llm
Collection of extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini
A free and open documentation platform built with Laravel and Filament, enhanced by Ollama for local AI features, focused on clarity, structure, and self-hosted simplicity.
Servers and tools from the community that connect models to files, APIs, databases, and more.
Related contents:
Challenging Software Optimization Tasks for Evaluating SWE-Agents.
A benchmark for evaluating language models' capabilities in developing high-performance software.
GSO (Global Software Optimization) is a benchmark for evaluating language models' capabilities in developing high-performance software. We present 100+ challenging optimization tasks across 10 codebases spanning diverse domains and programming languages. Each task provides a codebase and performance test as a precise specification, with agents required to optmize the codebase and measured against expert developer commits.
System Optimization through Reflective Text Evolution. Optimize prompts, code, and more with AI-powered Reflective Text Evolution.
GEPA (Genetic-Pareto) is a framework for optimizing arbitrary systems composed of text components—like AI prompts, code snippets, or textual specs—against any evaluation metric. It employs LLMs to reflect on system behavior, using feedback from execution and evaluation traces to drive targeted improvements. Through iterative mutation, reflection, and Pareto-aware candidate selection, GEPA evolves robust, high-performing variants with minimal evaluations, co-evolving multiple components in modular systems for domain-specific gains.
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:
A framework for building AI agents and applications.
AutoGen is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans.
Related contents:
A modern open source language for analyzing, transforming, and modeling data.
Malloy is a modern open source language for describing data relationships and transformations. It is both a semantic modeling language and a query language that uses an existing SQL engine to execute queries. Malloy currently can connect to BigQuery, Snowflake, PostgreSQL, MySQL, Trino, or Presto, and natively supports DuckDB. We've built a Visual Studio Code extension to facilitate building Malloy data models, querying and transforming data, and creating simple visualizations and dashboards.
Related contents:
A proposal to standardise on using an /llms.txt file to provide information to help LLMs use a website at inference time.
We propose adding a /llms.txt markdown file to websites to provide LLM-friendly content. This file offers brief background information, guidance, and links to detailed markdown files.
llms.txt markdown is human and LLM readable, but is also in a precise format allowing fixed processing methods (i.e. classical programming techniques such as parsers and regex).
Related contents:
An open-source framework for building AI-powered apps, built and used in production by Google
Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google
It offers a unified interface for integrating AI models from providers like Google, OpenAI, Anthropic, Ollama, and more. Rapidly build and deploy production-ready chatbots, automations, and recommendation systems using streamlined APIs for multimodal content, structured outputs, tool calling, and agentic workflows.
Related contents:
Chronon is a data platform for serving for AI/ML applications.
Chronon is a platform that abstracts away the complexity of data computation and serving for AI/ML applications. Users define features as transformation of raw data, then Chronon can perform batch and streaming computation, scalable backfills, low-latency serving, guaranteed correctness and consistency, as well as a host of observability and monitoring tools.
It allows you to utilize all of the data within your organization, from batch tables, event streams or services to power your AI/ML projects, without needing to worry about all the complex orchestration that this would usually entail.
Semantic Data Processing. Build data processing and data analysis pipelines that leverage the power of LLMs 🧠
Semlib is a Python library for building data processing and data analysis pipelines that leverage the power of large language models (LLMs). Semlib provides, as building blocks, familiar functional programming primitives like map, reduce, sort, and filter, but with a twist: Semlib's implementation of these operations are programmed with natural language descriptions rather than code. Under the hood, Semlib handles complexities such as prompting, parsing, concurrency control, caching, and cost tracking.
☁️ Convert any site to clean markdown & llms.txt. Boost your site's AI discoverability or generate LLM context for a project you're working with.
Mdream core is a highly optimized primitive for producing Markdown from HTML that is optimized for LLMs.
Chat Gipitty (Chat Get Information, Print Information TTY) is a command line client primarily intended for the official OpenAI Chat Completions API. It allows you to chat with language models in a terminal and even pipe output into it. While optimized for OpenAI's ChatGPT (with GPT-4 as the default model), it can also work with other providers that expose OpenAI-compatible endpoints.
Related contents:
Your personal AI productivity tool for a smarter brain.
🤯 Lobe Chat - an open-source, modern design AI chat framework. Supports multiple AI providers (OpenAI / Claude 4 / Gemini / DeepSeek / Ollama / Qwen), Knowledge Base (file upload / RAG ), one click install MCP Marketplace and Artifacts / Thinking. One-click FREE deployment of your private AI Agent application.
Related contents:
A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations).
🚀 Serena is a powerful coding agent toolkit capable of turning an LLM into a fully-featured agent that works directly on your codebase. Unlike most other tools, it is not tied to an LLM, framework or an interface, making it easy to use it in a variety of ways.
Related contents:
Your best engineers shouldn't Q&A all day.
Dosu is an AI-powered Github maintainer agent. Dosu helps open source maintainers encourage contributors, organize issues, triage bugs, answer questions, and more.
Dosu turns your codebase into a living knowledge base that every team member can understand—from engineering to operations—so builders can build.
Related contents:
EPFL, ETH Zurich, and the Swiss National Supercomputing Centre (CSCS) has released Apertus, Switzerland’s first large-scale open, multilingual language model — a milestone in generative AI for transparency and diversity. Trained on 15 trillion tokens across more than 1,000 languages – 40% of the data is non-English – Apertus includes many languages that have so far been underrepresented in LLMs, such as Swiss German, Romansh, and many others. Apertus serves as a building block for developers and organizations for future applications such as chatbots, translation systems, or educational tools.
Related contents:
Qwen Code is a coding agent that lives in the digital world.
Qwen Code brings the capabilities of advanced code models to your terminal in an interactive Read-Eval-Print Loop (REPL) environment. Qwen Code consists of a client-side application (packages/cli) that communicates with a local server (packages/core). Qwen Code also contains a variety of tools for tasks such as performing file system operations, running shells, and web fetching, which are managed by packages/core.
Related contents:
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.
Tensors and Dynamic neural networks in Python with strong GPU acceleration.
PyTorch is a Python package that provides two high-level features:
- Tensor computation (like NumPy) with strong GPU acceleration
- Deep neural networks built on a tape-based autograd system
You can reuse your favorite Python packages such as NumPy, SciPy, and Cython to extend PyTorch when needed.
Related contents:
Call all LLM APIs using the OpenAI format [Bedrock, Huggingface, VertexAI, TogetherAI, Azure, OpenAI, Groq etc.]
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Related contents:
Single-Binary Kubernetes Dashboard with Multi-Cluster Management & AI Integration. (OpenAI / Claude 4 / Gemini / DeepSeek / OpenRouter / Ollama / Qwen / LMStudio).
It provides a simple and rich realtime interface to manage and investigate your clusters.
Related contents:
Advanced LLM-powered brute-force tool combining AI intelligence with automated login attacks.
Related contents:
Build compliant AI chat agents, in minutes. LLM agents built for control. Designed for real-world use. Deployed in minutes.
Parlant gives you all the structure you need to build customer-facing agents that behave exactly as your business requires
An honest CLI for openrouter.ai. Fast and tmux-aware. ort sends your prompts to AI models on openrouter.ai.
It is built the old fashioned way, in solid Rust. It doesn't slow you down with Python interpreters. This is a modest 2 MiB ELF binary.
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:
Render any git repo into a single static HTML page for humans or LLMs.
Tired of clicking around complex file hierarchies of GitHub repos? Do you just want to see all of the code on a single page? Enter rendergit. Flatten any GitHub repository into a single, static HTML page with syntax highlighting, markdown rendering, and a clean sidebar navigation. Perfect for code review, exploration, and an instant Ctrl+F experience.
Build / Deploy Agent Workflows.
Launch agentic workflows with an open source, user-friendly environment for devs and agents.
Sim is an open-source AI agent workflow builder. Sim Studio's interface is a lightweight, intuitive way to quickly build and deploy LLMs that connect with your favorite tools.
Related contents:
A simple, open format for guiding coding agents, used by over 20k open-source projects.
Think of AGENTS.md as a README for agents: a dedicated, predictable place to provide the context and instructions to help AI coding agents work on your project.
Related contents:
- Improve your AI code output with AGENTS.md (+ my best tips) @ builder.io.
- #118 - Les news sur le développement web et l'IA pour septembre 2025 RC1 @ Double Slash :fr:.
- Optimizing repos for AI @ Tom Bedor's Blog.
- How to write a great agents.md: Lessons from over 2,500 repositories @ GitHub Blog.
- Writing a good CLAUDE.md @ humanlayer.
- Streamlining my user-level CLAUDE.md @ chris dzombak.
- The Complete Guide to CLAUDE.md @ builder.io.
- How to build self-improving coding agents - Part 1 @ Eric J Ma's Website.
- AGENTS.md outperforms skills in our agent evals @ Vercel.
- Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents? @ arXiv.
- Knowledge Priming @ martinFowler.com.
- J'ai mis deux IA en code review l'une contre l'autre — voici ce que ça donne @ Maxence Maireaux :fr:.
- Filesystems are having a moment @ madalitso.me.
- Your Docs Directory Is Doomed @ Jim Yagmin's Blog.
- Stop Wasting Hours Writing Unit Tests: Use GitHub Copilot to Explode Code Coverage Fast @ Build5Nines.
The Elegant Desktop Companion for Claude Code.
A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.
Related contents:
Your Ultimate Virtual Assistant.
Experience the future of AI assistance with advanced customization, flexible model support, and seamless integration. Newelle brings you the power of AI with unmatched flexibility and control.
Related contents:
Towards Natural‑Language Programming for GitHub Action.
Write agentic workflows in natural language markdown, and run them in GitHub Actions.
A Database for Your Mind.
One shared context across all your apps. Your transcripts inform your notes. Your notes guide your AI. Everything connects through a single folder of plain text and SQLite.
Epicenter is an ecosystem of open-source, local-first apps. Our eventual goal is to store all of your data—notes, transcripts, chat histories—in a single folder of plain text and SQLite. Every tool we build shares this memory. It's open, tweakable, and yours. Grep it, open it in Obsidian, host it wherever you like. The choice is yours.
The Easiest Way to Build Desktop Agents. Bytebot is a turn-key container for developers building desktop agents.
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.
Related contents:
RamaLama strives to make working with AI simple, straightforward, and familiar by using OCI containers.
RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.
Related contents:
a Kubernetes-native high-performance distributed LLM inference framework.
llm-d is a Kubernetes-native distributed inference serving stack, providing well-lit paths for anyone to serve large generative AI models at scale, with the fastest time-to-value and competitive performance per dollar for most models across most hardware accelerators.
Related contents:
💫 Industrial-strength Natural Language Processing (NLP) in Python.
spaCy is a library for advanced Natural Language Processing in Python and Cython. It's built on the very latest research, and was designed from day one to be used in real products.
spaCy comes with pretrained pipelines and currently supports tokenization and training for 70+ languages. It features state-of-the-art speed and neural network models for tagging, parsing, named entity recognition, text classification and more, multi-task learning with pretrained transformers like BERT, as well as a production-ready training system and easy model packaging, deployment and workflow management. spaCy is commercial open-source software, released under the MIT license.
Related contents:
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:
Yet Another Memory System. Content addressable storage with excellent search.
Persistent memory for LLMs and applications. Content‑addressed storage with deduplication, compression, semantic search, and full‑text indexing.
Chat UI for Coderunner.
coderunner-ui is a local‑first AI workspace that lets you:
- Chat with local or remote LLMs
- Run generated code inside a fully isolated Apple Container VM
- Browse the web and automate tasks via a built‑in headless browser (Playwright) All without sending your data to the cloud.
Related contents:
Run AI Generated Code Locally. A secure local sandbox to run LLM-generated code using Apple containers.
CodeRunner is an MCP (Model Context Protocol) server that executes AI-generated code in a sandboxed environment on your Mac using Apple's native containers.
Related contents:
Your AI workforce launchpad, in your pocket. Talk to Your AI Agents from Anywhere!
Omnara transforms your AI agents (Claude Code, Cursor, GitHub Copilot, and more) from silent workers into communicative teammates. Get real-time visibility into what your agents are doing, respond to their questions instantly, and guide them to success - all from your phone.
Cut Code Review Time & Bugs in Half. Instantly.
Supercharge your team to ship faster with the most advanced AI code reviews.
Related contents:
Chat with AI to build React apps instantly.
🔥 Clone and recreate any website as a modern React app in seconds.
POML (Prompt Orchestration Markup Language) is a novel markup language designed to bring structure, maintainability, and versatility to advanced prompt engineering for Large Language Models (LLMs). It addresses common challenges in prompt development, such as lack of structure, complex data integration, format sensitivity, and inadequate tooling. POML provides a systematic way to organize prompt components, integrate diverse data types seamlessly, and manage presentation variations, empowering developers to create more sophisticated and reliable LLM applications.
Train your AI self, amplify you, bridge the world.
an open-source prototype where you craft your own AI self—a new AI species that preserves you, delivers your context, and defends your interests.
Related contents:
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI.
Related contents:
Claude Code IDE integration for Emacs.
Claude Code IDE for Emacs provides native integration with Claude Code CLI through the Model Context Protocol (MCP). Unlike simple terminal wrappers, this package creates a bidirectional bridge between Claude and Emacs, enabling Claude to understand and leverage Emacs’ powerful features—from LSP and project management to custom Elisp functions. This transforms Claude into a true Emacs-aware AI assistant that works within your existing workflow and can interact with your entire Emacs ecosystem.
stagewise is the first frontend coding agent for existing production-grade web apps 🪄 -- Lives inside your browser 💻 -- Makes changes in local codebase 🤓 -- Compatible with all kinds of frameworks and setups 💪 .
Renderer for the harmony response format to be used with gpt-oss.
The gpt-oss models were trained on the harmony response format for defining conversation structures, generating reasoning output and structuring function calls. If you are not using gpt-oss directly but through an API or a provider like HuggingFace, Ollama, or vLLM, you will not have to be concerned about this as your inference solution will handle the formatting. If you are building your own inference solution, this guide will walk you through the prompt format. The format is designed to mimic the OpenAI Responses API, so if you have used that API before, this format should hopefully feel familiar to you. gpt-oss should not be used without using the harmony format as it will not work correctly.
Add React UI components to your AI agent.
A React package for building AI-powered applications with generative UI, where users interact through natural language.
LLM API Pricing Data.
Up-to-date pricing information for major LLM APIs including OpenAI, Anthropic, Google, and more. Compare costs across different AI models and find the best value for your use case.
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.
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
LangExtract is a Python library that uses LLMs to extract structured information from unstructured text documents based on user-defined instructions. It processes materials such as clinical notes or reports, identifying and organizing key details while ensuring the extracted data corresponds to the source text.
Related contents:
Deep Research at Your Fingertipsat Your Fingertips
Meet DeerFlow, your personal Deep Research assistant. With powerful tools like search engines, web crawlers, Python and MCP services, it delivers instant insights, comprehensive reports, and even captivating podcasts.
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
Understand your codebase.The Code Understanding Tool.
Sourcebot is a self-hosted tool that helps you answer questions about your code.
Build and deploy MCP agents.
Spin-up and aggregate MCP servers through a single endpoint and zero friction.
mcp-use is the easiest way to interact with mcp servers with custom agents. 🌐 MCP-Use is the open source way to connect any LLM to any MCP server and build custom MCP agents that have tool access, without using closed source or application clients.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Related contents: