ex3ndr/llama-coder

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2089 stars · 169 forks observed · 2026-08-28

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

Llama Coder is a self-hosted GitHub Copilot replacement implemented as a VS Code extension. It uses Ollama running CodeLlama or Stable Code models on your own hardware to provide local AI code autocomplete.

Use cases

• replace github copilot with a local ai autocomplete
• self-hosted code completion in vs code
• run code llama autocomplete on my own gpu
• offline ai code suggestions without telemetry
• offload llm code completion to a dedicated gpu machine
• private ai pair programming on apple silicon

When to choose

• you want code completion without sending code to the cloud
• you have a capable GPU (Apple Silicon or RTX 30xx/40xx) or a dedicated inference machine
• you use VS Code and want a free Copilot alternative
• privacy and no telemetry are requirements

When to avoid

• you lack the recommended hardware (16GB+ RAM, decent GPU)
• you want multi-model support beyond CodeLlama/Stable Code
• you prefer managed cloud assistants with broader IDE support
• you need the most cutting-edge completion quality of commercial tools

Facets

plugin · maturity active

llm-inference developer-tools editor developer-tools large-language-models text-editors editor-plugin windows vscode-extension ollama code-completion self-hosted copilot-alternative codellama local-ai macos linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ex3ndr/llama-coder")