Highlights
- Pro
Lists (3)
Sort Name ascending (A-Z)
Stars
Model export recipes, Python primitives, and Swift runtime utilities for on-device AI
A fast, helpful, and open-source document parser
Offical implementation of "Life-Harness"
Hallucination-prevention RAG system with verbatim span extraction. Ensures all generated content is grounded in source documents with exact citations.
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
26m function call model that runs on incredibly small devices
Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI repl…
Dataset Collection, Training & Evaluation Code for Brave's Ocelot model
(ICML 2026) Official repository of paper "ObjEmbed: Towards Universal Multimodal Object Embeddings"
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
Official skills for using Brave Search API with AI coding agents.
An Evaluation Framework for Web Search APIs
1K resolution vision transformers pretrained on 1B human images.
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
TIPSv2 (CVPR'26) and TIPS (ICLR'25)
SteerViT is a framework that equips any ViT with the ability to steer both its global and local visual representations with natural language.
Allen Institute for AI: WildDet3D: Scaling Promptable 3D Detection in the Wild
Create book from markdown files. Like Gitbook but implemented in Rust
Inference repo for Falcon-Perception and Falcon-OCR model, early-fusion, natively multimodal, dense Autoregressive Transformer models.