Stars
An official OpenAI toolkit for social scientists and data scientists to measure quantitative attributes in text, images, or audio using the GPT API.
Workshop: Agentic Search for Context Engineering
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Inference repo for Falcon-Perception and Falcon-OCR model, early-fusion, natively multimodal, dense Autoregressive Transformer models.
Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models
Our free and open source annotation platform
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A research toolkit for decomposing and explaining text similarity across neural, structured, and symbolic levels.
The absolute trainer to light up AI agents.
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
Arabic Arud (prosody) toolkit for Python. Features meter detection, tafeela analysis, and support for all 16 poetic meters with strict type safety.
Recursive Language Models for unbounded context processing. Process 100k+ tokens with any LLM by storing context as variables instead of prompts.
Manazir OCR — Arabic-first, optics-inspired multi-model OCR. Extracts high-quality text and layout (HTML/Markdown) from Arabic documents using pluggable backends (Qari, DIMI, OCR-RL2, TrOCR, Qwen2/…
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Supercharge Your LLM with the Fastest KV Cache Layer
A high-throughput and memory-efficient inference and serving engine for LLMs
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
VECMAN (Vector Manager) - A VQ-VAE based vector database for efficient text embeddings and retrieval. This package provides a memory-efficient way to store and retrieve text embeddings using Vector…
Inspect: A framework for large language model evaluations
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Fast Multimodal Semantic Deduplication & Filtering
12 Lessons to Get Started Building AI Agents
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
🏅 Collection of Kaggle Solutions and Ideas 🏅