#374 · Primary category： AI Coding Assistants
Whale
Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.
Project last updated：08/11/26
GitHub Stars
923
Forks
71
Contributors
7
License
MIT
Why we included this project
For teams building heavily on DeepSeek's API, Whale offers a lightweight alternative to general-purpose coding assistants. It lives in the terminal: the interactive TUI reads files, runs commands, edits code, and searches the web, while one-shot and headless modes fit automated PR reviews or CI jobs. Its DeepSeek-native design takes advantage of the provider's 1M-token context and aggressive prompt caching, hitting cache about 98% of the time, so iterating over large codebases doesn't run up session costs. Beyond single-agent chat, Whale pulls in MCP servers, community skills, and subagents, and scripted JavaScript workflows can orchestrate multiple agents or set up automated review pipelines.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.