Skip to content
View Oldpan's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report Oldpan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Run parallel research agents with any model

Rust 280 23 Updated Aug 19, 2026

Evidence-driven CUDA, CUTLASS, Triton and GPU workload optimization for ChatGPT · 使用 ChatGPT 驱动 GPU workload 性能优化

Python 7 Updated Aug 13, 2026

High-performance MXFP6 GEMM implementation optimized for NVIDIA SM120 GPUs.

Cuda 10 2 Updated Aug 19, 2026

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、…

Shell 5,491 1,106 Updated Aug 17, 2026

Skills for Real Engineers. Straight from my .agents directory.

Shell 223,113 19,211 Updated Aug 19, 2026

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

Rust 25,686 4,831 Updated Aug 19, 2026

Show usage stats for OpenAI Codex and Claude Code, without having to login.

Swift 20,335 1,746 Updated Aug 19, 2026

Bub it. Build it. A hook-first runtime for agents that live alongside people.

Python 1,587 156 Updated Aug 19, 2026

DreamReasoner-8B, a large diffusion reasoning model

16 Updated Jun 18, 2026

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…

Python 33 2 Updated May 16, 2026

Make Any Website into CLI & Use your logged-in browser by AI agent.

JavaScript 28,349 2,782 Updated Aug 17, 2026

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Python 10,739 1,172 Updated Jul 30, 2026

Docker configuration for running VLLM on dual DGX Sparks

Shell 2,135 363 Updated Aug 19, 2026
Python 19 Updated Aug 18, 2026
Python 284 27 Updated Jun 17, 2026

the runtime your coding agents live on

Rust 30,589 2,181 Updated Aug 19, 2026

Terminal UI to get stuff done in the browser

Rust 621 37 Updated Aug 16, 2026

A tiny account switcher for Factory Droid

Rust 5 1 Updated Apr 30, 2026

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…

Go 47,914 7,391 Updated Aug 19, 2026

Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents

Python 3,427 337 Updated Aug 18, 2026

How much experts do we need to serve a model?

Python 150 15 Updated Mar 18, 2026

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

TypeScript 19,978 1,435 Updated Aug 19, 2026

Beads - A memory upgrade for your coding agent

Go 26,444 1,780 Updated Aug 19, 2026

Spec-driven development (SDD) for AI coding assistants.

TypeScript 65,486 4,511 Updated Aug 19, 2026

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!

TypeScript 32,113 3,287 Updated Aug 19, 2026

A protocol for connecting any editor to any agent

Rust 4,015 348 Updated Aug 19, 2026

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

TypeScript 22,124 16,478 Updated Aug 18, 2026

Assign issues to Claude Code, Codex, Cursor, and 17 more coding agents like teammates — open-source and self-hostable.

Go 46,836 5,984 Updated Aug 19, 2026

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Rust 195,085 109,042 Updated Aug 16, 2026

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

Rust 652 102 Updated Aug 19, 2026
Next