Havuz

QuickJS with durable execution: suspend running JS, snapshot the whole heap, resume it in another process. Native TypeScript, a REPL that su

LordOS — a free, fast and secure GNU/Linux distribution based on Debian, with its own desktop environment: display server and Wayland compos

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 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

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

Native PSP engine for The Simpsons: Hit & Run (PS2), written in C with PSPSDK. Not an emulator: data is converted from your own disc, runs o

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

Run large AI models across your computers and servers. Powered by Colibri. Pure C.

Nordstjernen Sol web browser. A open source web browser with dual GPL 3+ or NSL license, written from scratch in 2026.

eBPF tracer and analyzer for io_uring. Reconstructs per-request latency, io-wq punts, and batching from kernel tracepoints, then names the p

Command-line tools for photographers.

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。

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

Terminal research and study client for MITRE ATT&CK®

A sakura tree with falling petals for your terminal

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

libcli - a singe-header library for typed argument parsing in C

CLI tool for extracting files from damaged, corrupted, or encrypted APFS disk images. Written in C11, macOS-first (Linux supported). Handles

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

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

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

meowdo is a cute, keyboard-driven todo list with a cat sidekick. It lives in your terminal, supports tags, search, pinning, and remembers ev

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

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

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;

Lightweight C networking runtime with embedded Lua: cross-platform event loop (epoll/kqueue/WSAPoll, optional io_uring), one isolated Lua st

A Unix-like shell for microcontrollers and PCs: users, files, .tdsh scripts, Wi-Fi and Ethernet, SSH/SFTP, FTP, SMB mounts, SD card. Tested

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

VTC 2026: Simple Terminal Vocabulary Trainer for Fast Language Learning

A stealth-focused kernel-mode virtual HID mouse driver for Windows. Built with KMDF and VHF for precise, hardware-level input simulation usi

A terminal-only Bluesky / AT Proto client written in Fortran, with an asm/Rust native firehose decoder for the relay-raw stream. Dither imag

A small multithreaded TCP port scanner in plain C (POSIX sockets + pthreads), zero dependencies.

Pharmacy+ POS is Point of Sale for health institutions that deal with walk-in patients such as clinics and drug shops.

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

Programming language which it allows you to write your smallest possible programs.

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

A lightweight, zero-allocation CSV library written in portable C99. Supports RFC 4180 parsing, streaming, zero-copy fields, writing, fuzz te

A modular C++ CLI tool demonstrating dynamic memory allocation, strict pointer manipulation, and safe resource management.

Circuit breaker for production PostgreSQL. Native extension that can ALLOW, WARN, or BLOCK dangerous SQL based on live database state. Apach

Lightweight virtual LAN tool that creates a private IPv4 subnet over UDP

Tiny language models that never touch DRAM.

Open-source C17 game engine and integrated editor focused on completing a full 3D development workflow, with first-class 2D and 2.5D planned

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

A native Microsoft Excel XLL add-in for querying Excel ranges with DuckDB SQL and parameter binding.

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.

Independent desktop operating system with its own kernel, userspace and native BoringWM, written primarily in C