Open Source TypeScript Large Language Models (LLM) - Page 3
Sort By:
TypeScript Large Language Models (LLM)
View 371 business solutionsBrowse free open source TypeScript Large Language Models (LLM) and projects below. Use the toggles on the left to filter open source TypeScript Large Language Models (LLM) by OS, license, language, programming language, and project status.
-
Transforming NetOps Through No-Code Network Automation - NetBrainNetBrain, founded in 2004, provides a powerful no-code automation platform for hybrid network observability, allowing organizations to enhance their operational efficiency through automated workflows. The platform applies automation across three key workflows: troubleshooting, change management, and assessment.
-
The most user-friendly sales commission software for revenue-focused teamsRated as #1 sales compensation management software, Everstage helps businesses streamline commission administration, boost sales performance and improve ROI with actionable insights. Top features: No-code plan designer, detailed commission statements, advanced commission forecasting, quota management, queries & approval workflows, deferred commissions (ASC606), BI-powered reporting, and more.
-
1
Flock
Flock is a workflow-based low-code platform for building chatbots
Flock is a workflow-based low-code platform designed for building AI applications such as chatbots, retrieval-augmented generation systems, and multi-agent workflows. The platform uses a visual workflow architecture where different nodes represent processing steps such as input processing, model inference, retrieval operations, and tool execution. Developers can connect these nodes to create complex pipelines that orchestrate multiple language models and external services. Built on technologies such as LangChain, LangGraph, FastAPI, and Next.js, Flock combines a modern web interface with a flexible backend capable of supporting advanced AI workflows. The platform supports multi-agent collaboration, allowing developers to design workflows where different agents handle specialized tasks within the same system. Flock also includes features such as intent recognition, code execution nodes, and human-in-the-loop approval processes that make it suitable for production AI applications. -
2
Fulling
Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui
Fulling is an open-source AI-powered development environment designed to function as an autonomous full-stack engineering assistant. The platform provides a sandboxed workspace where developers can build complete applications with the help of an integrated AI coding agent. Instead of manually configuring development environments, the system automatically provisions the required infrastructure including a Linux environment, database services, and development tools. It integrates an AI pair programmer that can generate code, implement features, and assist with debugging tasks through natural language instructions. The environment also includes web-based terminals, file management tools, and version control capabilities to support collaborative software development workflows. Developers can connect external services by simply providing API credentials, allowing the AI system to automatically integrate features such as authentication or payment processing. -
3
Generative AI Use Cases (GenU)
Application implementation with business use cases
AWS Generative AI Use Cases is an open-source repository developed by AWS that provides practical examples and reference implementations for building applications powered by generative artificial intelligence. The project collects a wide range of real-world scenarios that demonstrate how organizations can use large language models and generative AI services within cloud-based architectures. Each example typically includes infrastructure templates, backend services, and application code that show how to integrate generative AI capabilities with other AWS services. These examples cover tasks such as document analysis, conversational assistants, content generation, and knowledge retrieval systems. The repository is intended to serve as both a learning resource and a starting point for developers who want to deploy generative AI solutions using AWS infrastructure. -
4
Grounded Docs
Open-Source Alternative to Context7, Nia, and Ref.Tools
Grounded Docs is an open-source implementation of a Model Context Protocol server designed to expose documentation and structured information as tools that AI agents can query. The project allows language models and agent frameworks to retrieve and interact with documentation through standardized MCP interfaces. By acting as an intermediary layer between documentation sources and AI tools, the server enables models to access structured documentation in a consistent and machine-readable format. This makes it easier for AI systems to answer technical questions, generate code examples, or retrieve reference material without requiring developers to manually integrate documentation into prompts. The architecture follows the MCP specification, which allows AI assistants and agent frameworks to connect to external tools through standardized protocols. -
Striven | All In One Business Management SoftwareStriven is the all-in-one business management software that lowers your costs, improves your operations, and makes work easier. Make your company’s data coherent, connected, and relevant.
-
5
Knowledge + Chat
Knowledge is a tool for saving, searching, accessing, and chatting
Knowledge is an open-source desktop application designed for organizing, exploring, and interacting with information gathered from websites, documents, and other digital sources. The platform allows users to collect knowledge from multiple formats including web pages, PDF files, videos, and other documents and organize them into structured projects and subprojects. These sources can then be visualized and explored using several views such as graph, grid, table, and calendar interfaces, making it easier to understand relationships between pieces of information. The application also includes a conversational chat interface that allows users to ask questions about stored sources and receive AI-generated explanations or summaries. A built-in Chromium-based browser enables users to capture and analyze web content directly within the application environment. -
6
LLMChat
Unified interface for AI chat, Agentic workflows and more
LLMChat is an open-source AI chat platform designed to provide a unified interface for interacting with multiple large language model providers while emphasizing privacy and advanced research capabilities. The system is built as a modern monorepo using technologies such as Next.js and TypeScript, enabling developers to deploy a full-featured web-based chatbot environment. One of its primary goals is to support sophisticated research workflows that combine conversational AI with information retrieval and reasoning tools. The platform includes specialized interaction modes such as deep research analysis and enhanced search capabilities that help users explore complex topics more effectively. It also incorporates agent-style workflows that allow the system to orchestrate multiple steps of reasoning or data retrieval during a conversation. -
7
LangChain.js
Building applications with LLMs through composability
Building applications with LLMs through composability. Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. But using these LLMs in isolation is often not enough to create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge. This library is aimed at assisting in the development of those types of applications. This is built to integrate as seamlessly as possible with the LangChain Python package. Specifically, this means all objects (prompts, LLMs, chains, etc) are designed in a way where they can be serialized and shared between languages. -
8
Langtrace
Open Telemetry based end-to-end observability tool for LLM apps
Langtrace is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations, and metrics for popular LLMs, LLM frameworks, vectors, and more.. Integrate using Typescript, and Python. Langtrace is an open-source observability tool that collects and analyzes traces and metrics to help you improve your LLM apps. -
9
Lunary
The production toolkit for LLMs. Observability, prompt management
Lunary helps developers of LLM Chatbots develop and improve them. -
Boon: The Agile Referral Hiring PlatformBoon's agile referral platform expands your recruiting power through AI, automation, integrations, and gamification.
-
10
MCP Router
A Unified MCP Server Management App (MCP Manager)
MCP Router is an open-source management platform designed to simplify the deployment and coordination of Model Context Protocol (MCP) servers used by AI agents. MCP is an emerging standard that allows language models and AI assistants to connect to external tools, data sources, and services through a structured interface. The MCP Router project acts as a centralized manager that helps developers run, configure, and coordinate multiple MCP servers within a single environment. This enables AI applications to access multiple tools and knowledge sources through a unified interface rather than connecting to each service individually. The project provides infrastructure for routing requests between clients and MCP servers, enabling scalable multi-tool agent systems. Developers building AI agents can use the platform to manage tool endpoints, control service availability, and simplify agent integration workflows. -
11
ModelFusion
The TypeScript library for building AI applications
ModelFusion is an open-source TypeScript library designed to simplify the development of AI-powered applications by providing a unified abstraction layer for interacting with different AI model providers. The framework allows developers to integrate large language models and other generative systems into JavaScript and TypeScript applications through a consistent and standardized API. Instead of writing separate integration logic for each provider, developers can use ModelFusion to handle common operations such as text generation, structured object generation, streaming responses, and tool calls. The library supports a wide range of model types, including text generation models, vision models, text-to-speech engines, speech-to-text systems, and embedding models. It also includes built-in production features such as observability hooks, logging, automatic retries, and error handling mechanisms that improve reliability when deploying AI systems in real-world environments. -
12
NativeMind Extension
Your fully private, open-source, on-device AI assistant
NativeMindExtension is an open-source browser extension that provides a private, on-device AI assistant designed to run without cloud dependencies. The project is built around a privacy-first model in which conversations, document analysis, translations, and writing assistance stay on the user’s device rather than being sent to external servers. It integrates with local model back ends such as Ollama and also supports WebLLM for quick in-browser trials, giving users a choice between stronger local setups and lighter no-install demonstrations. The extension is aimed at everyday browser workflows, offering features like multi-tab context awareness, webpage summarization, document understanding, contextual toolbars, and AI-assisted rewriting directly inside the browsing experience. Because it runs locally after setup, it is also positioned as an always-available assistant that avoids API quotas, network latency, and service outages common in cloud-based AI tools. -
13
Obsidian Text Generator Plugin
Text generator is a handy plugin for Obsidian
Text Generator is an open-source AI Assistant Tool that brings the power of Generative Artificial Intelligence to the power of knowledge creation and organization in Obsidian. For example, use Text Generator to generate ideas, attractive titles, summaries, outlines, and whole paragraphs based on your knowledge database. -
14
POML
Prompt Orchestration Markup Language
POML, or Prompt Orchestration Markup Language, is a structured markup language created to improve the organization and maintainability of prompts used in large language model applications. Traditional prompt engineering often relies on unstructured text, which can become difficult to manage as prompts grow more complex and incorporate dynamic data sources. POML addresses this issue by introducing an HTML-like syntax that allows developers to organize prompts into structured components such as roles, tasks, and examples. This structure enables prompts to be reused, modified, and versioned more easily within complex AI applications. The language also supports integration of multiple data types including documents, tables, and other external inputs that must be incorporated into prompts dynamically. By separating prompt content from presentation logic, POML enables developers to maintain cleaner and more maintainable prompt pipelines. -
15
PasteGuard
Masks sensitive data and secrets before they reach AI
PasteGuard is an open-source privacy proxy that protects sensitive information like personal data and API secrets by detecting and masking them before they reach large language model APIs such as OpenAI or Anthropic Claude. It sits between an application and the LLM provider, automatically replacing names, emails, tokens, and other personally identifiable information (PII) with placeholders so that external services never see raw sensitive values, and then optionally unmasking them in the returned output. PasteGuard supports two primary modes: mask mode, which anonymizes data and still uses external APIs; and route mode, which forwards sensitive requests to a local LLM inference engine while sending the rest to the cloud. It can be self-hosted via Docker, works with a wide range of SDKs and tools, and includes a browser extension for automatic protection in everyday AI chats. -
16
PeterCat
A conversational Q&A agent configuration system
PeterCat is an open-source conversational agent framework designed to create automated question-and-answer assistants for GitHub repositories and technical projects. The system allows developers to build AI-powered bots that understand project documentation, GitHub issues, and other repository content in order to answer questions from users or contributors. By simply providing the repository name or URL, the platform can automatically collect relevant project information and construct a knowledge base that the agent uses to respond to inquiries. The framework also provides a configuration system that allows developers to customize how the conversational agent behaves and how it integrates with external services. PeterCat can be deployed as a self-hosted solution and offers an application SDK that enables integration with websites, developer portals, and community support platforms. -
17
Pezzo
Open-source, developer-first LLMOps platform
Pezzo enables you to build, test, monitor and instantly ship AI all in one platform, while constantly optimizing for cost and performance. Packed with powerful features to streamline your workflow, so you can focus on what matters. Pezzo is a fully cloud-native and open-source LLMOps platform. Seamlessly observe and monitor your AI operations, troubleshoot issues, save up to 90% on costs and latency, collaborate and manage your prompts in one place, and instantly deliver AI changes. -
18
React Native AI
Full stack framework for building cross-platform mobile AI apps
React Native AI is a full-stack framework designed to simplify the development of AI-powered mobile applications using React Native. The project provides a ready-to-use infrastructure for building cross-platform apps that integrate large language models and other AI services. It supports real-time streaming responses from multiple AI providers and enables developers to build chat interfaces, AI-driven image generation tools, and natural language features within mobile apps. The framework includes backend components such as an Express-based server proxy that handles authentication and API communication with model providers. Developers can also integrate multiple models and services through a unified interface, making it easier to experiment with different AI capabilities. Built-in theming and UI templates allow developers to quickly create polished interfaces for AI chat and generative features. -
19
Rocketnotes
AI-powered markdown editor - leverage LLMs with your documents
RocketNotes is an open-source note-taking application designed to combine traditional knowledge management with artificial intelligence features that enhance how users capture and organize information. The project focuses on providing a fast, lightweight environment where users can create structured notes, manage personal knowledge bases, and interact with AI tools to summarize or expand their content. Instead of functioning purely as a document editor, RocketNotes integrates AI capabilities that assist with tasks such as generating insights, organizing ideas, and improving written content. The system is designed with productivity workflows in mind, allowing users to build interconnected notes and maintain organized collections of information. By combining note management with AI-assisted writing and summarization tools, the platform aims to help users process large volumes of information more efficiently. -
20
SkyAGI
SkyAGI: Emerging human-behavior simulation capability in LLM
SkyAGI is a python package that demonstrates LLM's emerging capability in simulating believable human behaviors. Specifically, SkyAGI implements the idea of Generative Agents and delivers a role-playing game that creates a very interesting user experience. Different from previous AI-based NPC systems, SkyAGI's NPC generates very believable human responses. The interesting observations in this demo show a huge potential for rethinking game development in many aspects, such as NPC script writing. -
21
SmythOS
Cloud-native runtime for agentic AI
SmythOS SRE (Smyth Runtime Environment) is an open-source runtime and development platform designed for building and operating production-grade AI agents. It provides a foundational infrastructure layer that functions similarly to an operating system for agentic AI systems, managing resources such as language models, storage, vector databases, and caching through a unified interface. Developers can use the runtime to create, deploy, and orchestrate intelligent agents across local machines, cloud environments, or hybrid infrastructures without rewriting their application logic. The platform includes a software development kit and command-line interface that allow developers to define agent workflows, manage execution environments, and automate deployment processes. SRE is designed with modular architecture so that connectors to external services or infrastructure providers can be swapped or extended without changing the agent’s core logic. -
22
Stripe AI
One-stop shop for building AI-powered products and businesses
Stripe AI is an open-source collection of tools and software development kits designed to help developers build AI-powered products and services that integrate directly with Stripe’s payment infrastructure. The project acts as a centralized repository containing resources, libraries, and examples that simplify the process of incorporating payments, billing, and financial workflows into AI applications. It enables developers to connect large language models and AI agents with Stripe APIs so that automated systems can perform actions such as handling transactions, managing subscriptions, or processing financial events. The platform is particularly relevant for companies building AI-driven products that require monetization, usage-based billing, or programmable financial interactions. By offering ready-to-use integrations and development tools, Stripe AI reduces the complexity of connecting AI systems with payment services. -
23
TONL
TONL (Token-Optimized Notation Language)
TONL is a cutting-edge data platform built around a production-ready serialization format designed to be both compact and powerful, combining human readability with performance features that make it suitable for large-scale applications and AI workflows. It provides a serialization format that significantly reduces token usage compared with traditional JSON, which can result in lower costs and more efficient prompt size utilization in LLM-driven systems. TONL isn’t just a format — it includes a rich API for querying, indexing, modifying, and streaming data, along with tools for schema validation and TypeScript code generation. The platform comes with a complete command-line interface that supports interactive dashboards and cross-platform usage in browsers and server environments, and its high test coverage gives developers confidence in stability. -
24
TaxHacker
Self-hosted AI accounting app. LLM analyzer for receipts
TaxHacker is an open-source, self-hosted accounting application that uses artificial intelligence to automate financial record management for freelancers, independent developers, and small businesses. The system is designed to simplify bookkeeping by automatically processing financial documents such as receipts, invoices, and transaction records. It integrates large language models to analyze these documents, extract relevant financial information, and categorize expenses or income based on configurable rules. Users can deploy the application on their own infrastructure, ensuring that financial data remains private and under their control rather than being processed by external services. The software provides tools for tracking income streams, monitoring expenses, and organizing financial records in a structured format. Because the system supports customizable prompts and categories, users can adapt the AI analysis to match their accounting workflows or tax requirements. -
25
Token-Oriented Object Notation
Token-Oriented Object Notation (TOON)
Token-Oriented Object Notation is an open specification and toolkit for a data serialization format called Token-Oriented Object Notation (TOON), designed specifically to optimize how structured data is passed to large language models. The format aims to reduce token overhead compared with traditional formats like JSON while remaining human-readable and structurally expressive. TOON represents the same data model as JSON but removes unnecessary syntax such as braces and quotes, relying instead on indentation and structured tokens to represent objects and arrays. This design allows prompts containing structured data to use significantly fewer tokens, which can reduce inference costs and improve efficiency in LLM applications. The project includes a formal specification, encoding rules, and reference implementations that developers can use to serialize and parse TOON data in their applications.
