[PR #460] docs: add Octomind integration guide

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/awesome-deepseek-agent/pull/460 **Author:** [@donk8r](https://github.com/donk8r) **Created:** 10/17/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `add-octomind` --- ### 📝 Commits (1) - [`54c969f`](https://github.com/deepseek-ai/awesome-deepseek-agent/commit/54c969f20c54fd2d59466f11224b3f5d38aaf60e) Add Octomind ### 📊 Changes **4 files changed** (+222 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) 📝 `README.zh-CN.md` (+1 -0) ➕ `docs/octomind.md` (+110 -0) ➕ `docs/octomind.zh-CN.md` (+110 -0) </details> ### 📄 Description Adds an integration guide for [Octomind](https://github.com/muvon/octomind), an open-source (Apache-2.0) AI coding agent runtime written in Rust: CLI-first, single binary, any model, MCP-native. Octomind ships a built-in `deepseek` provider (`DEEPSEEK_API_KEY`, official endpoint), so no OpenAI-compatible shim is needed. What the guide covers: - Install (install script or Homebrew) and `octomind --version` - A `deepseek.toml` config file using `deepseek:deepseek-v4-pro` / `deepseek:deepseek-v4-flash`, with `reasoning_effort = "max"` and `max_session_tokens_threshold = 1000000` for the 1M context window - Running `octomind run developer:general`, switching models with `/model`, effort with `/effort max`, and usage/cost with `/info` See [CONTRIBUTING.md](./CONTRIBUTING.md) for full guidelines. ## Checklist ### Agent Configuration - [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 - [ ] Pricing is current (input, output, cache hit), verified against [DeepSeek API Docs](https://api-docs.deepseek.com/quick_start/pricing) (N/A: the guide includes no pricing table) - [x] Config fields are verified to work in the agent - [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 - [ ] Images placed in `docs/assets/` with descriptive filenames and reasonable sizes (N/A: no images) Notes: - `reasoning_effort = "max"` is passed to DeepSeek as `reasoning_effort: "max"`; `"high"` maps to `high` and `"none"` sets `thinking.type = "disabled"`. - The official pricing page now lists Flash as `deepseek-flash` (DeepSeek-V4.1-Flash) and keeps `deepseek-v4-flash` as an accepted legacy name. The guide uses `deepseek-v4-flash` per CONTRIBUTING and adds a short note that Octomind accepts both names. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi commented

2026-10-26 09:49:47 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-agent/pull/460
Author: @donk8r
Created: 10/17/2026
Status: 🔄 Open

Base: main ← Head: add-octomind

📝 Commits (1)

54c969f Add Octomind

📊 Changes

4 files changed (+222 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)
📝 README.zh-CN.md (+1 -0)
➕ docs/octomind.md (+110 -0)
➕ docs/octomind.zh-CN.md (+110 -0)

📄 Description

Adds an integration guide for Octomind, an open-source (Apache-2.0) AI coding agent runtime written in Rust: CLI-first, single binary, any model, MCP-native. Octomind ships a built-in deepseek provider (DEEPSEEK_API_KEY, official endpoint), so no OpenAI-compatible shim is needed.

What the guide covers:

Install (install script or Homebrew) and octomind --version
A deepseek.toml config file using deepseek:deepseek-v4-pro / deepseek:deepseek-v4-flash, with reasoning_effort = "max" and max_session_tokens_threshold = 1000000 for the 1M context window
Running octomind run developer:general, switching models with /model, effort with /effort max, and usage/cost with /info

See CONTRIBUTING.md for full guidelines.

Checklist

Agent Configuration

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 (input, output, cache hit), verified against DeepSeek API Docs (N/A: the guide includes no pricing table)
Config fields are verified to work in the agent
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 (N/A: no images)

Notes:

reasoning_effort = "max" is passed to DeepSeek as reasoning_effort: "max"; "high" maps to high and "none" sets thinking.type = "disabled".
The official pricing page now lists Flash as deepseek-flash (DeepSeek-V4.1-Flash) and keeps deepseek-v4-flash as an accepted legacy name. The guide uses deepseek-v4-flash per CONTRIBUTING and adds a short note that Octomind accepts both names.

🤖 Generated with Claude Code

_{🔄 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 #460] docs: add Octomind integration guide #454