[PR #434] docs: add GEBAI integration guide (EN + zh-CN)

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/awesome-deepseek-agent/pull/434 **Author:** [@xuxinle](https://github.com/xuxinle) **Created:** 9/30/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `add-gebai-guide` --- ### 📝 Commits (1) - [`0004be5`](https://github.com/deepseek-ai/awesome-deepseek-agent/commit/0004be51bd917f32bccd474db499f66db70018a7) docs: add GEBAI integration guide (EN + zh-CN) ### 📊 Changes **4 files changed** (+122 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) 📝 `README.zh-CN.md` (+1 -0) ➕ `docs/gebai.md` (+60 -0) ➕ `docs/gebai.zh-CN.md` (+60 -0) </details> ### 📄 Description See [CONTRIBUTING.md](./CONTRIBUTING.md) for full guidelines. ## Checklist ### Agent Configuration - [x] Model names are current (`deepseek-v4-pro`; the fast model uses the current `deepseek-flash` ID, with `deepseek-v4-flash` mentioned only as the still-accepted alias) - [x] 1M context is configured (`GEBAI_LLM_MAX_CONTEXT=1000000`, `GEBAI_LLM_MAX_OUTPUT_TOKENS=384000`) - [x] Max thinking effort level is supported (`GEBAI_LLM_EXTRA_PARAMS={"reasoning_effort":"max"}`) - [x] Pricing is current (the guide includes no pricing table) - [x] Config fields are verified to work in the agent (`GEBAI_LLM_*` is GEBAI's documented configuration surface; both model IDs plus `reasoning_effort:max` were verified against the live API) - [x] No workarounds for already-fixed upstream bugs ### Documentation - [x] Both English and Chinese versions included in a single PR - [x] README table entry inserted in alphabetical order - [x] One tool per PR; unrelated tools not combined - [x] Images placed in `docs/assets/` with descriptive filenames and reasonable sizes (no images in this PR) ## Summary Adds `docs/gebai.md` + `docs/gebai.zh-CN.md` and inserts the **GEBAI** entry into both README tables (between DeepSeek-TUI and GitHub Copilot, alphabetical). **GEBAI (歌白)** is an open-source AI agent engine (Bun/TypeScript) built around a stable "conversation → tool calls → approval → execution" loop. Model access is configured through `GEBAI_LLM_*` environment variables (or the in-browser environment panel); DeepSeek V4 connects via the OpenAI-compatible `https://api.deepseek.com` endpoint. The guide covers install (`git clone` + `bun install`) → configure `deepseek-v4-pro` with 1M context, 384K max output and `reasoning_effort: max` → first run (`bun run dev` at http://127.0.0.1:3000), plus a short troubleshooting section. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi commented

2026-10-26 09:49:12 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-agent/pull/434
Author: @xuxinle
Created: 9/30/2026
Status: 🔄 Open

Base: main ← Head: add-gebai-guide

📝 Commits (1)

0004be5 docs: add GEBAI integration guide (EN + zh-CN)

📊 Changes

4 files changed (+122 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)
📝 README.zh-CN.md (+1 -0)
➕ docs/gebai.md (+60 -0)
➕ docs/gebai.zh-CN.md (+60 -0)

📄 Description

See CONTRIBUTING.md for full guidelines.

Checklist

Agent Configuration

Model names are current (deepseek-v4-pro; the fast model uses the current deepseek-flash ID, with deepseek-v4-flash mentioned only as the still-accepted alias)
1M context is configured (GEBAI_LLM_MAX_CONTEXT=1000000, GEBAI_LLM_MAX_OUTPUT_TOKENS=384000)
Max thinking effort level is supported (GEBAI_LLM_EXTRA_PARAMS={"reasoning_effort":"max"})
Pricing is current (the guide includes no pricing table)
Config fields are verified to work in the agent (GEBAI_LLM_* is GEBAI's documented configuration surface; both model IDs plus reasoning_effort:max were verified against the live API)
No workarounds for already-fixed upstream bugs

Documentation

Both English and Chinese versions included in a single PR
README table entry inserted in alphabetical order
One tool per PR; unrelated tools not combined
Images placed in docs/assets/ with descriptive filenames and reasonable sizes (no images in this PR)

Summary

Adds docs/gebai.md + docs/gebai.zh-CN.md and inserts the GEBAI entry into both README tables (between DeepSeek-TUI and GitHub Copilot, alphabetical).

GEBAI (歌白) is an open-source AI agent engine (Bun/TypeScript) built around a stable "conversation → tool calls → approval → execution" loop. Model access is configured through GEBAI_LLM_* environment variables (or the in-browser environment panel); DeepSeek V4 connects via the OpenAI-compatible https://api.deepseek.com endpoint.

The guide covers install (git clone + bun install) → configure deepseek-v4-pro with 1M context, 384K max output and reasoning_effort: max → first run (bun run dev at http://127.0.0.1:3000), plus a short troubleshooting section.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

bsakaguchi added the

pull-request

label

Rows
Columns

[PR #434] docs: add GEBAI integration guide (EN + zh-CN) #431