Llama Swap vs claude-code-delegate-local
Side-by-side comparison of two Ai projects on AiList.
Tagline
Hot-swap llama.cpp models in a running Claude Code session without losing conversation context.
MCP server that delegates Claude Code subagents to local models (LiteLLM/llama.cpp/Ollama), DeepSeek, AWS Bedrock, or any OpenAI/Anthropic-compatible backend — without losing the Claude Code orchestrator session.
GitHub Stars
5
6
Stars This Week
—
—
Language
Python
—
License
Apache-2.0
—
Built With
—
—
Views
46
36
Clicks
4
0
