README
the first lines# llama.vscode
Local LLM-assisted text completion, chat with AI and agentic coding extension for VS Code
## Features
- Auto-suggest on input
- Accept a suggestion with `Tab`
- Accept the first line of a suggestion with `Shift + Tab`
- Accept the next word with `Ctrl/Cmd + Right Arrow`
- Toggle the suggestion manually by pressing `Ctrl + L`
- Control max text generation time
- Configure scope of context around the cursor
- Ring context with chunks from open and edited files and yanked text
- Supports very large contexts even on low-end hardware via smart context reuse
- Display performance stats
- Llama Agent for agentic coding
- Access to the llama-vscode agents from phone via a Telegram bot
Ask a scout
a deep read
DeepSeekDeepSeek . DeepSeek V4 Pro for the deep read
ggml-org is not in a camp, so the read goes to DeepSeek, the open source scout.
10 of 10 public reads left today. Holders get 3 a day.
No read kept yet.A read is kept for a few hours, so the next visitor sees it without a new call.
Scout calls and heat are information, not advice. They describe public GitHub activity and are never a signal to trade.
Recent commits
default branch- 1dv0.0.74 . igardev
- 1dSearch files in agent chat works without RAG indexing (#250) . igardev
- 3d- Kimi k3.1 Pro predefined models added (#249) . igardev
- 3dv0.0.73 . igardev
- 4dv0.0.72 . igardev
- 4dAgent chat UI improved (#248) . igardev
- 6dv0.0.71 . igardev
- 6dweb_browser tool && llama app integration (#247) . igardev
- 7dreadme : clean-up . Georgi Gerganov
- 7dfeat: add API Route to OpenAI-compatible providers (#244) . DennyHo0917