Agent infrastructure
deltafin
gavamedia/deltafin
A 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.
Topics
Related projects
llamafile26.6kA Mozilla project that packs LLMs into single-file executables for local, no-install inference across operating systems.
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.
locally-uncensored3.3kLocally Uncensored is an all-in-one local AI studio for the desktop. It combines chat, image and video generation, a coding agent and tool-using agents in one app, running models locally or in the cloud.
kimi-k3-in-c10.2kA portable C99 inference engine that runs the 2.78T-parameter Kimi K3 model on a single CPU with streaming.
turbo-fieldfare7.2kAn efficient Gemma 4 inference runtime for Apple-silicon Macs, streaming experts under low-memory budgets and bundling a demo app with evaluation tooling.
shimmy6kA tiny pure-Rust local inference server for GGUF models with an OpenAI-compatible API and WebGPU acceleration.