Watchtower | Self-hosted AI security assessment, asset intelligence, and evidence workflows.
- ai-agents
- attack-surface-management
- docker
- penetration-testing
47,133 repositories indexed
481–504 of 635 · Most stars
Watchtower | Self-hosted AI security assessment, asset intelligence, and evidence workflows.
Offline NVIDIA Blackwell VBIOS editor.
Passive market-making bot for Predict.fun: quotes from live order books, replaces stale orders and cancels on unsafe price/depth; Windows desktop app and web console for Ubuntu servers.
Toggle the iPhone call-recording announcement on/off from a Windows GUI, built on the airlift AirTraffic sandbox escape.
Custom build of ida-pro-mcp - stability-hardened MCP server for hosting headless IDA Pro instances
Do stock correlations predict the market? 66 pre-registered tests, the data, and a triple pendulum that explains why not. If you have an idea you want me to try, submit it as a PR and I will test it and get back to you.
Research tooling for MW4 on-demand texture streaming: loopback proxy, hosts manager, resumable mirror, control GUI. Code and notes only - no game files.
Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis)
A local retry shim that stops Codex's "Selected model is at capacity" error from interrupting your work.
Offline evidence-policy checker for PandaSI.
The repository host gives no description.
TranslatedBuild GPT-2 from scratch in PyTorch, step by step
Evidence-aware Japanese speech visualization: pitch and intonation, waveform inspection, and experimental alignment.
Build autonomous AI agents that interact with blockchains — in minutes, not months.
The repository host gives no description.
Translated子瑜量研 (Ziyu Quant Research, "Ziyu quantitative research") | A local A-share quantitative research workbench: factor research and evolution, strategy backtesting, simulation validation, and traceable evidence. Product introduction and interactive demo.
SteerAct: Unlocking Action Models through Few-Shot Temporal Steering
The official implementation of 'S4VY: Segment Anything in Feed-Forward 4D Visual Geometry'
TranslatedCurated agent skills for social media: Xiaohongshu (RedNote), Douyin, WeChat, X, YouTube, TikTok and LinkedIn. Also covers self-media operations, including WeChat Official Accounts, WeChat Channels and Bilibili: topic selection, writing, images, publishing and data. Usable by agents such as 千问 (Qianwen, "Thousand Questions"), 豆包 (Doubao, "bun"), 龙虾 (Longxia, "lobster") OpenClaw, WorkBuddy, Claude Code and Codex.
Official implementation of paper "Cache Engineering for Agents"
Templates to pin Claude and Google Pay to one static residential proxy on Clash Party, Shadowrocket, and FlClash.
Free Course : Data, Machine Learning, Deep Learning and AI Engineering, the long way round: the math, the code, the systems and the security. 173 lessons, 166 runnable labs, no shortcuts. Free under CC BY-NC 4.0.
CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.
Manga / black & white comic filter for ComfyUI: crisp lines, flat tones, real screentone (halftone), solid blacks and panel frames.