The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
The AI Scientist from Sakana AI is an experiment in automating the research loop: generating ideas, writing the code to test them, running the experiments, and drafting a paper about what happened. It is interesting less as something to use and more as something to look at, because it makes concrete a question everyone in the field is arguing about, which is how much of research is mechanical and how much is not. The output is real code and real drafts, and the honest reading of the results is that the pipeline works and the judgement of what is worth studying is still the hard part. Worth reading if you follow where agents are heading rather than looking for a tool to put to work tomorrow.
Assemble, configure, and deploy autonomous AI Agents in your browser.
AgentGPT lets you give an AI agent a goal in a browser tab and watch it break that goal into tasks and work through them, rather than answering one message at a time. You type something like research three competitors and summarise their pricing pages, and it plans the steps, runs them, and reports back. It is an open source project from Reworkd, and you can either use the hosted version or run the whole thing yourself. Either way it works by calling a language model on your behalf, so you supply an API key and the model provider bills you for what the agent uses. The appeal is seeing the planning happen in front of you. The catch is the same one every autonomous agent has: it is confident, it does not always know when it is stuck, and an open ended goal can run up a bill while going nowhere useful.
AnimateDiff adds motion to image generation models. Rather than being a separate video model, it is a motion module that plugs into an existing Stable Diffusion setup, so the characters and the style you already get from your favourite image model can be made to move without retraining anything. That design is why it spread so quickly through the image generation community: people could keep their existing models and checkpoints and add animation on top. The results are short clips rather than long video, and consistency across frames is the thing you fight with. It is open source, it expects you to be comfortable with a local image generation stack, and it rewards patience with settings.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
AutoGPT is the project that made autonomous agents a mainstream idea. You give it an objective, and it writes itself a task list, works through it using tools like web search and file access, and keeps going until it decides the objective is met. It is open source and has grown from the original script into a larger platform for building and running agents. It matters partly for what it does and partly for what it taught everyone: the demos that go well are the ones with a clear finish line, and the failures are almost always an agent that cannot tell it has gone wrong. If you want to understand how modern coding and research agents came to be shaped the way they are, this is the codebase that started the conversation.
Awesome-LLM: a curated list of Large Language Model
Awesome-LLM is a curated list: papers, models, tooling and courses about large language models, collected in one place and kept current by a community of contributors. It is not software and it will not do anything for you. What it is good for is orientation. If you need to find the important paper on a topic, or work out which open models exist in a category, or hand somebody a starting point that is not a search engine, a maintained list saves hours of wandering. Lists like this age quickly in a field that moves this fast, so check the dates on what you find, and treat it as a map rather than a verdict on what is best.
BitNet is Microsoft's inference framework for very low precision language models, the line of research that asks how far model weights can be squeezed before quality falls away. The practical point of it is hardware: models in this format are small enough and cheap enough to run on an ordinary processor, without the graphics card that usually decides whether you can run a model locally at all. That makes it interesting for anyone who wants text generation on a laptop, on a server without a GPU, or on hardware at the edge of a network. It is a research oriented project rather than a finished product, so the model choice is narrower than in the general ecosystem and you should expect to read the repository rather than follow a wizard.
Stop writing prompts from scratch, a searchable prompt library for ChatGPT, Claude, Gemini and Cursor · Русский 한국어 العربية हिन्दी ไทย ｜ 别再从头写提示词：现成的拿来就用，好用的收进自己的库
Written mainly in TypeScript. Released under the MIT licence.
ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, this extension provides a hub feature and convenience functions to access a wide range of information within ComfyUI.
Written mainly in Python. Released under the GPL-3.0 licence.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Written mainly in JavaScript. Released under the MIT licence.
Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
Fabric is a command line tool built around the idea that most useful prompting is repeatable. Instead of writing a fresh prompt each time, you keep a library of patterns, small named prompts for jobs like summarising an article, extracting the argument from an essay, or turning notes into a structure, and you pipe text through them from the terminal. Anything that can produce text on standard input can feed it, which makes it easy to wire into scripts and existing habits. It is open source and the pattern library is public, so you can read exactly what each one asks the model to do and change it. It suits people who already live in a terminal; if you do not, the same ideas exist in friendlier packaging elsewhere.
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
FastGPT is a platform for building question answering systems over your own knowledge base. You import documents, it handles the indexing and retrieval, and then a visual flow builder lets you decide what happens at each step: which sources to search, when to call a model, what to do with the answer. That flow builder is the part that distinguishes it from simpler document chat tools, because it lets non programmers assemble something closer to an application than a chat box. It is open source and can be self hosted, which is why it turns up in companies that cannot send internal documents to a third party. Expect to spend real time on setup and on tuning how documents are split, which is where the quality of the answers is won or lost.
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
Written mainly in Python. Released under the Apache-2.0 licence. The repository is archived and is no longer maintained.
Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.
Written mainly in Python. Released under the Apache-2.0 licence.
A reference containing Styles and Keywords that you can use with MidJourney AI. There are also pages showing resolution comparison, image weights, and much more!
Zero-config AI chat assistant. No API key needed, sign up and instantly chat with GPT-5, Claude 4, Gemini 2.5, DeepSeek & 100+ top models. Pay-as-you-go saves you more. Available on Web, iOS, macOS, Android, Linux, Windows.
Written mainly in TypeScript. Released under the MIT licence.
Compiles a demonstrated GUI task into a program that reports VERIFIED only if an independent check agrees. pip install openadapt; openadapt flow tutorial. Compiler lives in openadapt-flow.
Written mainly in Python. Released under the MIT licence.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Written mainly in Python. Released under the Apache-2.0 licence.
Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
The Prompt Engineering Guide from DAIR.AI is reading material rather than software: an open, maintained guide to how prompting actually works, from the basic shapes of an instruction through to techniques like chain of thought, retrieval and structured output. It is organised as a course you can work through, and it cites the papers behind each technique, which is what separates it from the thousands of prompt tip lists online. If you have been using models by instinct and want to know why some prompts work, this is the resource most likely to change how you write them. It costs nothing, needs nothing installed, and is worth an afternoon.
