Agent infrastructure
llamafile
mozilla-ai/llamafile
A Mozilla project that packs LLMs into single-file executables for local, no-install inference across operating systems.
Topics
Related projects
OGAM3.3kAn offline AI suite for phones and Macs that bundles local LLMs, image generation, vision, speech transcription, tool calling, and a project knowledge base.
shimmy6kA tiny pure-Rust local inference server for GGUF models with an OpenAI-compatible API and WebGPU acceleration.
claude-code-local3.5kA local inference setup that lets Claude Code run on Apple Silicon or a PC using MLX or llama.cpp. It serves an Anthropic-compatible API, picks a model for your hardware, and keeps code offline.
lucebox3kFast LLM inference server for consumer-grade GPUs that uses speculative decoding and custom kernels to raise throughput while lowering memory use.
deltafin858A single-file inference program for running the full Kimi K3 model on consumer hardware, plus an OpenAI-compatible local API server for chat and coding agents.
bigmoeonedge709An inference engine built on stock llama.cpp that runs oversized MoE models on memory-constrained phones by streaming only routed experts from flash without quality loss.