Starred repositories
A decision layer embedded into the harness tool-selection loop
AI Powered Knowledge Graph Generator
Semantic-first multi-agent communication protocol — 4 concepts, 3 operations, infinite collaboration patterns
SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses
An open-source coding agent for your terminal, powered by MiniMax.
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a s…
由夜安团队研发的AI Agent渗透测试平台，强调自监督，自循环，自进化首创寻宝机制、三段式上升结构，此项目主要探索在可控环境（CTF）下的能力，不具备真实世界渗透能力
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
视频转字幕、字幕翻译、AI 配音与声音克隆、字幕烧录——免费开源的一站式桌面工具。基于 Whisper / FunASR 等本地模型离线语音转文字，批量处理 + 全平台 GPU 加速，跨 Windows / macOS / Linux。Free, open-source desktop app to generate, translate, dub & burn video subtitle…
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Two source-verified AI-agent skills that turn project code into traceable business-rule documents (whole-project + single-module). Graph-guided, evidence-graded, evaluation-backed.
Open-source release prep & bilingual README generator (Codex Skill). Turn any repo into a releasable state: evidence-based checklist, sensitive-info redline, bilingual README, topics/Discussions, u…
Minimal Postgres editor for speed, collaboration, and AI
SSYM 内存取证符号格式研究与验证 / Research on a compiled symbol format for memory forensics, with PDB, JSON and SSYM benchmarks and Volatility 3 comparisons. StarMem source code is not public.
Linux Memory Forensics Framework That Transforms Memory Dumps Into a Navigable Filesystem
The Patterns of Scalable, Reliable, and Performant Large-Scale Systems
VulnForge · 智能漏洞挖掘工作台：静态分析 → 模糊测试（AFL++）→ 崩溃分析 → CNVD 报告闭环
VaultBox - local-first E2E encrypted vault (Tauri 2 + Vue 3, Argon2id + AES-256-GCM)
Local-first open-source multi-profile fingerprint browser based on Chromium and Electron
The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.
Turn any open model into a classifier/jev endpoint
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
The chat decision assistant: before you reply, Jev reads the chat, judges intent and risk, and drafts replies you fill in with one tap. You press send. Android · Windows · macOS · iOS | 聊天辅助决策工具：先看…
Sketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts.
MiniCPM5: SOTA on-device LLMs, small yet powerful.