A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
Repository Index
57,138 visible repositories in the index
169–192 of 246 · Most stars
EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluation code.
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.
- anthropic-api
- cuda
- gemma
- gguf
🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.
Reusable prompts for a structured, evidence-first bug bounty hunting workflow
- application-security
- bug-bounty
- bug-bounty-hunting
- cybersecurity
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
Local inference engine optimized for NVIDIA Blackwell
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
Fast vectorization, topic modeling, distances and GloVe word embeddings in R.
- word2vec
- text-mining
- natural-language-processing
- glove
A code repository indexing tool to supercharge your LLM experience.
- neovim-plugin
- retrieval-augmented
- embeddings
- rag
🚀 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.
Localize your websites with AI assistance.
The repository host gives no description.
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
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
- apple-silicon
- clover
- coding-agents
- decision-models
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
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
- apple-silicon
- llm
- llm-inference
- local-llm
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
- agent-security
- ai-agents
- audit-log
- claude-code
Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, deep research, content generation, vibe coding, browser automation, governance, and admin controls.
- agent
- ai-agents
- dsh-plugin
- enterprise-agents
🔥 The first-ever interactive streaming video generation benchmark.
- avatar-performance
- interaction-streaming-video
- real-time-video-editing
- streaming-video-generation
A comprehensive observability solution for monitoring Claude Code usage, performance, and costs.
WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.
Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding && Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
- cpu
- diffusion-models
- gguf
- inference