-
@xidian University
- ai.oldpan.me
Highlights
Lists (1)
Sort Name ascending (A-Z)
Stars
Run parallel research agents with any model
Evidence-driven CUDA, CUTLASS, Triton and GPU workload optimization for ChatGPT · 使用 ChatGPT 驱动 GPU workload 性能优化
High-performance MXFP6 GEMM implementation optimized for NVIDIA SM120 GPUs.
Sing-box 全家桶 --- 一键多协议脚本。支持 Reality、Hysteria2 、TUIC 、Trojan 、Shadowsocks 、 AnyTLS 、ShadowTLS 、 Vmess 、 VLESS 、NaiveProxy,搭配 Argo 隧道等,多客户端订阅(Clash / V2rayN / Throne / ShadowRocket / SFA ),无须域名、功能强大、…
Skills for Real Engineers. Straight from my .agents directory.
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
Show usage stats for OpenAI Codex and Claude Code, without having to login.
Bub it. Build it. A hook-first runtime for agents that live alongside people.
First public benchmark of llama.cpp speculative decoding on Qwen3.6-35B-A3B with a single RTX 3090 (post PR #19493 merge, 2026-04-19). 19 configurations covering ngram-cache, ngram-mod, and classic…
Make Any Website into CLI & Use your logged-in browser by AI agent.
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
Docker configuration for running VLLM on dual DGX Sparks
Terminal UI to get stuff done in the browser
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude mod…
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents
How much experts do we need to serve a model?
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Beads - A memory upgrade for your coding agent
Spec-driven development (SDD) for AI coding assistants.
Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Customize your assistants | Team them up|Star if you like it!
A protocol for connecting any editor to any agent
原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复
Assign issues to Claude Code, Codex, Cursor, and 17 more coding agents like teammates — open-source and self-hostable.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2