Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)
- ai-text-detection
- explainable-ai
- interpretability
- mechanistic-interpretability
47,133 repositories indexed
769–792 of 1,192 · Most stars
Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)
TranslatedAI live streaming room: Vidu S2 real-time digital human + danmaku (bullet comment) filtering and scheduling + wardrobe outfit changing + OBS overlay (character assets not included)
Cornelius, le cadre/miroir intelligent : il vous reconnaît, vous écoute et répond en français. Assistant vocal, reconnaissance faciale en local, Home Assistant, météo, transports et beaucoup plus !
Naive-N0.5-Flash is an open-weight 309B MoE model with 15.5B active parameters, built for coding and AI R&D.
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
TranslatedUncensored NSFW API for AI video generation — Seedance Spicy & Wan NSFW docs: 18+ text-to-video / image-to-video, async tasks, webhooks, credits billing. Adult-oriented AI video generation API: Seedance Spicy, Wan NSFW, text-to-video / image-to-video, async tasks, credit-based billing, integration guide.
Xiryn — the open-source personal agent. Does everything Muse, Grok Bot and Dots do, on your own computer: each agent gets its own Linux desktop in Docker, any model with your keys, an encrypted vault, and control from Telegram.
DeepSeek-V4.1-Flash-1017 EXL3 on 2x DGX Sparks with TensorFold
Real-time generative rendering for interactive worlds, from any visual reference.
AI Skill for Playwright Best Practices—made by Currents.dev
Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.
Compile-time i18n toolkit that requires zero code changes and produces the smallest possible bundles. Supports React, Svelte, SolidJS, Astro, and more
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
Agentic browser control driven by your own Claude / Cursor subscriptions
TestDino Playwright Skill: AI-powered guides for Playwright best practices, made by testdino.com.
All your machines, one app. For you and your AI agents: agent sessions, desktops, files, logs and GitHub across your Macs, Linux and Windows machines, with an MCP server.
Shift-left API Integration | Auto-fix integration drift before integration. Specmatic turns API specifications into executable contracts, continuously verifying that every change made by AI coding agents and engineers stays true to the desired behaviour. Ship AI-ready APIs 10x faster, from intent to implementation, with Spec-Driven API Development.
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test Flutter, React Native, iOS, Android, Web, Electron, Tauri, KMP, .NET MAUI — all from natural language.
A curated collection of REA and AI-assisted reverse engineering cases, projects, and ideas. Updated every four hours.
TranslatedAn AI avatar for real-time voice/text conversations with idols from "The iDOLM@STER Shiny Colors": original Japanese voice + Chinese subtitles, recalling the original story, memory shared across characters; supports Google/GitHub login and bring-your-own key, one-command deployment with Docker Compose (inspired by LAPLACE Eidolon)
TranslatedAutomagically generate conventional git commit messages with AI.
Aixio Layer v2 recovers editable layers from flat designs where possible. 150-design benchmark vs Canva Magic Layers, Qwen-Image-Layer and GPT-6 Astra Ultra.
Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode