llm
The Typescript AI framework.
Mastra is an opinionated Typescript framework that helps you build AI applications and features quickly. It gives you the set of primitives you need: workflows, agents, RAG, integrations, syncs and evals. You can run Mastra on your local machine, or deploy to a serverless cloud.
Related contents:
the LLM vulnerability scanner. Generative AI Red-teaming & Assessment Kit
garak checks if an LLM can be made to fail in a way we don't want. garak probes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other weaknesses. If you know nmap, it's nmap for LLMs.
AI Assistant. Knowledge Graph based RAG built with TiDB Serverless Vector Storage and LlamaIndex.
An open source GraphRAG (Knowledge Graph) built on top of TiDB Vector and LlamaIndex and DSPy. pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage.
AIOps modules is a collection of reusable Infrastructure as Code (IaC) modules for Machine Learning (ML), Foundation Models (FM), Large Language Models (LLM) and GenAI development and operations on AWS
Willow Is a Practical, Open Source, Privacy-focused Platform for Voice Assistants and Other Applications. Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative.
Willow is an ESP IDF based project primarily targeting the ESP32-S3-BOX hardware family from Espressif. Our goal is to provide Amazon Echo/Google Home competitive performance, accuracy, cost and functionality with Home Assistant, openHAB and other platforms.
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue).
A simple tool to convert screenshots, mockups and Figma designs into clean, functional code using AI.
Common Corpus is the largest open and permissible licensed text dataset, comprising over 2 trillion tokens (2,003,039,184,047 tokens). It is a diverse dataset, consisting of books, newspapers, scientific articles, government and legal documents, code, and more.
the AI-native open-source embedding database. The fastest way to build Python or JavaScript LLM apps with memory! Chroma is the open-source AI application database. Batteries included.
Embeddings, vector search, document storage, full-text search, metadata filtering, and multi-modal. All in one place. Retrieval that just works. As it should be.
Related contents:
Extract structured data from PDFs. Stop wasting time extracting PDFs. Transform your PDF documents into structured data with Documind. Simple, powerful and open-source.
Documind is an advanced document processing tool that leverages AI to extract structured data from PDFs. It is built to handle PDF conversions, extract relevant information, and format results as specified by customizable schemas.
RAG that intelligently adapts to your use case, data, and queries.
Streamlined and promptable Fast GraphRAG framework designed for interpretable, high-precision, agent-driven retrieval workflows.
MinerU is a tool that converts PDFs into machine-readable formats (e.g., markdown, JSON), allowing for easy extraction into any format. MinerU was born during the pre-training process of InternLM. We focus on solving symbol conversion issues in scientific literature and hope to contribute to technological development in the era of large models. Compared to well-known commercial products, MinerU is still young. If you encounter any issues or if the results are not as expected, please submit an issue on issue and attach the relevant PDF.
⚡️ OpenAI PHP is a supercharged community-maintained PHP API client that allows you to interact with OpenAI API.
OpenAI PHP is a community-maintained PHP API client that allows you to interact with the Open AI API.
Conversational Data Analysis.
PandasAI is a Python platform that makes it easy to ask questions to your data in natural language. It helps non-technical users to interact with their data in a more natural way, and it helps technical users to save time, and effort when working with data.
PandasAI is a Python library that integrates generative artificial intelligence capabilities into pandas, making dataframes conversational. Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.
A playbook for effectively prompting post-trained LLMs.
This document is for anyone who would like to get better at prompting post-trained LLMs. We assume that readers have had some basic interactions with some sort of LLM (e.g. Gemini), but we do not assume a rigorous technical understanding.
Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.
WebLLM Chat is a private AI chat interface that combines WebLLM with a user-friendly design, leveraging WebGPU to run large language models (LLMs) natively in your browser. Enjoy an unprecedented, private, and accessible AI conversation experience.
🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library. The no-nonsense RAG chunking library that's lightweight, lightning-fast, and ready to CHONK your texts
Open Source Agents for Developers
Use AI to tackle the toil in your backlog, so you can focus on what matters: hard problems, creative challenges, and over-engineering your dotfiles.
Related contents:
The open-source AI-native IDE. Powered by the state-of-the-art agentic framework on swebench-lite.
Aide is the Open Source AI-native code editor. It is a fork of VS Code, and integrates tightly with the leading agentic framework on swebench-lite.
Docling parses documents and exports them to the desired format with ease and speed. 🗂️ Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON.
Related contents:
Open-Source Web Automation library with any LLM.
Let LLMs interact with websites through a simple interface.
Hertz-dev is an open-source, first-of-its-kind base model for full-duplex conversational audio.
Investbrain is a smart open-source platform that consolidates your portfolios from different brokerages, tracks market performance across your portfolios, and gives you an AI-powered investment best friend.
Related contents:
Zero shot pdf OCR with gpt-4o-mini.
A dead simple way of OCR-ing a document for AI ingestion. Documents are meant to be a visual representation after all. With weird layouts, tables, charts, etc. The vision models just make sense!
STORM: Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking.
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
STORM is a LLM system that writes Wikipedia-like articles from scratch based on Internet search. Co-STORM further enhanced its feature by enabling human to collaborative LLM system to support more aligned and preferred information seeking and knowledge curation.
Structured text generation and robust prompting for language models.
Outlines is a Python library that allows you to use Large Language Model in a simple and robust way (with structured generation). It is built by .txt, and is already used in production by many companies.
Related contents:
The Data Processor for Agents.
Marly allows your agents to extract tables & text from your PDFs, Powerpoints, etc in a structured format making it easy for them to take subsequent actions (database call, API call, creating a chart etc).
The repository of TrafficLLM, a universal LLM adaptation framework to learn robust traffic representation for all open-sourced LLM in real-world scenarios and enhance the generalization across diverse traffic analysis tasks.
The repository of TrafficLLM, a universal LLM adaptation framework to learn robust traffic representation for all open-sourced LLM in real-world scenarios and enhance the generalization across diverse traffic analysis tasks.
Build, train, and deploy machine learning (ML) models for any use case with fully managed infrastructure, tools, and workflows.
Amazon SageMaker is a fully managed service that brings together a broad set of tools to enable high-performance, low-cost machine learning (ML) for any use case. With SageMaker, you can build, train and deploy ML models at scale using tools like notebooks, debuggers, profilers, pipelines, MLOps, and more – all in one integrated development environment (IDE).
Zero shot vulnerability discovery using LLMs. A tool to identify remotely exploitable vulnerabilities using LLMs and static code analysis.
Vulnhuntr leverages the power of LLMs to automatically create and analyze entire code call chains starting from remote user input and ending at server output for detection of complex, multi-step, security-bypassing vulnerabilities that go far beyond what traditional static code analysis tools are capable of performing.
Related contents:
Generative AI Scripting.
Programmatically assemble prompts for LLMs using JavaScript.
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.
Personalized AI SQL Agent. Let Vanna.AI write your SQL for you
The fastest way to get actionable insights from your database just by asking questions.
📦 Repopack is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, and Gemini.
🤖 CLI AI Assistant
A simple command-line AI assistant that translates natural language into shell commands. Supports all Windows and Unix-based systems (Linux, MacOS).
Open source AI. Code Reviews and Docs. Customizable LLM-enabled workflows to automate reviews, docs and patches.
Patchwork automates development gruntwork like PR reviews, bug fixing, security patching, and more using a self-hosted CLI agent and your preferred LLMs. Try the hosted version here.
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Meta Lingua is a minimal and fast LLM training and inference library designed for research. Meta Lingua uses easy-to-modify PyTorch components in order to try new architectures, losses, data, etc. We aim for this code to enable end to end training, inference and evaluation as well as provide tools to better understand speed and stability. While Meta Lingua is currently under development, we provide you with multiple apps to showcase how to use this codebase.
Llama3.1 learns to Listen. Local real-time voice AI (Formerly llama3-s).
🍓 Ichigo is an open, ongoing research experiment to extend a text-based LLM to have native "listening" ability. Think of it as an open data, open weight, on device Siri.
Open-Source ML Monitoring and LLM Observability.
Open-source evaluation and observability for ML and LLM systems Evaluate, test, and monitor AI-powered systems. From tabular data to LLMs. Built for data scientists, AI, and ML engineers.
Intelligent Prompt Gateway.
Arch is an intelligent prompt gateway. Engineered with (fast) LLMs for the secure handling, robust observability, and seamless integration of prompts with APIs - all outside business logic. Built by the core contributors of Envoy proxy, on Envoy.
Arch is an intelligent Layer 7 gateway designed to protect, observe, and personalize LLM applications (agents, assistants, co-pilots) with your APIs.
OmniParse is a platform that ingests/parses any unstructured data into structured, actionable data optimized for GenAI (LLM) applications. Whether working with documents, tables, images, videos, audio files, or web pages, OmniParse prepares your data to be clean, structured and ready for AI applications, such as RAG , fine-tuning and more.
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
Forget expensive NVIDIA GPUs, unify your existing devices into one powerful GPU: iPhone, iPad, Android, Mac, Linux, pretty much any device!
Related contents:
Chub is platform that allows you to interact with characters through the use of Artificial Intelligence (AI) Large Language Models (LLMs). These models are accessed through the use of APIs which Chub streamlines into a convenient to use chatbot service.
Chub is uncensored. We do not restrict in any meaningful capacity the variety of characters that are allowed to be posted on the platform nor the type of interactions you are allowed to have with said characters.
Chub AI supports numerous APIs such as OpenAI or Anthropic (Claude), features such as chat trees, exporting/importing chats from existing services, and much more!
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Related contents:
Amplified developers, AI-enhanced development.
⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains.
NotebookLM is an AI-powered research and writing assistant that works best with the sources you import.
Automate dogfoodingfor your team. Get more eyes on your web app. Testing your product is now just a simple command away. Get more eyes on your website. Ship with confidence.
Donobu simplifies automation through intuitive prompts, getting you started in no time.
Prompt, run, edit & deploy web apps.
Bolt.new is an AI-powered web development agent that allows you to prompt, run, edit, and deploy full-stack applications directly from your browser—no local setup required. If you're here to build your own AI-powered web dev agent using the Bolt open source codebase, click here to get started!
Related contents:
Build in-app AI chatbots in days, not weeks.
assistant-ui is a chatbot UI for your React app
Related contents:
AI powered by what you've seen, said, or heard. Alternative to Rewind.ai.
screenpipe records your screens and mics 24/7 safely on your computer, and connects it to AI, creating magic from your data.
Rank LLMs, RAG systems, and prompts using automated judge evaluation.
Giving Kubernetes Superpowers to everyone.
k8sgpt is a tool for scanning your Kubernetes clusters, diagnosing, and triaging issues in simple English. It has SRE experience codified into its analyzers and helps to pull out the most relevant information to enrich it with AI.
Open Source AI Code Editor for Fast Development. The Open Source AI-Powered Code Editor. A fork of VSCode and Continue.
Deobfuscate Javascript code using LLMs ("AI")
This tool uses large language modeles (like ChatGPT & llama) and other tools to deobfuscate, unminify, transpile, decompile and unpack Javascript code. Note that LLMs don't perform any structural changes – they only provide hints to rename variables and functions. The heavy lifting is done by Babel on AST level to ensure code stays 1-1 equivalent.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Related contents:
Data Framework for LLM Applications.
LlamaIndex (GPT Index) is a data framework for your LLM application. Building with LlamaIndex typically involves working with LlamaIndex core and a chosen set of integrations (or plugins). There are two ways to start building with LlamaIndex in Python:
Related contents:
The largest community building the future of LLM apps
LangChain’s flexible abstractions and AI-first toolkit make it the #1 choice for developers when building with GenAI. Join 1M+ builders standardizing their LLM app development in LangChain's Python and JavaScript frameworks.
Related contents:
- #307.src - Langchain: Faire de l'IA comme des Lego avec Maxime Thoonsen @ <ifttd>.
- Tour d'horizon des frameworks pour créer des applications basées sur les LLM @ Data-Crafting.io :fr:.
- #304.bin - Bilan 2024: Le début de la révolution avec Quentin Adam @ <ifttd>.
- Construire son RAG (Retrieval Augmented Generation) grâce à langchain: L’exemple de l’Helpdesk d’OCTO @ OCTO talks :fr:.
- CLI Chatbot with LangChain and OpenAI in Node.js @ rw;eruch.
- Meetup GenAI - Découverte de LangChain @ Flint's YouTube :fr:.
- Agents 2.0: From Shallow Loops to Deep Agents @ PHILSCHMID.
- Production RAG: what I learned from processing 5M+ documents @ Abdellatif Abdelfattah.
- Intégration de Google Drive avec langchain @ Octo talks! :fr:.
- Deux techniques pour ingérer des pages web pour le RAG : BeautifulSoup vs Docling @ lbke :fr:.
- Créer un RAG avec LangChain en 5 étapes @ lbke :fr:.
- RAG Against The Machine @ Quoi de neuf les devs ? :fr:.
- LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks @ The Hacker News.
An open-source RAG-based tool for chatting with your documents.
An open-source clean & customizable RAG UI for chatting with your documents. Built with both end users and developers in mind.
Prompt design using JSX.
Priompt (priority + prompt) is a JSX-based prompting library. It uses priorities to decide what to include in the context window.
Priompt is an attempt at a prompt design library, inspired by web design libraries like React.
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering.
Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs).