#
Lists (29)
Doc-Extraction
2 repositories
Hypervisors
1 repository
✨ Inspiration
4 repositories
Inspo
2 repositories
Linux-Tooling
1 repository
LLM-Agent-Related
1 repository
LLM-Evals
38 repositories
LLM-FrontEnds
14 repositories
LLM-Model-Research
18 repositories
LLM-Research
88 repositories
LLM-Tools
90 repositories
Misc-Tools-MultiPlatform
2 repositories
ML-Educational
6 repositories
ML-Ops/LLM-Ops
9 repositories
ML-RAG & Search
30 repositories
ML-Security
1 repository
ML-Training
22 repositories
Note-taking
1 repository
Personal-Infra
26 repositories
Product-Design
3 repositories
RT-General
4 repositories
Secure-Infra
2 repositories
Security-Tooling (random)
6 repositories
Software_Engineering
1 repository
TTS/STT
38 repositories
VLM & Audio LLMs
18 repositories
WebDev
2 repositories
WinDev
2 repositories
Windows-Vulns
1 repository
Starred repositories
VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)
A single Gradio + React WebUI with extensions for ACE-Step, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, …
[ArXiv 2025] Imperceptible Jailbreaking against Large Language Models
Fully customizable AI chatbot component for your website
Typescript/React Library for AI Chat💬🚀
rmusser01 / tldw_browser_assistant
Forked from n4ze3m/page-assistBrowser extension for tldw_server
[NeurIPS 2024] | An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding
Official repository for paper "ReasonIR Training Retrievers for Reasoning Tasks".
MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.
Cybersecurity AI (CAI), the framework for AI Security
A collection of GGUF and quantizations for jina-embeddings-v4
Use Cloudflare to create HTTP pass-through proxies for unique IP rotation, similar to fireprox
AirLLM 70B inference with single 4GB GPU
TrustJudge is a probabilistic evaluation framework that reduces score-comparison and pairwise transitivity inconsistencies in LLM-as-a-judge systems.
Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.
Your universal AI text processor, powered by local and cloud LLMs. Edit, refactor, and transform text in any application on Windows, macOS, and Linux.
Qwen3Guard is a multilingual guardrail model series developed by the Qwen team at Alibaba Cloud.
Parkiet is a 1.6B parameter Dutch text-to-speech model (TTS)
EDR-Freeze is a tool that puts a process of EDR, AntiMalware into a coma state.
OWASP CycloneDX is a full-stack Bill of Materials (BOM) standard that provides advanced supply chain capabilities for cyber risk reduction. SBOM, SaaSBOM, HBOM, AI/ML-BOM, CBOM, OBOM, MBOM, VDR, an…
CycloneDX Software Bill of Materials (SBOM) generator for Python projects and environments
Fast RUST TUI app for parallel AI coding assistants and agents directly in the terminal.
12
Updated Oct 9, 2025