Trending

Self-hosted AI workspace.

The agent that grows with you

Python terminal multitool — OSINT, Discord, web & network utilities. Rich TUI, 13 themes, remote updates. Educational use only.

JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation

Advanced open-source AI humanizer designed to make AI-generated text undetectable by Turnitin, GPTZero, and other AI detection services.

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

A 7-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.

Convert Google Gemini web into OpenAI-compatible API. Zero auth, cross-platform, single file.

This repo contains different Soul.md files each file is different and allow your agents to behave in unique interesting personality.

Speaker is a Codex skill project for academic presentations: read real.pptx, combine text extraction, PPTX structure parsing, page-by-page rendering, OCR, and visual review to generate page-by-page speaker notes, and write a clean version of the lecture into the PowerPoint comment area.

AI-friendly PPT builder skill: 17 hand-polished Chinese PPTX templates + non-destructive text-only editing tools (python-pptx based). Pick a template, write edits.json, build a real .pptx with the layout intact. Personal/research use only.

Codex skill for 750px image-to-code reconstruction and transparent PNG slicing

Sports sponsorship intelligence platform for World Cup match data, real-source text signals, ROI prediction, uncertainty analysis, and scenario recommendations.

BioMate-KB Bioconductor Skills — top 100 packages as Claude/agent skills, vignette-grounded

Role-specific Codex plugin templates

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

[CVPR 2026] Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking