GoatCode – open-source terminal AI agent with provider failover

GoatCode released version 2.1.10, an open-source terminal AI agent distributed as a single 85 MB binary that connects to more than 180 LLM providers and automatically retries and switches providers mid-turn when a quota is exhausted. The v2.1.10 update adds Anthropic prompt caching that cuts long-session costs by up to 90%, inline unified diffs after every write/edit, a /rewind command, up to 3 concurrent parallel subagents, and full-text /search across saved sessions. GoatCode installs via npm install -g goatcode-cli or a static binary from its releases page.

GoatCode is a single 85 MB binary that runs in your terminal. It brings 180+ LLM providers or your existing Claude/ChatGPT/Gemini/Copilot subscriptions via OAuth , and when your quota dies mid-session it automatically retries then walks your fallback chain live — switches provider mid-turn, says so, and finishes the answer. No crash, no lost context. What’s new in v2.1.10: - Prompt caching on Anthropic up to 90% cheaper long sessions; savings shown in /cost - Inline unified diffs after every write/edit - /rewind — jump transcript + files back to any turn - Parallel subagents up to 3 task calls fan out concurrently - /search + goat search — full-text across every saved session - @file Tab completion, /model sonnet aliases - True context meter real API tokens vs model window - GOAT MODE bypass that actually works: mid-turn switch, prompt resolves YES - Noir theme: deep slate + black-green surfaces Install: npm install -g goatcode-cli or grab a static binary from the releases page Repo: https://github.com/Arhan-w/GoatCode Landing: https://goatcode.vercel.app Comments URL: https://news.ycombinator.com/item?id=49670455 https://news.ycombinator.com/item?id=49670455 Points: 2 Comments: 0