A local gateway that routes Cursor requests through user-supplied model API keys while preserving agentic tool-call workflows, designed for developers wanting flexible model selection without losing native IDE integration.
An open-source fingerprint browser built on Ungoogled Chromium that spoofs device fingerprints and defeats automation detection for private scraping and multi-account workflows.
Industrial-grade open-source framework for AI digital humans supporting real-time conversation, WebRTC playback, private deployment, and pluggable models for developers building interactive avatars.
General-purpose AI state-space search engine using blackboard architecture to schedule agents for autonomous exploration. First validated in autonomous penetration testing scenarios.
Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
A curated collection of reusable skills, custom agents, MCP server configurations, and Agents.md files that ground coding agents in Azure SDK and Foundry development practices and APIs.
Comprehensive guide and tutorial collection for mastering Claude Code, covering setup, commands, hooks, workflows, automation, and MCP integration. Provides step-by-step examples for beginners through advanced users.
A federated enterprise AI search application that queries 100+ business apps in place, delivering instant answers with citations while keeping sensitive data within existing security boundaries and deployments.
A privacy-preserving reverse proxy for Claude Code that normalizes device fingerprints and telemetry into one canonical identity while centrally managing OAuth tokens.
An AI-assisted tender document application for bidding teams, providing draft generation, knowledge base management, duplication checks, and compliance inspection in one workflow.
Adds MCP client capabilities to n8n workflows, letting automation builders connect to MCP servers over multiple transports and expose tools and resources for AI agents to call.
Minimalist, easy-to-host service for sharing images and other files. ([Clients](https://github.com/mtlynch/picoshare#third-party-clients)) `AGPL-3.0` `Go/Docker`
A blueprint-driven AutoResearch runtime that orchestrates AI research workflows from idea generation and experiments through paper writing and peer review with auditable evidence.
A collection of ready-to-use agents for marketing, design, finance, and similar workflows, designed to attach to popular coding assistants for business users.
All-in-one pure C++ inference engine powered by ggml for audio models, covering TTS, STT, VAD, voice conversion, and music generation with optimized performance and no Python requirement.
Developer-oriented scraping interface for Perplexity that collects AI answers and structured metadata to support brand-mention tracking, ranking, and competitor analysis for developers.
Teaches creators how to automate faceless short- and long-form videos across YouTube, TikTok, and Instagram, covering ideation, scripting, production, scheduling, monetization, and multi-account growth strategies.
Rust-based declarative rendering engine turning JSX, HTML, and CSS into OG images, animations, and paged PDFs without a headless browser across Node, Workers, and browsers.
A collection of more than 170+ tools, scripts, cheatsheets and other loots that I've developed over years for Red Teaming/Pentesting/IT Security audits purposes.
J-Space Cognition Suite V3.6 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩:Tiger380 (UID 3494375382321675) - https://space.bilibili.com/3494375382321675
J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩:Tiger380 (UID 3494375382321675) - https://space.bilibili.com/3494375382321675
J-Space Cognition Suite - a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.
An MCP server that supplies LLMs with structured context about shadcn/ui components, blocks, installation, and usage across React, Vue, Svelte 5, and React Native, deployable over SSE.
An MCP server that converts files, web pages, PDFs, and audio or video transcripts into clean Markdown, giving AI agents a uniform text format for downstream retrieval and processing.
Enterprise-grade reinforcement learning framework for LLM and VLM post-training, supporting large-scale distributed rollouts with low-precision optimizations for efficient training at scale.