dmmdea

dmmdea/offload-harness

Delegate summarize/classify/extract/triage to a FREE local Gemma-4 cascade via llama.cpp. Go CLI + MCP server; never calls a cloud model. Includes a turnkey setup skill for Claude Code.

4 stars 1 forks 4 watchers Go Apache License 2.0
claude-code cli gemma golang llamacpp local-llm mcp offload
View on GitHub
2 Open Issues Need Help Last updated: Oct 29, 2026

Open Issues Need Help

View All on GitHub
Audition alternative models for the amd-gcn tier seat 6 days ago
help wanted needs-hardware amd-gcn
dmmdea/offload-harness
4

Delegate summarize/classify/extract/triage to a FREE local Gemma-4 cascade via llama.cpp. Go CLI + MCP server; never calls a cloud model. Includes a turnkey setup skill for Claude Code.

Go
#claude-code#cli#gemma#golang#llamacpp#local-llm#mcp#offload
amd-gcn profile: replace projections with your measured values (+ README GCN fix) 6 days ago
help wanted needs-hardware amd-gcn
dmmdea/offload-harness
4

Delegate summarize/classify/extract/triage to a FREE local Gemma-4 cascade via llama.cpp. Go CLI + MCP server; never calls a cloud model. Includes a turnkey setup skill for Claude Code.

Go
#claude-code#cli#gemma#golang#llamacpp#local-llm#mcp#offload