Search Results for "llm" - Page 3
Sort By:
Showing 88 open source projects for "llm"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
APIPark
APIPark is the #1 open-source AI Gateway and Developer Portal
APIPark is an open-source, all-in-one AI gateway and API developer portal, that helps developers and enterprises easily manage, integrate, and deploy AI services. No matter which AI model you use, APIPark provides a one-stop integration solution. It unifies the management of all authentication information and tracks the costs of API calls. Standardize the request data format for all AI models. When switching AI models or modifying prompts, it won’t affect your app or microservices,... -
2
ComfyUI Workflows ZHO
My ComfyUI workflows collection
ComfyUI Workflows ZHO is a collection of reusable ComfyUI workflow files for generative image, video, 3D, and multimodal experiments. It brings together ready-made graphs for systems such as Stable Cascade, SD3, FLUX.1, Hunyuan Video, InstantID, PhotoMaker, and LivePortrait Animals. The repository also includes workflows that combine large language models with diffusion systems. Other examples cover ControlNet, image-to-image generation, inpainting, prompt visualization, upscaling, and... -
3
TensorZero
TensorZero is an open-source stack for industrial-grade LLM apps
tensorzero is a lightweight C++ library designed for tensor operations and numerical computing. It offers a minimal and readable implementation of core tensor functionality, making it ideal for educational purposes, lightweight applications, or those wanting to understand how tensor libraries work under the hood. With no external dependencies, tensorzero is easy to integrate into C++ projects needing basic multi-dimensional array support. -
4
Backtrack Sampler
An easy-to-understand framework for LLM samplers
Backtrack Sampler is a framework designed for experimenting with custom sampling strategies for language models (LLMs), enabling the ability to rewind and revise generated tokens. It allows developers to create and test their own token generation strategies by providing a base structure for manipulating logits and probabilities, making it a flexible tool for those interested in fine-tuning the behavior of LLMs. -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
OpenWiki
OpenWiki is a CLI that writes and maintains agent documentation
OpenWiki is a CLI from LangChain that writes and maintains documentation for codebases. It is designed specifically for AI agents that need reliable project context while working in a repository. The tool can generate a new openwiki/ documentation folder when none exists, then refresh that documentation as the code changes. It also updates agent instruction files such as AGENTS.md or CLAUDE.md so coding agents know to use the generated wiki. OpenWiki supports interactive sessions, one-shot... -
6
QodeAssist
QodeAssist is an AI-powered coding assistant plugin for Qt Creator
QodeAssist is an AI-powered coding assistant plugin specifically designed for Qt Creator, bringing modern AI capabilities directly into a C++ and QML development environment. It provides intelligent code completion, inline refactoring, and conversational chat interfaces that can appear as popups, side panels, or embedded views within the IDE. The plugin supports both local and cloud-based language model providers, including Ollama, llama.cpp, OpenAI, Claude, and others, allowing developers... -
7
ollama-hpp
Modern, Header-only C++ bindings for the Ollama API
...It is designed with performance and portability in mind, making it suitable for systems where low-level control and minimal overhead are important. The library exposes core Ollama functionality such as text generation and chat through a C++-friendly API, allowing developers to integrate local LLM capabilities into desktop, embedded, or high-performance applications. It includes support for streaming responses, enabling applications to process output as it is generated rather than waiting for full completions. The project also evolves alongside the Ollama API, adding support for newer features such as blob handling and improved model interaction capabilities. ... -
8
Mini Jinja
MiniJinja is a powerful but minimal dependency template engine
...MiniJinja can also be used as a small expression language or embedded template layer in larger applications. It is useful for configuration generation, HTML rendering, LLM chat templating, data workflows, and command-line templating. -
9
1Backend
Build AI (or any) apps with scalable microservices & microfrontends
1Backend is an AI-native full-stack platform for building distributed applications with microservices and microfrontends. It works as a framework, proxy, and runtime that reduces early infrastructure overhead for developers. The platform includes built-in capabilities for authentication, user accounts, service routing, microfrontend routing, email, and API access. It can run and program LLMs inside containers, making it suitable for AI applications as well as general software products.... -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
OWL
Optimized Workforce Learning for General Multi-Agent Assistance
OWL (Optimized Workforce Learning) is a sophisticated open-source framework built on the CAMEL-AI ecosystem for orchestrating teams of AI agents to collaboratively solve complex, real-world tasks with dynamic planning and automation capabilities. Unlike single-agent systems, it treats task completion as a collaborative workforce where agents take on specialized roles (planning, execution, analysis) and coordinate via a modular multi-agent architecture that supports flexible teamwork across... -
11
voice-input-src
Documents and exposes generated source for menu-bar workflows
voice-input-src documents and exposes the generated source workflow for a macOS menu-bar speech input application. Holding the Fn key starts recording, and releasing it transcribes and pastes text into the currently focused field. It uses Apple's streaming Speech Recognition framework and requires macOS 14 or newer. The application supports English, Simplified Chinese, Traditional Chinese, Japanese, and Korean, with the chosen language stored locally. A floating capsule displays a live... -
12
Orbiton
Snappy and configuration-free text editor/IDE for the terminal
Orbiton is a terminal-based text editor that incorporates AI-assisted capabilities directly into a lightweight and efficient command-line environment. It is designed for developers who prefer minimal interfaces but still want access to modern AI features such as code generation, editing assistance, and contextual suggestions. The editor emphasizes speed and simplicity, maintaining a small footprint while integrating with external language model providers. It allows users to interact with AI... -
13
Languine
Translate your application with Languine CLI powered by AI.
Languine is an AI-powered localization platform designed to automate and streamline the translation process for applications, ensuring seamless integration within development workflows. It offers intelligent, context-aware translations across over 100 languages, maintaining brand voice and tone consistency. It provides a command-line interface and continuous integration/continuous deployment integration, allowing developers to manage translations directly or automate them within existing... -
14
PydanticAI
Agent Framework / shim to use Pydantic with LLMs
When I first found FastAPI, I got it immediately. I was excited to find something so innovative and ergonomic built on Pydantic. Virtually every Agent Framework and LLM library in Python uses Pydantic, but when we began to use LLMs in Pydantic Logfire, I couldn't find anything that gave me the same feeling. PydanticAI is a Python Agent Framework designed to make it less painful to build production-grade applications with Generative AI. Built by the team behind Pydantic (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor, and many more). -
15
any-agent
A single interface to use and evaluate different agent frameworks
...The library is designed to simplify experimentation and benchmarking, making it easier to compare agent behavior, performance, and reliability across different implementations. It includes built-in evaluation tools such as LLM-as-a-judge and agent-as-a-judge methodologies, which help developers assess output quality systematically. any-agent also supports advanced capabilities like tracing, callbacks, and standardized observability through OpenTelemetry, ensuring consistent monitoring across frameworks. Additionally, it allows agents to be deployed using protocols like MCP. -
16
Ellama
Ellama is a tool for interacting with large language models from Emacs
Ellama is an Emacs integration that brings large language model capabilities directly into the Emacs editor environment, focusing on extensibility and deep workflow integration. It allows users to interact with local or remote models through a unified interface embedded within their editing sessions. The tool is designed to align with Emacs’ philosophy of customization, enabling users to define prompts, commands, and behaviors tailored to their workflows. It supports conversational... -
17
Groq TypeScript / Node.s
The official Node.js / Typescript library for the Groq API
Groq TypeScript / Node.s (also often referred to as “groq-sdk” on npm) is the official Node.js / TypeScript client library for Groq’s REST API, enabling JavaScript/TypeScript developers to integrate LLM and AI-powered services into web backends, serverless functions, or frontend apps. It exports strongly-typed interfaces for models, chat completions, file uploads (e.g. for audio transcription), and other endpoints, allowing for better type safety and developer experience when using Groq from TypeScript. The library also supports passing different input types (file streams, blobs, fetch responses) for media-related endpoints, making it flexible for diverse environments (backend, browser, serverless). ... -
18
FastMCP Framework
A TypeScript framework for building MCP servers
...Because it’s built in TypeScript and designed with modern deployment targets (Node.js, Cloudflare Workers, etc), it aims to support production-ready MCP servers with strong type safety and extensibility. Developers can use it to build server back-ends that expose data or capabilities to LLM applications in a standardized way, reducing the custom boilerplate required for integrating with AI systems. It includes tooling for development (examples, CLI) and is open-source, inviting contributions and extensions. -
19
Tunix
A JAX-native LLM Post-Training Library
Tunix is a JAX-native library for post-training large language models, bringing supervised fine-tuning, reinforcement learning–based alignment, and knowledge distillation into one coherent toolkit. It embraces JAX’s strengths—functional programming, jit compilation, and effortless multi-device execution—so experiments scale from a single GPU to pods of TPUs with minimal code changes. The library is organized around modular pipelines for data loading, rollout, optimization, and evaluation,... -
20
Fabric
Fabric is an open-source framework for augmenting humans using AI
...Patterns can be customized with variables, chained into pipelines, and applied to entire directories, which helps scale editorial or analytical tasks. A growing catalog of community patterns serves as a knowledge base for effective prompt engineering in practical contexts. In short, Fabric makes LLM work predictable and scriptable, so teams can share methods rather than one-off prompts. -
21
LangChain for .NET
C# implementation of LangChain
LangChain .NET is a C# implementation of the LangChain framework that enables developers to build LLM-powered applications using the .NET ecosystem. The project aims to replicate the core abstractions of LangChain, such as chains, agents, and vector stores, while adapting them to the conventions and strengths of C#. It emphasizes composability, allowing developers to build complex workflows by combining modular components that interact with language models and external data sources. ... -
22
LoopTroop
Free, open-source local GUI orchestrator for AI coding.
LoopTroop is a local-first, open-source GUI app for running complex AI coding tickets from start to finish across multiple projects. Instead of one long chat that suffers context rot, an LLM Council plans the work, atomic Beads run in isolated git worktrees, and Ralph Loops retry failed steps with fresh context. The result is a transparent, auditable workflow from ticket to reviewable PR, with logs and artifacts visible in one pane. -
23
Temporal Inference Engine
A real time inference engine for temporal logical specifications
A real time inference engine for temporal logical specifications, which is able to acquire, process and generate any binary or real signal through POSIX IPC, files or UNIX sockets. Specifications of signals and dynamic systems are represented as special graphs and executed in real time, with a predictable sampling time of few milliseconds. Real time signal processing, dynamic system control, state machine modeling and logical property verification are some fields of application of this... -
24
Astro Stardrive Boilerplate
The Astro boilerplate to create super stable websites even faster
...It skips the first 36 steps of creating a high-class website, giving you a fast, secure, accessible, and SEO-optimized foundation without reinventing the wheel. What makes it special: it is LLM-friendly by design, with dedicated AI guidance files so coding assistants immediately understand the project. It also prepares your site for WebMCP, auto-populates an llms.txt, and generates Schema.org structured data automatically. Out of the box: powerful blog, Markdown-driven events with Add to Calendar buttons, full i18n, light/dark mode, configurable pricing table, WCAG-ready accessibility, and a thousand SEO and GEO tweaks. ... -
25
gptstudio
GPT RStudio addins that enable GPT assisted coding, writing & analysis
gptstudio is an R package and RStudio Addins interface that enables interactive use of large language models (OpenAI, HuggingFace, etc.) from within R. It includes a Chat add-in and source editing helpers to query models, generate code, comment or refactor code, and manage conversations—all integrated into RStudio using Shiny and bslib.