LLM 325

Terracotta simplifies LLM experimentation with a unified platform for training and evaluation. Terracotta is a platform designed to simplify and accelerate the process of experimenting with Large Language Models (LLMs). It streamlines the training and evaluation of LLMs by providing a unified interface for managing models, data, and evaluations. Terracotta aims to supercharge the LLM iteration process, making it more intuitive and efficient.

Vext is a RAG & managed LLM platform for custom AI application development. Vext is an out-of-the-box RAG & managed LLM platform that allows businesses to easily and quickly create custom AI applications using their custom data. It provides custom AI solutions for enterprises, including LLM applications, model fine-tuning, managed hosting, and custom API services. Vext offers tools like Vext Flow, a low-code builder for LLM and agent workflows, and Vext Zound, a low-latency, high-accuracy real-time AI captioning tool.

Personal AI app for offline, private chats with local AI models and documents. RecurseChat is a personal AI app designed for chatting with local AI offline and privately. It allows users to use local AI as their daily driver, enabling them to chat with local documents, images, import ChatGPT history, perform full-text searches, and more. It's a powerful, fast, and local-first AI client for local LLMs, ChatGPT, and Claude.

AI chatbot for documentation, support, and analytics. CrawlChat is an AI-powered platform that transforms your help documentation and other knowledge sources into an AI chatbot. This chatbot can answer customer and client queries and be integrated with your website, Discord server, or Slack workspace. It also provides analytics to help identify and fix data gaps in your documentation. Additionally, CrawlChat includes a traditional support ticketing system to ensure comprehensive customer support, aiming to significantly reduce support tickets by offering instant, 24/7 answers directly from your documentation.

Open-source UI Kit for LLMs to format text outputs into richer GUIs. LanguageUI is an open-source design system and UI Kit for giving LLMs the flexibility of formatting text outputs into richer graphical user interfaces. LanguageGUI is the UI Kit for LLMs, including dozens of unique UI elements that serve different use cases for rich conversational user interfaces.

AI storyteller that creates personalized stories with children as main characters. Ada is an AI Large Language Model (LLM) that specializes in writing immersive stories. It creates magical triumphs and illustrates them with the facial features of the child. Ada allows kids to be the main characters in their favorite stories, featuring characters like Iron Man, Hulk, and Elsa.

Niche job board for prompt engineering roles. Prompt Engineering Jobs is a niche job board tailored to connect innovative companies with skilled professionals in the field of prompt engineering. It offers curated listings, tools, learnings, and networking opportunities to maximize career potential and elevate job searches.

AI-powered knowledge management and AI/ML consulting services. Semafind is an AI-enabled knowledge management platform that helps teams and businesses store, share, semantically search, and explore their private information to boost productivity. It also provides research and engineering consulting services in AI, ML, and Data Science, offering tailored algorithms to enhance competitive edge and drive business growth.

Democratizing access to advanced financial data with live market and off-market event views. Toyon.Live aims to democratize access to advanced financial data through up-to-date joined views on both market and off-market events, by combining the power of state-of-the-art streaming data processing technologies with the latest advances in LLM. It provides live spectrums of finance, including trending and fading stocks and currencies, along with related scores and metrics.

Ragie is a managed RAG service for developers to build generative AI applications. Ragie is a fully managed RAG-as-a-Service (Retrieval-Augmented Generation) built for developers to streamline the ingestion, chunking, and multimodal indexing of structured and unstructured data. It offers simple APIs and SDKs, seamless integration with data sources like Google Drive, Notion, and Confluence, and built-in advanced features like summary indexing, chunk reranking, and flexible vector filtering to help applications deliver state-of-the-art generative AI.

Private AI tools for complex enterprises, focusing on financial, legal, and regulatory compliance. LLMWare AI provides pioneering AI tools built for financial, legal, compliance, and regulatory-intensive industries in private cloud environments. It offers an innovative end-to-end solution, from specialized LLMs to RAG frameworks, enabling complex enterprises to leverage AI securely and efficiently. LLMWare focuses on private AI solutions, allowing users to run AI models locally on PCs and laptops, ensuring data privacy and control. The platform supports features like on-device document search, natural language SQL queries, and more, all without requiring an internet connection after initial setup.

Healthcare NLP solutions for medical data analysis and personalized patient care. Insights AI provides healthcare NLP solutions, including medical data curation, annotation, model training, and testing. They offer services such as medical data collection and annotation, leveraging their Omniview LLM, fine-tuned on 30M patient charts, for precise and fast processing of complex information. Their technology includes OCR, NER, Data De-identification, and Clinical APIs to simplify medical data analysis, derive greater clinical insights, and deliver personalized patient care.

A private platform for chatting, automation, and content generation using multiple LLMs. CosmoSpeak is a platform that allows users to chat, automate tasks, and generate content using over 30 Large Language Models (LLMs) privately. It offers a way to explore Space Engineering through AI and provides a free trial to get started. It also features Niddam_AI, a private chatbot.

Open-source library for building fast, model-agnostic AI agents with memory and tools. Agno is a lightweight, open-source library to build lightning-fast, model-agnostic multimodal AI agents. It allows users to add memory, knowledge, tools & reasoning to their agents. It's an open-source platform to build, ship and monitor agentic systems, designed to be model agnostic, blazing fast, and future-proof.

AI-powered command-line tool for shell prompting and autocompletion. Butterfish is a command-line tool that adds AI prompting to your shell (bash, zsh) using OpenAI or compatible APIs. It's like Github Copilot for your shell, allowing you to use LLMs for software engineering tasks directly from the command line. It provides contextual AI help, command autocompletion, and more.

In-browser Postgres sandbox with AI assistance for database creation and management. database.build (formerly postgres.new) is an in-browser Postgres sandbox with AI assistance. It allows users to instantly spin up unlimited Postgres databases that run directly in the browser and soon, deploy them to S3. Each database is paired with a large language model (LLM) to enable features like CSV import, report generation, chart creation, and database diagram building.

No-code web scraping tool leveraging AI for effortless data extraction. No-Code Scraper is a no-code scraping tool that enables you to extract data from any website effortlessly without needing to write code or manage complex scripts. By leveraging large language models, it simplifies the data extraction process, making it accessible to everyone. It aims to solve the pain points of traditional web scraping by providing a simple, reliable, and ready-to-use platform that eliminates coding and maintenance headaches.

AI-native API gateway for AI Agent development and LLM API management. Higress is an AI native API gateway based on Istio and Envoy, which can be extended with Wasm plugins written in Go/Rust/JS. It offers AI Gateway, MCP Server Hosting, Kubernetes ingress controller, Microservice gateway and Security gateway. Higress AI网关提供多模型灵活切换与兜底重试、大模型内容安全与合规、语义化缓存、多 API Key 均衡、Token 配额管理和限流、大模型流量灰度、调用成本审计等能力，帮助企业开发 Agent、管理LLM API.

Weavel automates prompt engineering for optimized and accurate prompts. Weavel automates prompt engineering, delivering the best prompts 50x faster than humans. Simply input your prompt and receive optimized prompts with highest accuracy. Boost your prompt's accuracy by an average 20% in less than 5 minutes. Weavel is also building Typa, the storytelling platform for modern companies.

Open-source AI models from OpenAI, free for developers. GPT-Oss offers OpenAI's 120B and 20B open-source language models, designed to be run locally with a Mixture of Experts (MoE) architecture. It is free for developers and provides powerful AI capabilities with features like a 131k context window, hardware flexibility (H100 GPUs or consumer hardware), and a privacy-first approach by running entirely on user hardware. It aims to bring advanced AI to the open-source community, enabling natural conversations, code generation, and complex reasoning.

CopilotChat simplifies code generation using Test-Driven Development (TDD). CopilotChat is designed to simplify code generation with the Test-driven development (TDD) process. Developers can easily specify their test cases and let CopilotChat generate code that not only fulfills their needs but also passes through validation. Copilot Chat iteratively interacts with LLM to refine the code until all test cases pass.

Cleanlab Chat offers a trustworthy language model (TLM) for reliable GenAI applications. Cleanlab Chat features Cleanlab’s Trustworthy Language Model (TLM), designed to solve reliability and hallucination issues in GenAI production. It aims to provide more accurate outputs than GPT-4, along with trustworthiness scores. It enables reliable LLM applications like text generation, data enrichment, and RAG at scale.

tinynudge.ai: Automates LLM prompts and emails responses at a set frequency. tinynudge.ai allows users to input a prompt and a frequency, and the platform will feed the prompt to a Large Language Model (LLM) and email the response at the user's desired frequency.

A tool to compare LLM API prices from top providers. LLM Price Check is a tool designed to help users quickly find the perfect Large Language Model (LLM) API for their budget. It allows users to instantly compare the latest prices from top providers like OpenAI, AWS, and Google. The platform offers a streamlined price comparison and calculator to optimize AI budgets efficiently.