llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): TurboQuant KV cache, MTP speculative decoding with a 64K draft-vocabulary shortlist, custom SM86 + Q…

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent…

The only browser automation that bypasses anti-bot systems. AI writes network hooks, clones UIs pixel-perfect via simple chat.

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code…

Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, and structured output. Supports vLLM, SGLang, and llama.cpp.

Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.

Open-source framework for superagents.

Linux GPU Configuration And Monitoring Tool

One-click Qwen3.6-27B inference on Windows. 158 tok/s on RTX 5090, 72 tok/s on RTX 3090. Native, no WSL, no Docker, no telemetry.

vLLM Docker Container for Qwen3.6 27b

LLM speculative inference server for heterogeneous hardware & consumer GPUs

It's like Windows Task Manager, but for GNU/Linux

An agentic skills framework & software development methodology that works.

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

🎚️ Open Source Audio Matching and Mastering

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal d…

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. F…

A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

Hindsight: Agent Memory That Learns

Export and Run Hugging Face Transformers Models on Rockchip NPUs

DirectInput8 proxy DLL that fixes Force Feedback reconnection in DCS World — automatically restores FFB effects (spring centering, trim forces) after USB device disconnect/reconnect without mission…

An expanded Adwaita-styled companion icon theme with extra icons for popular apps and MIME types to complement Gnome Shell's original icons.

DCS scripting tools

FFB Joystick designed around VPForceControl kits forked from Gadroc's Design, modified for 86 series motors