Lists (1)
Stars
Lossless compression C library built for ultra-fast decode. Faster than LZ4 (+35% to 105%+; best on ARM64), at a better ratio. Official Rust, Python, Node.js, Go and WASM bindings. Write-once/read-…
Rust profiler for CPU, memory, SQL, HTTP, and async performance, with Prometheus and Grafana support.
Native Windows port of Dead or Alive Xtreme Beach Volleyball (Xbox), built by static recompilation with a hand-written runtime. Requires your own copy of the game.
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
Very fast, high quality, platform-independent hashing algorithm.
Unlocking _everything_ on the CPU with DRAM scrambling
OpenCode plugin for AxonHub that dynamically discovers available models, caches them daily, and configures OpenAI/Anthropic-compatible endpoints automatically.
Validate-then-repair extension for pi — fixes common LLM tool-call mistakes (null fields, stringified arrays, wrong field names, anchor bleed) before tools execute
A universal OpenCode plugin for dynamic model discovery with flexible configuration for OpenAI-compatible providers.
TokenSpeed is a speed-of-light LLM inference engine.
Firefly III: a personal finances manager
A delightful Firefly III companion web app for effortless transaction tracking
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
Algorithm powering the For You feed on X
⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
A go native library for converting documents to markdown. Includes OCR
Benchmark AI model speeds with TTFT, tokens/sec, and performance metrics .
Home of the development of the Nexus Mods App
Lightweight, heavily optimized coding tool implementations for LLM-powered development agents.
Sub-millisecond VM sandboxes for AI agents via copy-on-write forking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
ShadowONE is a cross-platform successor to the HeroesONE and HeroesONE-Reloaded ONE file editors
Automate the obvious and investigate the ambiguous. High-performance safety rules engine for real-time event processing at scale.
Array of Struct to Struct of Array helpers in Rust