React app for inspecting, building and debugging with the Realtime API

The Memory layer for AI Agents

🧠 Motorhead is a memory and information retrieval server for LLMs.

Super performant RAG pipelines for AI apps. Summarization, Retrieve/Rerank and Code Interpreters in one simple API.

Fluid Database

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration

Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

Set-of-Mark Prompting for GPT-4V and LMMs

LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

Chat with your PDFs with AI

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

A Perplexity clone.

From anywhere you can type, query and stream the output of an LLM or any other script

Building a chatbot powered with a RAG pipeline to read,summarize and quote the most relevant papers related to the user query.

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

🚀 PR-Agent (Qodo Merge open-source): An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍

Effortless data labeling with AI support from Segment Anything and other awesome models.

🔥🔥🔥AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.

There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

Question and Answer based on Anything.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Sample AI movies app built with ❍ Ion

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

[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.