Heratiki/
locallama-mcp
Heratiki/locallama-mcpConnectors
An MCP Server that works with Roo Code/Cline.Bot/Claude Desktop to optimize costs by intelligently routing coding tasks between local LLMs free APIs and paid APIs.
43
ddalcu/
mlx-serve
ddalcu/mlx-serveTools
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
1.2k
roampal-ai/
roampal
roampal-ai/roampalConnectors
Memory that learns what works.
127
ypollak2/
llm-router
ypollak2/llm-routerConnectors
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
78
av/harborTools
Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.
3.2k
dcostenco/
prism-coder
dcostenco/prism-coderConnectors
Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.
157
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
3.7k