ggml-org/llama.vscode

Health v2 · maintenance only

Adoption not part of the score

1490 stars · 151 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A VS Code extension providing local LLM-assisted text and code completion, AI chat, and agentic coding powered by llama.cpp. It supports auto-suggestions, large-context reuse, model management, MCP tools, and access to agents via Telegram or deep links.

Use cases

• get local AI code completions in VS Code like Copilot but offline
• chat with a local LLM while coding in the editor
• run an agentic coding assistant inside VS Code
• use MCP tools with an LLM coding agent
• accept inline suggestions with Tab and word-by-word completion
• download and manage local models from Hugging Face
• control coding agents from a phone via Telegram

When to choose

• you want a free, local, privacy-preserving Copilot alternative in VS Code
• you already use llama.cpp and want editor integration
• you need agentic coding with MCP tool support
• you work on low-end hardware and need smart context reuse

When to avoid

• you prefer cloud-hosted assistants with frontier models and no local setup
• you use an editor other than VS Code or VSCodium-compatible forks
• you don't want to install and manage local llama.cpp models

Facets

plugin · maturity active

llm-inference agent-framework chatbot mcp developer-tools developer-tools large-language-models text-editors editor-plugin cross-platform windows vscode-extension code-completion llama-cpp local-llm copilot-alternative agentic-coding tab-completion ai-agents macos linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ggml-org/llama.vscode")