[PR #227] docs: add Ante integration guide

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/awesome-deepseek-agent/pull/227 **Author:** [@mohanz](https://github.com/mohanz) **Created:** 6/17/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `add-ante-guide` --- ### 📝 Commits (1) - [`9d0d829`](https://github.com/deepseek-ai/awesome-deepseek-agent/commit/9d0d8291f2afbb180d90361dadabd574bfdfbf8e) docs: add Ante integration guide ### 📊 Changes **5 files changed** (+296 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) 📝 `README.zh-CN.md` (+1 -0) ➕ `docs/ante.md` (+147 -0) ➕ `docs/ante.zh-CN.md` (+147 -0) ➕ `docs/assets/ante_deepseek_auto_mode.gif` (+0 -0) </details> ### 📄 Description ## Summary Adds a bilingual integration guide for **Ante** — Antigma Labs' local-first, dependency-free Rust agent runtime — and registers it in the README tools table (alphabetical order, first data row). - `docs/ante.md` + `docs/ante.zh-CN.md` — install → DeepSeek API key → run (native `deepseek` provider) → max reasoning effort → Anthropic wire-protocol alternative → modes & extensions → pricing → configuration reference. - `docs/assets/ante_deepseek_auto_mode.gif` — TUI demo with DeepSeek-V4-Pro selected. - README / README.zh-CN table rows. Ante ships a **built-in `deepseek` provider** (OpenAI-compatible; `deepseek-v4-pro` / `deepseek-v4-flash` at 1M context), so DeepSeek works with no catalog edit. On **Terminal-Bench 2.1**, Ante drives DeepSeek-V4-Pro to **64%** — and even DeepSeek-V4-Flash to **62%** — vs **50.19%** for DeepSeek-V4 in [vals.ai](https://www.vals.ai/benchmarks/terminal-bench-2-1)'s independent eval. Both Ante results clear vals.ai's number, so whichever V4 tier that 50.19% reflects, the harness advantage holds. Public, reproducible runs on Harbor Hub: [Pro](https://hub.harborframework.com/jobs/b56ccc56-1e77-4ba9-b1b2-3b0df51c4d49), [Flash](https://hub.harborframework.com/jobs/f4c08d76-7d36-4b9e-afe6-0720f20b5269). ## Notes - All config is verified against Ante's source docs and DeepSeek's [Anthropic API guide](https://api-docs.deepseek.com/guides/anthropic_api). The Anthropic-wire example uses a `claude-opus-*` model id, which DeepSeek's endpoint reliably maps to `deepseek-v4-pro` (avoiding a silent downgrade to Flash); the native `deepseek` provider remains the recommended path for the full 1M context. - Pricing is pass-through: Ante calls the DeepSeek API directly, so users pay DeepSeek's standard rates with no markup. Figures verified against the [official pricing page](https://api-docs.deepseek.com/quick_start/pricing). - Demo gif optimized to ~646 KB (960px wide). 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 - [x] Pricing is current (input, output, cache hit), verified against [DeepSeek API Docs](https://api-docs.deepseek.com/quick_start/pricing) - [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 - [x] Images placed in `docs/assets/` with descriptive filenames and reasonable sizes --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi commented

2026-10-26 09:47:30 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-agent/pull/227
Author: @mohanz
Created: 6/17/2026
Status: 🔄 Open

Base: main ← Head: add-ante-guide

📝 Commits (1)

9d0d829 docs: add Ante integration guide

📊 Changes

5 files changed (+296 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)
📝 README.zh-CN.md (+1 -0)
➕ docs/ante.md (+147 -0)
➕ docs/ante.zh-CN.md (+147 -0)
➕ docs/assets/ante_deepseek_auto_mode.gif (+0 -0)

📄 Description

Summary

Adds a bilingual integration guide for Ante — Antigma Labs' local-first, dependency-free Rust agent runtime — and registers it in the README tools table (alphabetical order, first data row).

docs/ante.md + docs/ante.zh-CN.md — install → DeepSeek API key → run (native deepseek provider) → max reasoning effort → Anthropic wire-protocol alternative → modes & extensions → pricing → configuration reference.
docs/assets/ante_deepseek_auto_mode.gif — TUI demo with DeepSeek-V4-Pro selected.
README / README.zh-CN table rows.

Ante ships a built-in deepseek provider (OpenAI-compatible; deepseek-v4-pro / deepseek-v4-flash at 1M context), so DeepSeek works with no catalog edit. On Terminal-Bench 2.1, Ante drives DeepSeek-V4-Pro to 64% — and even DeepSeek-V4-Flash to 62% — vs 50.19% for DeepSeek-V4 in vals.ai's independent eval. Both Ante results clear vals.ai's number, so whichever V4 tier that 50.19% reflects, the harness advantage holds. Public, reproducible runs on Harbor Hub: Pro, Flash.

Notes

All config is verified against Ante's source docs and DeepSeek's Anthropic API guide. The Anthropic-wire example uses a claude-opus-* model id, which DeepSeek's endpoint reliably maps to deepseek-v4-pro (avoiding a silent downgrade to Flash); the native deepseek provider remains the recommended path for the full 1M context.
Pricing is pass-through: Ante calls the DeepSeek API directly, so users pay DeepSeek's standard rates with no markup. Figures verified against the official pricing page.
Demo gif optimized to ~646 KB (960px wide).

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
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

_{🔄 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 #227] docs: add Ante integration guide #275