NNDial is an open source toolkit for building end-to-end trainable task-oriented dialogue models. It is released by Tsung-Hsien (Shawn) Wen from Cambridge Dialogue Systems Group under Apache License 2.0.
AI Agent failure replay and root cause analysis platform
TranslatedClaude Code plugin: turn one still image into a ~5 s seamless looping animation (MP4, GIF, WebP, Live Photo).
A guide and tool for cracking ssh known_hosts files with hashcat
A replica, near real-time, miniature UK railway station train departure sign based upon a Raspberry Pi Zero and 256x64 SPI OLED display
Python installable command line utiltity for mitigation of host and key compromises.
TranslatedCodex&GPT desktop pet data center | Your desktop dragon girl little assistant
- codex
- desktop-assistant
- desktop-pet
- pyside6
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.
- clean-room-reimplementation
- ai-agents
- behavioral-testing
- black-box-testing
A unified framework for tabular probabilistic regression, time-to-event prediction, and probability distributions in python
PyC (Pytorch Concepts) is a PyTorch-based library for designing concept-based interpretable deep learning models.
- ai
- concepts
- explainable-ai
- interventions
Translated☕ Using AI to assist Java / Spring Boot development (AI for Java / AI for Spring) | Requirements, implementation, testing, review, and delivery | Graph → Loop → Workflow → Agent / Skill, fictional runnable examples, and worktree / Docker tools | Aimed at business development, not an implementation of the Spring AI framework
Django project protecting American consumers
Self-improving code for any git repo: give it a measurable goal, a coding agent (Claude Code or Aider) proposes changes, the kernel scores them, keeps winners and rolls back failures. Open-source AlphaEvolve / FunSearch-style evolution loop, sandboxed, with an auditable ledger.
Interactive Coq Proofs in Vim
Automated client-side template injection (sandbox escape/bypass) detection for AngularJS v1.x.
Agent Skill for fine-tuning an agentic model on your own Claude Code sessions with Tinker. Works in Claude Code, Codex and OpenCode.
One-Step APK Decompilation With Multiple Backends
No-jailbreak iOS privacy, entitlement, sandbox & telemetry forensic auditor (inspired by Verlintas/NOIR)
Using deep stacked residual bidirectional LSTM cells (RNN) with TensorFlow, we do Human Activity Recognition (HAR). Classifying the type of movement amongst 6 categories or 18 categories on 2 different datasets.
Synchronize your ledger-cli files with your bank.
Command line tools for processing and uploading Mapillary imagery
Official repository for the paper “RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution”
Seamless long-form MiniMax H3 video generation for ComfyUI with native AV latent continuity, chunked sampling, session resume, and Spectrum/Sage/Sol compatibility.
Türkçe metinlerdeki yapay zeka izlerini (AI slop, translationese, çeviri kokan cümle mimarisi ve TDK hatalarını) temizleyen Agent Skill ve Humanizer paketi.