Stars
Triton‑style kernel toolkit for MLX plus a small upstream incubator: prototype, benchmark, and upstream fusions for Apple Silicon
Running a big model on a small laptop
Alexintosh / flash-moe
Forked from danveloper/flash-moeRunning a big model on a small laptop
Production ready toolkit to run AI locally
Memory library for building stateful agents
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
How much experts do we need to serve a model?
🤗 smolagents: a barebones library for agents that think in code.
AI Agent as a Pinix Clip — agentic loop with memory, tools, and vision
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
CLI-Anything: Making ALL Software Agent-Native
The largest open-source medical AI skills library for OpenClaw🦞.
miolini / autoresearch-macos
Forked from karpathy/autoresearchAI agents running research on single-GPU nanochat training automatically adopted for MacOS
AI agents running research on single-GPU nanochat training automatically
Fractals is a recursive task orchestrator for agent swarm
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Android Phone Control With Qwen3-VL
extract all your personal data history from cursor, codex, claude-code, windsurf, and trae
Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.
A CLI tool for analyzing Claude Code/Codex CLI usage from local JSONL files.
A lightweight, lightning-fast, in-process vector database
Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台. 提供 Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Satori e.g. …
Optimized ACE-STEP-1.5 to run on 8 Gb VRAM + MusicBox UI
nalexand / LTX-2-OPTIMIZED
Forked from Lightricks/LTX-2Optimized for 8Gb inference LTX-2 audio–video generative model. + Web UI. Model created by:
