Starred repositories
Triton kernel fusion for Qwen3-TTS 1.7B inference acceleration — RMSNorm, SwiGLU, M-RoPE, Norm+Residual
OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)
Collection of leaked system prompts
Code and datasets for the salesforce AI research paper on prompt leakage and multi-turn threats against LLMs
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
A python library for test combinations generator. The generator allows one to create a set of tests using "pairwise combinations" method, reducing a number of combinations of variables into a lesse…
Lean 4 programming language and theorem prover
A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ...
Neocities.org - the web site. Yep, the backend is open source!
🔎 A simple, tiny and lightweight benchmarking library!
A browser-based desktop where AI Agent operates every app through natural language.
Streamlit Annotation Tools is a Streamlit component that gives you access to various annotation tools (labeling, highlighting, etc.) for text data.
Building a chatbot for Argilla SDK Step by step
A community-driven collection of Label Studio configs for various data annotation tasks.
[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, and Vision fine-tuning — natively on MLX. Unsloth-compatible API.
Apache Doris is an easy-to-use, high performance and unified analytics database.
SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click