cd /news/ai-tools/whale-98-cache-hit-with-deepseek · home topics ai-tools article
[ARTICLE · art-61551] src=github.com ↗ pub= topic=ai-tools verified=true sentiment=↑ positive

Whale – 98% Cache Hit with DeepSeek

Whale, an open-source AI coding agent built specifically for DeepSeek, achieves approximately 98% prompt cache hit rates, drastically reducing costs to pennies per session. The tool supports long context (1M tokens), tool calling, dynamic workflows, and MCP servers, and is available on macOS, Linux, and Windows.

read3 min views64 publishedJul 16, 2026
Whale – 98% Cache Hit with DeepSeek
Image: Michielbdejong (auto-discovered)

简体中文 · English

Blazingly fast · ~98% prompt cache hit · Zero bloat

Whale — AI coding agent for DeepSeek, in any environment.

Long context, tools, and programmable workflows —

start in the terminal, scale to desktop and beyond.

Any platform:

npm install -g @usewhale/whale

macOS:

brew install usewhale/tap/whale

Linux:

curl -fsSL https://raw.githubusercontent.com/usewhale/Whale/main/scripts/install.sh | sh

Windows PowerShell:

Requires Windows 10 or Windows Server 2016 or later.

irm https://raw.githubusercontent.com/usewhale/Whale/main/scripts/install.ps1 | iex

Windows CMD:

powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://raw.githubusercontent.com/usewhale/Whale/main/scripts/install.ps1 | iex"
whale setup

whale

That's it. Type your question and Whale starts working — reading files, running commands, editing code, searching the web.

Need a different model provider, proxy, or custom config? See

[Configuration].

What Why it matters
💰 ~98% prompt cache hit
Whale reuses cached context aggressively — most prompts hit cache, slashing costs to pennies per session. DeepSeek pricing × Whale caching = AI-assisted coding at scale.
🐋 DeepSeek-native
Built for DeepSeek's long context (1M tokens), tool calling, and cost efficiency — no generic multi-model wrapper
🔁 Dynamic Workflows
Write JavaScript scripts that orchestrate multiple agents — fan-out research, multi-perspective review, pipelines. Claude Code compatible.
🔌 MCP
Plug in 1,000+ MCP servers for extended tooling — file ops, shell, git, web, and more
🧩 Skills + Plugins
Install community skills (code review, git workflows, etc.) or write your own

Whale's Dynamic Workflows let you script multi-agent orchestration in JavaScript:

// .whale/workflows/research.js
const results = await parallel([
  () => agent("Search for best practices in Go error handling"),
  () => agent("Find common Go error handling mistakes"),
]);
return agent("Synthesize both findings into a concise guide");

Fan-out research · Multi-perspective review · Pipeline processing · Adversarial validation

Claude Code compatible— workflow scripts written for Claude Code work as-is in Whale.

— run⚠️ Disabled by default/config

in the TUI and enableDynamic workflows

, or add[workflows] enabled = true

to.whale/config.local.toml

.

Learn more: Workflow Overview · Custom Workflow Guide

Extension What it does Get started
MCP Servers
Connect to 1,000+ tools (databases, APIs, browser automation)

Skillsdocs/skills.en.md** Subagents**docs/agents.en.md** Plugins**docs/plugins.en.md** Hooks**docs/hooks.en.mdWhale currently offers three interfaces — with more environments on the way:

Interface When to use
(TUI)whale
Interactive coding sessions — chat, review, iterate with full context
(CLI)whale ask "..."
One-shot questions, quick code reviews, single commands
whale --headless
CI/CD, automated PR reviews, scheduled tasks

Multi-model shell. Whale is DeepSeek-first — optimized for DeepSeek's caching, tools, and pricing.IDE replacement. Whale is not an IDE — it's an agent that meets you wherever you code: terminal, desktop, or CI.

Whale is in active development. Best suited for personal projects, experimental repositories, and workflows where changes can be reviewed and rolled back.

Disclaimer:This project is not affiliated with DeepSeek Inc. It is an independent open-source community project.

See CONTRIBUTING.md for local development, testing, issues, and PRs.

Current direction and available tasks: ROADMAP.md.

Security issues: SECURITY.md.

Whale stands on the shoulders of giants:

Charmbracelet— Bubble Tea, Lip Gloss, Glamour, and the entire TUI ecosystemfastschema/qjs— QuickJS Go bindings for workflow scriptingspf13/cobra— CLI frameworkalecthomas/chroma— Syntax highlightingyuin/goldmark— Markdown parsingmodelcontextprotocol/go-sdk— MCP protocol supporttetratelabs/wazero— Pure-Go WebAssembly runtime

And the many open-source libraries we depend on — thank you.

── more in #ai-tools 4 stories · sorted by recency
── more on @whale 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/whale-98-cache-hit-w…] indexed:0 read:3min 2026-07-16 ·