An AI memory layer with short- and long-term storage, semantic clustering, and optional memory decay for context-aware applications.

A free + OSS logo generator powered by Flux on Together AI

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

Efficiently find the best-suited language model (LM) for your NLP task

Aura is like Siri, but in your browser. An AI voice assistant optimized for low latency responses.

Domain Adapted Language Modeling Toolkit - E2E RAG

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

This repo gives a start for the docker.

The Open Cookbook for Top-Tier Code Large Language Model

A bot with memory, built on LangGraph Cloud.

A dashboard for dramatiq, specific to its Redis broker.

Python Stream Processing

a little task queue for python

A fast and reliable background task processing library for Python 3.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

The best OSS video generation models

ai-generated apps , full stack + generative UI

An AI search engine inspired by Perplexity

Get your documents ready for gen AI

The first AI agent that builds third-party integrations through reverse engineering platforms' internal APIs.

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Auto_Jobs_Applier_AI_Agent by AIHawk is an AI Agent that automates the jobs application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in an automated and p…

FAIR Chemistry's library of machine learning methods for chemistry

Evaluation and Tracking for LLM Experiments

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

A collection of projects designed to help developers quickly get started with building deployable applications using the Anthropic API

This is the repo for the paper "PANGEA: A FULLY OPEN MULTILINGUAL MULTIMODAL LLM FOR 39 LANGUAGES"