Sign in

Repository Index

47,133 repositories indexed

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters

Filters

Clear all filters

3,985–4,008 of 8,241 · Most stars

GRAVA: A Unified Grounded Reasoning-to-Action Framework for Autonomous Driving. Project overview.

mailio is a cross platform C++ library for MIME format and SMTP, POP3, IMAP protocols. It is based on the standard C++ 17 and Boost library.

You can outsource your thinking, but not your understanding. A hook for agent-assisted development that quizzes you on the changes before you push to prod.

🕷️ The fastest open-source AI Gateway and LLM Gateway — one binary with built-in console to route, secure, budget and observe every LLM call across OpenAI, Anthropic, Gemini, Bedrock and more.

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

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

Open-source, auditable network gateway for homelabs, NAS and servers: DDNS, STUN traversal, port forwarding with SNI routing, reverse proxy and web server, ACME certificates, WAF, Tailscale, frp, Cloudflare Tunnel, Docker and web terminal in one binary. Runs on Docker, fnOS, OpenWrt, Linux, macOS and Windows.

  • acme
  • ddns
  • frp
  • golang

A large language model (LLM) plugin for Neovim, provides commands to interact with LLM (like ChatGPT, Copilot, ChatGLM, kimi, deepseek, openrouter and local llms). Support Github models.

Library for creating DotNet Web Worker threads/multithreading in Client side Blazor

  • blazor
  • web-worker
  • backgroundservice
  • worker-process

Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.