llama.cpp
- ID
- 13469
- Status
- summarized
- Published
- 12 Aug 2026, 12:51 PM
- Fetched
- 14 Aug 2026, 6:58 AM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://llama.app/
- Source URL
- https://hnrss.org/best
Summary
- Score
- 6.5
- Created
- 14 Aug 2026, 6:59 AM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
llama.cpp launched an official website at llama.app with a one-line install script, package manager support (Brew, Winget), and a local coding agent workflow via the pi-llama plugin that auto-discovers your served model with no API keys or config. The site lists supported hardware ranging from Apple Silicon to H100 clusters and highlights models like Qwen 3.6, Gemma 4, GPT-OSS, and Gemma 3.
Why it matters
If you want a fully local coding agent with zero API costs and no data leaving your machine, the `llama serve` + `pi install git:github.com/huggingface/pi-llama` + `pi` flow is now a three-command path worth trying on your existing hardware before paying for an API-based agent.
Discussion angle
Compare the pi-llama local agent workflow against API-based agents like Cursor or Claude Code on cost, latency, and code quality—especially for developers on Apple Silicon who already have the hardware but haven't tried a no-API-key agent setup.