17 packages found
PDF extraction that checks its own work. #2 reading order accuracy — zero AI, zero GPU, zero cost.
memory-mcp-1file
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join o
Substrate-based context compaction for Claude Code. Inspectable signal weights, local-only, MCP-ready. Alternative to /c
Computer Experience Layer — MCP server for native computer use on macOS. Structured perception, reliable actions, contin
vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Sc
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) wi
A list of open-source AI projects you can use to generate income easily.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Open-source AI gateway — pool your provider keys behind one OpenAI-compatible endpoint with load balancing, failover, ci
clarifyprompt-mcp
Anchor AI FinOps to real, live cloud pricing — open source MCP server for AWS, GCP, and Azure
council of models for decision
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollam
A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-
Stop reading 5 AI answers. Get one clear recommendation. A Claude Skill for intelligent multi-model response synthesis.