Stars
pxzleo / ninfer-4090-48g
Forked from sergiuszm/ninfer-4090Qwen3.8-27B on one RTX 4090: full native 262K context via E8 4-bit KV, up to 149 tok/s code decode with MTP3, sm_89-retuned attention prefill, vision, llama.cpp-compatible /metrics + /slots
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
ZCode 开源版 · 复原功能版本 —— 还原官方正式版中被裁剪的内置插件与 Computer Use 能力
Z.ai's coding agent harness. Powerful, intelligent, extensible.
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
Yet another WeChat Mini-Program Framework (WMPF) debugger
🦊 内置 AI 逆向 Agent 的 Firefox — 通用 JS/JSVMP/WASM/签名逆向工作站,SpiderMonkey 引擎层非侵入 trace,把加密参数从黑盒还原成不依赖浏览器的纯算法
🦊 内置 AI 逆向 Agent 的 Firefox — 通用 JS/JSVMP/WASM/签名逆向工作站,SpiderMonkey 引擎层非侵入 trace,把加密参数从黑盒还原成不依赖浏览器的纯算法
Orbien v1: 一个开箱即用的内网穿透平台,支持 TCP/HTTP/HTTPS/UDP/SOCKS5 等多种协议,传输层支持 TCP、WebSocket、QUIC,支持TCP多路复用。同时提供证书自动申请与续期、抓包重放、压缩、mTLS 加密、访问控制、鉴权、限流、负载均衡、反向代理、健康检查等功能
An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.
A Codex jailbreak prompt and test pack for gpt. 针对 gpt 系列的 Codex 破甲提示词与测试包。
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.
手机平板远程 DeepSeek Harness:扫码即可继续使用电脑上的 DSH,无需远程桌面 / SSH / 公网 IP,支持一次性配对、Github授权加密登录,独立设备授权与随时撤销,实现远程连接很简单,但安全才是我们所想要的。
fr58386612 / Rshell
Forked from Rubby2001/Rshell本项目仅用于企业内部授权环境的资产管理、安全运维与合规检查,使用者须确保拥有目标系统的合法授权。禁止用于任何未授权场景,开发者不对滥用行为负责。
Free, open-source AI Office suite: Docs, Sheets, Slides, PDF, Markdown and HTML editors with a built-in AI agent, plus a `genoffice` CLI and agent skill so Claude Code, Codex and Cursor can create …
A cross-platform, multi-protocol C2 framework in Go (TCP/WebSocket/KCP/HTTP/OSS) for authorized pentesting & red teaming
fr58386612 / dsh-pentest
Forked from howmp/dsh-pentest面向 DeepSeek Harness(dsh)的渗透测试模式 @CloverSecLabs
DeepSeek Harness: Everything is a Plugin.
面向 DeepSeek Harness(dsh)的渗透测试模式 @CloverSecLabs
LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parallel and NUMA parallel architecture, su…
Run DeepSeek-V4.1-Flash / DeepSeek-V4-Flash and GLM-5.3-Flash on SM89 (Ada / RTX 4090) and SM120 (RTX PRO 6000) with vLLM
Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parallel architecture, suitable for MOE model hybrid inference.
All-in-one terminal covering 30+ protocols — SSH, RDP, SFTP, databases, Kubernetes and more. With a built-in AI Agent that runs multi-turn shell commands autonomously.
An AI agent-powered writing assistance system (Codex style) that enables AI-assisted content creation via WPS and Microsoft Word add-ins. 基于AI智能体的写作辅助系统,通过WPS、Microsoft Word加载项,实现AI辅助的文字创作
25 MB lightweight cross-platform database client for 100+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and D…
Codex Desktop App - Cross-platform Rebuild