deepseek-ai/awesome-deepseek-agent
1
0
Fork 0
mirror of https://github.com/deepseek-ai/awesome-deepseek-agent.git synced 2026-11-05 01:07:37 +00:00
Code Issues 354 Projects Packages Wiki Activity

[PR #467] docs: add bilingual Maxa integration guide #458

New issue
Open
opened 2026-10-26 09:49:52 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-10-26 09:49:52 +00:00
Owner
Copy link

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-agent/pull/467
Author: @maxzhao
Created: 10/20/2026
Status: 🔄 Open

Base: main ← Head: docs/add-maxa-guide

📝 Commits (1)

  • 26695c6 docs: add bilingual Maxa integration guide

📊 Changes

4 files changed (+184 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)
📝 README.zh-CN.md (+1 -0)
➕ docs/maxa.md (+91 -0)
➕ docs/maxa.zh-CN.md (+91 -0)

📄 Description

Summary

Add a DeepSeek integration guide for Maxa, a free, Apache-2.0 AI workspace inside Neovim with agentic coding, MCP tools, Abilities, and subagents.

  • Add English and Simplified Chinese guides covering installation, configuration, and first run.
  • Document the published WSL2 / Ubuntu 24.04 installation path, Neovim 0.11+ requirement, and backup/credential precautions.
  • Configure the official Responses API with deepseek-v4-pro or deepseek-flash, maximum reasoning, and a 1M context budget.
  • Add Maxa to both README tables between LobeHub and nanobot.

Maxa does not sell model access. Users supply their own DeepSeek API key, and API usage is billed by DeepSeek.

Model naming note

The guide uses deepseek-flash as recommended by the current official Models & Pricing documentation, alongside deepseek-v4-pro. This follows the current API naming rather than the older Flash name in the contribution checklist.

Validation

  • The Maxa maintainer confirmed completion of installation, configuration, and first-run verification before this documentation contribution.
  • Checked identical Lua and shell examples across the two language versions.
  • Parsed the Lua configuration and checked thinking_mode = "max", the model-name patterns, 1,000,000 context tokens, and 384,000 output tokens.
  • Checked relative links, README entry placement, and git diff --check.
  • No additional live API requests were made for this documentation-only change.

Checklist

Agent Configuration

  • Current model names (deepseek-v4-pro / deepseek-flash; see naming note above)
  • 1M context configured and explained
  • Maximum thinking effort supported (thinking_mode = "max" → reasoning.effort = "max")
  • Config fields verified in Maxa by its maintainer
  • No performance-degrading workarounds for upstream bugs
  • Pricing table: not included; API billing is explained without quoting prices

Documentation

  • English and Simplified Chinese versions included in this PR
  • Both README table entries inserted in alphabetical order
  • One tool per PR; only four documentation files changed
  • Images: not included

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

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/awesome-deepseek-agent/pull/467 **Author:** [@maxzhao](https://github.com/maxzhao) **Created:** 10/20/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `docs/add-maxa-guide` --- ### 📝 Commits (1) - [`26695c6`](https://github.com/deepseek-ai/awesome-deepseek-agent/commit/26695c6593c4d27253e4a387bd5f0c4c30c67c1a) docs: add bilingual Maxa integration guide ### 📊 Changes **4 files changed** (+184 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) 📝 `README.zh-CN.md` (+1 -0) ➕ `docs/maxa.md` (+91 -0) ➕ `docs/maxa.zh-CN.md` (+91 -0) </details> ### 📄 Description ## Summary Add a DeepSeek integration guide for [Maxa](https://github.com/maxzhao/maxa), a free, Apache-2.0 AI workspace inside Neovim with agentic coding, MCP tools, Abilities, and subagents. - Add English and Simplified Chinese guides covering installation, configuration, and first run. - Document the published WSL2 / Ubuntu 24.04 installation path, Neovim 0.11+ requirement, and backup/credential precautions. - Configure the official Responses API with `deepseek-v4-pro` or `deepseek-flash`, maximum reasoning, and a 1M context budget. - Add Maxa to both README tables between LobeHub and nanobot. Maxa does not sell model access. Users supply their own DeepSeek API key, and API usage is billed by DeepSeek. ## Model naming note The guide uses `deepseek-flash` as recommended by the current [official Models & Pricing documentation](https://api-docs.deepseek.com/quick_start/pricing), alongside `deepseek-v4-pro`. This follows the current API naming rather than the older Flash name in the contribution checklist. ## Validation - The Maxa maintainer confirmed completion of installation, configuration, and first-run verification before this documentation contribution. - Checked identical Lua and shell examples across the two language versions. - Parsed the Lua configuration and checked `thinking_mode = "max"`, the model-name patterns, 1,000,000 context tokens, and 384,000 output tokens. - Checked relative links, README entry placement, and `git diff --check`. - No additional live API requests were made for this documentation-only change. ## Checklist ### Agent Configuration - [x] Current model names (`deepseek-v4-pro` / `deepseek-flash`; see naming note above) - [x] 1M context configured and explained - [x] Maximum thinking effort supported (`thinking_mode = "max"` → `reasoning.effort = "max"`) - [x] Config fields verified in Maxa by its maintainer - [x] No performance-degrading workarounds for upstream bugs - Pricing table: not included; API billing is explained without quoting prices ### Documentation - [x] English and Simplified Chinese versions included in this PR - [x] Both README table entries inserted in alphabetical order - [x] One tool per PR; only four documentation files changed - Images: not included --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/awesome-deepseek-agent#458
No description provided.