|---|---|
| Stars | 23 | 23 | 23 |
| Language | Python | Python | Python |
| Setup difficulty | moderate | easy | moderate |
| Complexity | 3/5 | 2/5 | 3/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires a DeepSeek API key and a Python virtual environment.
edoCpeeD (DeepSeek Code) is a Python project that lets you use Claude Code's interaction layer, the system that handles conversations, tool use, and command execution, but powered by DeepSeek's AI models instead of Anthropic's Claude. Think of it as a compatibility shim: Claude Code expects a certain format for messages and tool calls, but DeepSeek uses a slightly different format. This project translates between the two so DeepSeek can act as a drop-in replacement. The project handles several translation tasks: converting Claude's message format to DeepSeek's format, remapping how tool definitions and tool results are passed back and forth, and streaming responses correctly. It also re-implements locally some Claude-specific helpers, permission checking before running commands, Git integration (reading configs, diffs, branches), and GitHub CLI support, so these features still work when DeepSeek is the underlying model. You would use this if you want to run an AI coding assistant similar to Claude Code but using DeepSeek's API, which may suit different cost or access preferences. You configure it with your DeepSeek API keys and endpoints in a .env file and run it from the command line with or without its full set of local tools enabled. The tech stack is Python.
A Python compatibility layer that runs Claude Code's interface using DeepSeek's AI models instead of Claude.
Mainly Python. The stack also includes Python, DeepSeek API.
The README does not state a license.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.