Repository Index

Native vLLM serving for Jev decision models

FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.

• accuracy-decline
• ai-safety
• audit-trail
• fact-checking

Reusable prompts for a structured, evidence-first bug bounty hunting workflow

• application-security
• bug-bounty
• bug-bounty-hunting
• cybersecurity

This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess financial LLMs. Our goal is to continually push forward the open-source development of financial artificial intelligence (AI).

• aifinance
• fintech
• llama
• machine-learning

Turn messy, real-world HTML into clean Markdown, from every major language.

• html-converter
• markdown-converter
• rag
• text-extraction

Fast vectorization, topic modeling, distances and GloVe word embeddings in R.

• word2vec
• text-mining
• natural-language-processing
• glove

🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.

• nlp
• natural-language-processing
• artificial-intelligence
• embeddings

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

• homebrew
• llama-cpp
• llm
• playstation-5

BLEURT is a metric for Natural Language Generation based on transfer learning.

Ontology-Augmented Generation for AI agents.

• agent-skills
• document-parsing
• knowledge-graph
• mineru

TranslatedStartup screen and startup animation plugin for DeepSeek Harness

• dsh
• dsh-plugin
• harness
• plugin

This repo offers a simple interface that helps you to read&summerize research papers in pdf format. You can ask some questions after reading. This interface is developed based on openai API and using GPT-3.5-turbo model.

Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.

• deep-learning
• protein-sequences
• protein-structure
• semi-supervised-learning

Real-time observability of claude code sessions & multi-agents.

TranslatedSprix AI at 屿智同行 (Yuzhi Tongxing, "island wisdom traveling together") × 保研岛 (Baoyan Dao, "Baoyan Island") — an open-source benchmark for AI agents in Baoyan advising and application planning.

A simple deep learning library for estimating a set of tags and extracting semantic feature vectors from given illustrations.

Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.

• ai-gateway
• anthropic
• claude-code
• codex

Have a conversation with ChatGPT using your voice, and have it talk back.

Better judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.

• ai-agents
• codex
• gpt
• prompt-engineering

OmniEdu: Open Foundation Models for Learning and Teaching

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.

• avx2
• c
• cpu-inference
• gguf

Translated341 code animation style prompts, 196 reference still frames, and an offline picker, packaged as a Claude Code / Codex Skill, with one-click import and HTML video rendering support.

• agent-skills
• animation
• claude-code
• codex

🔥 The first-ever interactive streaming video generation benchmark.

• avatar-performance
• interaction-streaming-video
• real-time-video-editing
• streaming-video-generation

Delicious diagnostic debugging in Neovim 🤤

• ai
• lsp
• lua
• neovim