tastesteak/codeseex

Analysis updated 2026-06-24

★ 34JavaScriptAudience · developerComplexity · 3/5LicenseSetup · moderate

Mindmap

mindmap
  root((CodeSeeX))
    Inputs
      Codex requests
      DeepSeek API key
      Tool calls
    Outputs
      Local Responses API
      Tool results
      Usage logs
    Use Cases
      Run DeepSeek in Codex
      Track API spend
      Use larger context
    Tech Stack
      JavaScript
      Electron
      DeepSeek API

mindmap root((CodeSeeX)) Inputs Codex requests DeepSeek API key Tool calls Outputs Local Responses API Tool results Usage logs Use Cases Run DeepSeek in Codex Track API spend Use larger context Tech Stack JavaScript Electron DeepSeek API

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Use DeepSeek V4 Pro or Flash inside the OpenAI Codex client through a local proxy

USE CASE 2

Monitor DeepSeek spend and daily token usage from a desktop manager UI

USE CASE 3

Wire Codex tools like Apply Patch and MCP to a DeepSeek-backed model

What is it built with?

JavaScriptElectronDeepSeekTOML

How does it compare?

	tastesteak/codeseex	maxforai/tokenless	systemoutprintlnhelloworld/plus-pp-helper
Stars	34	32	32
Language	JavaScript	JavaScript	JavaScript
Setup difficulty	moderate	easy	moderate
Complexity	3/5	2/5	3/5
Audience	developer	vibe coder	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires copying a generated config.toml into the Codex configuration and a working DeepSeek API key.

AGPL-3.0, free to use and modify, but anyone running a modified version as a network service must publish the modified source.

In plain English

CodeSeeX is a small desktop app that sits between OpenAI's Codex client and the DeepSeek API so a Codex user can run DeepSeek V4 models inside the Codex workflow. It runs a local server on port 8787 by default that mimics the OpenAI Responses API. Codex talks to that local endpoint, and CodeSeeX forwards the request upstream to DeepSeek. The README is explicit that the project is unofficial and not affiliated with OpenAI or DeepSeek, and that the user must follow each provider's terms. Two DeepSeek V4 models are exposed: deepseek-v4-pro and deepseek-v4-flash, both with a 1 million token context window declared in the model catalog. The bridge keeps Codex tool features working, including Apply Patch, MCP, Skills, and Plugins, and adds its own built-in tool layer: a Web Search tool, a workspace search, file reading, and patch support. There is also a desktop manager UI that shows service state, balance, usage estimates, daily logs, and tool activity. Setup involves downloading a release for Windows, macOS, or Linux, starting CodeSeeX, and copying the generated config.toml from the proxy settings page into the Codex configuration. The TOML defines a custom model_provider pointed at http://127.0.0.1:8787/v1 with wire_api set to responses. API credentials are read from the existing Codex auth setup rather than stored separately by CodeSeeX. Runtime files live under ~/.codeseex, including the model catalog JSON that Codex reads, daily JSONL log files, and optional community tool packages. Community tools are off by default and the README warns that enabling them runs local code from that tool package, so trust matters. The troubleshooting section covers balance query failures, missing DeepSeek models in Codex, and fetch-failed errors that are usually caused by a wrong base_url or a port collision. CodeSeeX is licensed under AGPL-3.0-only, which the README notes means anyone who modifies it and offers it as a network service must publish the modified source. The project is JavaScript and ships build scripts for all three desktop platforms, GitHub Actions can produce the desktop artifacts automatically.

Copy-paste prompts

Prompt 1

Install CodeSeeX on macOS, start the local proxy on 8787, and paste the config.toml into my Codex setup

Prompt 2

Switch Codex to deepseek-v4-flash through CodeSeeX and verify the 1M context window in a long file

Prompt 3

Debug a fetch-failed error in CodeSeeX caused by a wrong base_url or port collision

Prompt 4

Add a trusted community tool package to CodeSeeX under the codeseex config directory

Frequently asked questions

What is codeseex?

Local desktop bridge that translates OpenAI Codex client calls into DeepSeek API requests, letting Codex run DeepSeek V4 models with a 1M token context.

What language is codeseex written in?

Mainly JavaScript. The stack also includes JavaScript, Electron, DeepSeek.

What license does codeseex use?

AGPL-3.0, free to use and modify, but anyone running a modified version as a network service must publish the modified source.

How hard is codeseex to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is codeseex for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.