Havuz

Unified LLM access layer in Rust — one API for 325 AI providers. 统一 LLM 服务接入层：一套 API 接入 325 家 AI 服务商。

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cp

A minimalist, terminal-native coding agent written in C.

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

The AI-friendly C23 compiler for security research, built on LLVM [WIP]

Reconstructing DX-Ball 1.07 with REA, backed by original-x86 differential tests and pinned MSVC byte-exact oracles.

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

Run a 28.9M-parameter TinyLM on ESP32-S3 with an RP2040 OLED display node for fully local embedded AI inference.

Rust Based Multi-language Static Analyser & Developer tools for the AI age.

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b

A code knowledge graph built for LLM agents — accurate answers, minimal tokens, maximum speed

AI coding agent in C. Single binary, zero runtime deps, every major LLM provider.

Run the native 284B-A13B DeepSeek-V4-Flash-0731 LLM locally on one laptop CPU: pure C, 8 GB RAM minimum, no GPU, best TPOT 0.892 s/token, re

Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools;

The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no GP

A dependency-free C inference engine for Liquid AI's LFM2 / LFM2.5 models. Terminal chat, an OpenAI-compatible server, a web agent and a ter

True incremental Markdown-to-ANSI terminal renderer for streaming LLM output. CommonMark/GFM support tested, no full-document buffering. C C

A custom, high-performance, disk-backed Approximate Nearest Neighbor (ANN) vector database built entirely from scratch in C. Feel free to co

Tiny language models that never touch DRAM.

A phone OS written from scratch by Claude: Slab UI, own compositor, DHCP/DNS/HTTP stack, HTML/CSS browser and a YouTube player. Runs in QEMU

A tiny C runtime for durable AI agents: local-first, event-driven, restart-safe, and fully inspectable.

embeddable llm agent in c with lua plugins

Deterministic symbolic codes for embedding vectors. Byte-identical across CPUs and languages, content-addressed, diffable and verifiable. C

macOS-Port von kimi-k3-in-c: Patch, Installer und Validierung für Apple Silicon. Ohne Modellgewichte.