[PR #372] docs: add Synergy DeepSeek agent guide

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/awesome-deepseek-agent/pull/372 **Author:** [@yzxoi](https://github.com/yzxoi) **Created:** 8/13/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `add-synergy-guide` --- ### 📝 Commits (1) - [`d6dc415`](https://github.com/deepseek-ai/awesome-deepseek-agent/commit/d6dc4150e3ac028c127d3bada856ceb937184db7) docs: add Synergy DeepSeek integration guide (EN + zh-CN) ### 📊 Changes **4 files changed** (+96 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) 📝 `README.zh-CN.md` (+1 -0) ➕ `docs/synergy.md` (+47 -0) ➕ `docs/synergy.zh-CN.md` (+47 -0) </details> ### 📄 Description ## Summary - Add an English Synergy integration guide (`docs/synergy.md`). - Add a Simplified Chinese Synergy integration guide (`docs/synergy.zh-CN.md`). - Add Synergy entries to both README guide tables, inserted in alphabetical order (between Reasonix and WorkBuddy/CodeBuddy). ## What the guide covers Synergy (https://github.com/SII-Holos/synergy) is an open-source AI agent workspace (Web workbench / Desktop / CLI) with DeepSeek as a built-in provider. The guide walks through: 1. Install — desktop installer, install script, or npm. 2. Configure DeepSeek — add the DeepSeek API key in Settings → Providers (no base URL needed, the built-in provider already points at `api.deepseek.com` with an OpenAI-compatible transport). 3. Use DeepSeek V4 — set `deepseek/deepseek-v4-pro` as the default model and select the **max** thinking effort. 4. First run. ## DeepSeek configuration covered - Uses current DeepSeek V4 model names (`deepseek-v4-pro`); no deprecated `deepseek-chat` / `deepseek-reasoner` names appear in the diff. - Documents the **max** reasoning effort: Synergy exposes model effort variants and the `max` variant sends `reasoning_effort: "max"`; thinking mode is on by default with `high` effort. - Mentions the DeepSeek V4 1M-token context window. - Avoids pricing claims (no pricing table included). ## Checks - [x] Model names are current (v4-pro / v4-flash, not v3 names) - [x] 1M context is configured or mentioned - [x] Max thinking effort level is supported - [x] Pricing is current (not included — guide makes no pricing claims) - [x] Config fields are verified to work in the agent (verified against Synergy's config schema, provider registry, and settings surfaces) - [x] No workarounds for already-fixed upstream bugs - [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] No images --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi commented

2026-10-26 09:48:37 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-agent/pull/372
Author: @yzxoi
Created: 8/13/2026
Status: 🔄 Open

Base: main ← Head: add-synergy-guide

📝 Commits (1)

d6dc415 docs: add Synergy DeepSeek integration guide (EN + zh-CN)

📊 Changes

4 files changed (+96 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)
📝 README.zh-CN.md (+1 -0)
➕ docs/synergy.md (+47 -0)
➕ docs/synergy.zh-CN.md (+47 -0)

📄 Description

Summary

Add an English Synergy integration guide (docs/synergy.md).
Add a Simplified Chinese Synergy integration guide (docs/synergy.zh-CN.md).
Add Synergy entries to both README guide tables, inserted in alphabetical order (between Reasonix and WorkBuddy/CodeBuddy).

What the guide covers

Synergy (https://github.com/SII-Holos/synergy) is an open-source AI agent workspace (Web workbench / Desktop / CLI) with DeepSeek as a built-in provider. The guide walks through:

Install — desktop installer, install script, or npm.
Configure DeepSeek — add the DeepSeek API key in Settings → Providers (no base URL needed, the built-in provider already points at api.deepseek.com with an OpenAI-compatible transport).
Use DeepSeek V4 — set deepseek/deepseek-v4-pro as the default model and select the max thinking effort.
First run.

DeepSeek configuration covered

Uses current DeepSeek V4 model names (deepseek-v4-pro); no deprecated deepseek-chat / deepseek-reasoner names appear in the diff.
Documents the max reasoning effort: Synergy exposes model effort variants and the max variant sends reasoning_effort: "max"; thinking mode is on by default with high effort.
Mentions the DeepSeek V4 1M-token context window.
Avoids pricing claims (no pricing table included).

Checks

Model names are current (v4-pro / v4-flash, not v3 names)
1M context is configured or mentioned
Max thinking effort level is supported
Pricing is current (not included — guide makes no pricing claims)
Config fields are verified to work in the agent (verified against Synergy's config schema, provider registry, and settings surfaces)
No workarounds for already-fixed upstream bugs
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
No images