llm
Open source chatbot that can be personalized using a markdown file.
Open reimplementation of Sakana Fugu — the 'one model to command them all' LLM orchestrator. Read → run → train → serve.
An open, runnable reverse-engineering of Sakana AI's Fugu — the "one model to command them all" LLM orchestrator.
Fugu is sold as a single model; it is really a policy over models — a tiny coordinator that, per query, routes work to a pool of frontier LLMs and returns one answer. Sakana's product and trained weights are closed. OpenFugu rebuilds the mechanism from the two papers + released artifacts, verifies it against real weights, trains a Conductor of our own, and serves it behind one OpenAI-compatible endpoint. Four stages, all working: read → run → train → serve.
A unified interface for LLMs. Better prices, better uptime, no subscription.
Related contents:
A simple prompt playground to test and share your prompt templates.
A tool for testing, debugging, and refining AI prompts. Supports variables, templates to improve prompt quality and speed up development.
Hertz-dev is an open-source, first-of-its-kind base model for full-duplex conversational audio.
a 744-billion-parameter mind, on your desk tiny engine, immense model.
Run GLM-5.2 — 744B Mixture-of-Experts — on hardware you already own. Pure C, zero dependencies, experts staged just-in-time across VRAM, RAM and disk. The galaxy behind this text is real: the model's measured expert atlas.
Generate code from the terminal! Supercharge Your AI Coding. Simple. Fast. Powerful. Codebuff works in your terminal.
Codebuff is an open-source AI coding assistant that edits your codebase through natural language instructions. Instead of using one model for everything, it coordinates specialized agents that work together to understand your project and make precise changes.
Automated AI localization for web & mobile apps.
AI localization for teams who ship fast. Translate apps, websites, and entire databases using the best LLM models.
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.
Semantic If On-Device. Decision model in your browser.
A local model can either read probabilities for your allowed options without decoding them, or write the same kind of distribution token by token. Pick a size, run both on your own GPU, and measure the difference.
Simple CLI tool for deterministic routing of queries between local and hosted LLM models.
A fast, offline hard-or-easy call on every prompt — scored deterministically, with no model call. Route the easy ones to your small/local model and the hard ones to your big one, or compose any model-router behind it.
This is a cleanroom deobfuscation of the official Claude Code npm package.
Related contents:
Your Open-Source Personal Assistant.
Leon is your open-source personal assistant who can live on your server. He does stuff when you ask him to.
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.
LangGraph is a library for building stateful, multi-actor applications with LLMs, used to create agent and multi-agent workflows.
Related contents:
ClearerVoice-Studio is an open-source, AI-powered speech processing toolkit designed for researchers, developers, and end-users. It provides capabilities of speech enhancement, speech separation, target speaker extraction, and more. The toolkit provides state-of-the-art pre-trained models, along with training and inference scripts, all accessible from this repository.
Open-Source Browser Agent for autonomously performing complex tasks on the web
An open-source AI agent that brings the power of Grok directly into your terminal. A conversational AI CLI tool powered by Grok with intelligent text editor capabilities and tool usage.
Automatic Generation of Visualizations and Infographics with LLMs.
LIDA is a library for generating data visualizations and data-faithful infographics. LIDA is grammar agnostic (will work with any programming language and visualization libraries e.g. matplotlib, seaborn, altair, d3 etc) and works with multiple large language model providers (OpenAI, PaLM, Cohere, Huggingface). Details on the components of LIDA are described in the paper here and in this tutorial notebook. See the project page here for updates!.
Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debug prompts, and monitor context window usage across your AI development sessions.
tokentap tracks token usage for LLM CLI tools with a live terminal dashboard. See exactly how many tokens you're using in real-time.
A comprehensive PHP Generative AI Framework using OpenAI GPT 4. Inspired by Langchain.
Related contents:
A CLI utility and Python library for interacting with Large Language Models.
A CLI tool and Python library for interacting with OpenAI, Anthropic’s Claude, Google’s Gemini, Meta’s Llama and dozens of other Large Language Models, both via remote APIs and with models that can be installed and run on your own machine.
Related contents:
- Large Language Models can run tools in your terminal with LLM 0.26 @ Simon Willison’s Weblog.
- Using AI Without Leaving the Terminal: A Guide to llm @ Ashwin's Blog.
- Evaluating LLMs for my personal use case @ Graham King.
- Kimi K3, and what we can still learn from the pelican benchmark @ Simon Willison’s Weblog.
Open-source LLMOps platform for hosting and scaling AI in your own infrastructure 🏓🦙 Paddler is an open-source LLMOps platform that lets teams run inference and deploy LLMs on their own infrastructure.
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:
AirLLM 70B inference with single 4GB GPU.
AirLLM optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card without quantization, distillation and pruning. And you can run 405B Llama3.1 on 8GB vram now.
🌟 OpenVoiceOS is an open-source platform for smart speakers and other voice-centric devices.
OpenVoiceOS is a community-driven, open-source voice AI platform for creating custom voice-controlled interfaces across devices with NLP, a customizable UI, and a focus on privacy and security.
La plateforme d'IA qui simplifie l'analyse des données à tous les métiers. Piloter aujourd'hui. Anticiper demain. Dès maintenant.
MIA est une solution No Code d’analyse de données, basée sur l’Intelligence Artificielle, qui s'adapte à votre profil. Simple. Efficace. Rapide
Artificial Intelligence Infrastructure-as-Code Generator.
aiac is a library and command line tool to generate IaC (Infrastructure as Code) templates, configurations, utilities, queries and more via LLM providers such as OpenAI, Amazon Bedrock and Ollama.
The CLI allows you to ask a model to generate templates for different scenarios (e.g. "get terraform for AWS EC2"). It composes an appropriate request to the selected provider, and stores the resulting code to a file, and/or prints it to standard output.
AI-powered multi-agent builder. Let AI build multi-agent systems for you Build with Agents SDK. Connect MCP tools. Open-source.
A new community-based approach to build truly open-source LLMs.
InstructLab Command-Line Interface. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.
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.
macOS menu bar app that exposes Apple's on-device Foundation Models as an OpenAI-compatible local API. Zero cloud. Zero dependencies.
Related contents:
Open Source LLM Engineering Platform. Traces, evals, prompt management and metrics to debug and improve your LLM application.
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Related contents:
LLM Service Fingerprinting Tool.
Simple LLM service identification - translate IP:Port to Ollama, vLLM, LiteLLM, or 30+ other AI services in seconds.
Julius is an LLM service fingerprinting tool for security professionals. It detects which AI server software is running on network endpoints during penetration tests, attack surface discovery, and security assessments.
Unlike model fingerprinting tools that identify which LLM generated text, Julius identifies the server infrastructure: Is that endpoint running Ollama? vLLM? LiteLLM? A Hugging Face deployment? Julius answers in seconds.
Related contents:
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.
Open Responses is an open-source specification and ecosystem for building multi-provider, interoperable LLM interfaces based on the OpenAI Responses API. It defines a shared schema, and tooling layer that enable a unified experience for calling language models, streaming results, and composing agentic workflows—independent of provider.
Stability AI Language Models.
This repository contains Stability AI's ongoing development of the StableLM series of language models and will be continuously updated with new checkpoints. The following provides an overview of all currently available models. More coming soon.
ell is a lightweight prompt engineering library treating prompts as functions.
Jules is an experimental coding agent that helps you fix bugs, add documentation, and build new features. It integrates with GitHub, understands your codebase, and works asynchronously — so you can move on while it handles the task.
Related contents:
LLM Frontend for Power Users.
SillyTavern provides a single unified interface for many LLM APIs (KoboldAI/CPP, Horde, NovelAI, Ooba, Tabby, OpenAI, OpenRouter, Claude, Mistral and more), a mobile-friendly layout, Visual Novel Mode, Automatic1111 & ComfyUI API image generation integration, TTS, WorldInfo (lorebooks), customizable UI, auto-translate, more prompt options than you'd ever want or need, and endless growth potential via third-party extensions.
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.
LLM Gateway to provide model access, logging and usage tracking across 100+ LLMs. All in the OpenAI format.
Related contents:
- You need more than a vector database @ Redis.
- À la découverte de liteLLM, une plateforme pour les gouverner tous @ Arneo's YouTube :fr:.
- TeamPCP supply chain attack spreads to PyPI @ Reversing Labs.
- How a Poisoned Security Scanner Became the Key to Backdooring LiteLLM @ snyk.
- Building a Kubernetes-native pattern for AI infrastructure at scale @ The New Stack.
- My minute-by-minute response to the LiteLLM malware attack @ futuresearch.
- A popular Python library just became a backdoor to your entire machine @ XDA.
- LLMs on Kubernetes Part 1: Understanding the threat model @ CNCF.
Cost-efficient private AI inference. Private Inference Network on Idle Macs.
Darkbloom routes encrypted requests to hardware-verified Apple Silicon providers, delivering comparable model performance at about 50% lower cost than typical API providers. Prompts stay hidden from operators, and Mac owners earn from compute they already own.
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).
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm.
DwarfStar is a small native inference engine optimized first for DeepSeek V4 Flash. It also supports GLM 5.2 and, on very high-memory machines, DeepSeek V4 PRO. It is self-contained and deliberately narrow, not a general GGUF runner. Model loading, prompt rendering, tool calls, KV state, the HTTP server, and the coding agent are built and tested together. The repository also includes tools and data for GGUF, imatrix, quality, and speed.
Laravel x LLMs. A unified interface for working with LLMs in Laravel.
Prism is a powerful Laravel package for integrating Large Language Models (LLMs) into your applications.
A lightweight next-gen data explorer - Postgres, MySQL, SQLite, MongoDB, Redis, MariaDB, Elastic Search, and Clickhouse with Chat interface
Related contents:
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
Kubernetes AI Toolchain Operator.
KAITO is an operator that automates the AI/ML model inference or tuning workload in a Kubernetes cluster. The target models are popular open-sourced large models such as falcon and phi-3.
Related contents:
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI.
Related contents:
Simple, secure, and reproducible packaging for AI/ML projects.
KitOps is an open source DevOps tool that packages and versions your AI/ML model, datasets, code, and configuration into a reproducible artifact called a ModelKit. ModelKits are built on existing standards, ensuring compatibility with the tools your data scientists and developers already use.
🔂 Run Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging
Automated workflow that orchestrates Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging - so multi-step projects complete while you sleep.
The global AI enabler cloud.
Deploy globally, scale easily, and build on the cloud that enables AI-native companies to thrive. Whether you’re building AI models, blockchain networks, or games, Latitude makes it easy.
Related contents:
Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are “shallow” and fail to plan and act over longer, more complex tasks. Applications like “Deep Research”, "Manus", and “Claude Code” have gotten around this limitation by implementing a combination of four things: a planning tool, sub agents, access to a file system, and a detailed prompt.
deepagents is a Python package that implements these in a general purpose way so that you can easily create a Deep Agent for your application.
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.
Related contents:
build ml models in natural language and minimal code.
Create machine learning models with minimal code by describing what you want them to do in plain words. You explain the task, and the library builds a model for you, including data generation, feature engineering, training, and packaging.
A simple, open format for giving agents new capabilities and expertise. Agent Skills are folders of instructions, scripts, and resources that agents can discover and use to do things more accurately and efficiently.
Related contents:
The framework for programming—not prompting—language models
DSPy is a declarative framework for building modular AI software. It allows you to iterate fast on structured code, rather than brittle strings, and offers algorithms that compile AI programs into effective prompts and weights for your language models, whether you're building simple classifiers, sophisticated RAG pipelines, or Agent loops.
Related contents:
The huggingface_hub library allows you to interact with the Hugging Face Hub, a machine learning platform for creators and collaborators. Discover pre-trained models and datasets for your projects or play with the hundreds of machine learning apps hosted on the Hub. You can also create and share your own models and datasets with the community. The huggingface_hub library provides a simple way to do all these things with Python.
Related contents:
Kubernetes-native AI serving platform for scalable model serving.
Related contents: