Search

Coupled and Integrated Emission Inventory (CINEI): integrating anthropogenic emission inventories toward complete sectoral coverage, finer spatial resolution, and consistent NMVOC speciation for atmospheric chemistry, climate and multi-disciplinary applications.

Type annotations for aiobotocore StorageGateway 3.3.0 service generated with mypy-boto3-builder 8.12.0

OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations.

LLM-guided ML optimization — point it at a training script, it reads the curves and designs better models

Git-like version control for LLM prompts

LangChain tools for the ihyee web intelligence API

Abstract interfaces for Datus storage backends (vector & RDB)

A high-throughput and memory-efficient inference and serving engine for LLMs

Generate browsable HTML logs from OpenCode local storage

Python port of @mariozechner/pi-ai — unified LLM streaming API with OAuth authentication

A high-performance array storage and manipulation library

Persistent long-term memory for Claude Code — episodic, semantic, and procedural memory augmentation

A local LLM-based clipboard translator

Realtime prediction using neuroglancer

Inference-time governance layer for LLMs — PEF world-state, claim verification, forensic audit

Unified SDK for AI services with OpenAI compatibility

Rule-based PII and secret redaction for Markdown documents — audit log, risk-level filtering, LLM pipeline ready

LLM powered Python

An open research toolkit powered by LLMs. Branch into questions through tree structures, navigate the full space of perspectives, and grid-search evaluate across prompts and models to find what works best.

Distributed LLM inference protocol