LightMem is a lightweight and efficient memory management framework designed for Large Language Models and AI Agents. It provides a simple yet powerful memory storage, retrieval, and update mechanism to help you quickly build intelligent applications with long-term memory capabilities. The framework is minimalist in design, ensuring minimal resource consumption and fast response times. It offers a simple API for easy integration into applications with just a few lines of code. LightMem's modular architecture supports custom storage engines and retrieval strategies, making it flexible and extensible. It is compatible with various cloud APIs like OpenAI and DeepSeek, as well as local models such as Ollama and vLLM.

YuLan-Mini is a lightweight language model with 2.4 billion parameters that achieves performance comparable to industry-leading models despite being pre-trained on only 1.08T tokens. It excels in mathematics and code domains. The repository provides pre-training resources, including data pipeline, optimization methods, and annealing approaches. Users can pre-train their own language models, perform learning rate annealing, fine-tune the model, research training dynamics, and synthesize data. The team behind YuLan-Mini is AI Box at Renmin University of China. The code is released under the MIT License with future updates on model weights usage policies. Users are advised on potential safety concerns and ethical use of the model.

The react-native-nitro-mlx repository allows users to run LLMs, Text-to-Speech, and Speech-to-Text on-device in React Native using MLX Swift. It provides functionalities for downloading models, loading and generating responses, streaming audio, text-to-speech, and speech-to-text capabilities. Users can interact with various MLX-compatible models from Hugging Face, with pre-defined models available for convenience. The repository supports iOS 26.0+ and offers detailed API documentation for each feature.

FLUTE (Flexible Lookup Table Engine for LUT-quantized LLMs) is a tool designed for uniform quantization and lookup table quantization of weights in lower-precision intervals. It offers flexibility in mapping intervals to arbitrary values through a lookup table. FLUTE supports various quantization formats such as int4, int3, int2, fp4, fp3, fp2, nf4, nf3, nf2, and even custom tables. The tool also introduces new quantization algorithms like Learned Normal Float (NFL) for improved performance and calibration data learning. FLUTE provides benchmarks, model zoo, and integration with frameworks like vLLM and HuggingFace for easy deployment and usage.

AdaSociety is a multi-agent environment designed for simulating social structures and decision-making processes. It offers built-in resources, events, and player interactions. Users can customize the environment through JSON configuration or custom Python code. The environment supports training agents using RLlib and LLM frameworks. It provides a platform for studying multi-agent systems and social dynamics.

AgentKit Samples is a repository containing a series of examples and tutorials to help users understand, implement, and integrate various functionalities of AgentKit into their applications. The platform offers a complete solution for building, deploying, and maintaining AI agents, significantly reducing the complexity of developing intelligent applications. The repository provides different levels of examples and tutorials, including basic tutorials for understanding AgentKit's concepts and use cases, as well as more complex examples for experienced developers.

OneClickLLAMA is a tool designed to run local LLM models such as Qwen2.5 and SakuraLLM with ease. It can be used in conjunction with various OpenAI format translators and analyzers, including LinguaGacha and KeywordGacha. By following the setup guides provided on the page, users can optimize performance and achieve a 3-5 times speed improvement compared to default settings. The tool requires a minimum of 8GB dedicated graphics memory, preferably NVIDIA, and the latest version of graphics drivers installed. Users can download the tool from the release page, choose the appropriate model based on usage and memory size, and start the tool by selecting the corresponding launch script.

Beet is a collection of crates for authoring and running web pages, games and AI behaviors. It includes crates like `beet_flow` for scenes-as-control-flow bevy library, `beet_spatial` for spatial behaviors, `beet_ml` for machine learning, `beet_sim` for simulation tooling, `beet_rsx` for authoring tools for html and bevy, and `beet_router` for file-based router for web docs. The `beet` crate acts as a base crate that re-exports sub-crates based on feature flags, similar to the `bevy` crate structure.

Cyber is a superintelligence protocol that aims to create a decentralized and censorship-resistant internet. It uses a novel consensus mechanism called CometBFT and a knowledge graph to store and process information. Cyber is designed to be scalable, secure, and efficient, and it has the potential to revolutionize the way we interact with the internet.

MOSS-TTS Family is an open-source speech and sound generation model family designed for high-fidelity, high-expressiveness, and complex real-world scenarios. It includes five production-ready models: MOSS-TTS, MOSS-TTSD, MOSS-VoiceGenerator, MOSS-TTS-Realtime, and MOSS-SoundEffect, each serving specific purposes in speech generation, dialogue, voice design, real-time interactions, and sound effect generation. The models offer features like long-speech generation, fine-grained control over phonemes and duration, multilingual synthesis, voice cloning, and real-time voice agents.

S2A allows your large model API to support networking, searching, news, and web page summarization. It currently supports OpenAI, Gemini, and Moonshot (non-streaming). The large model will determine whether to connect to the network based on your input, and it will not connect to the network for searching every time. You don't need to install any plugins or replace keys. You can directly replace the custom address in your commonly used third-party client. You can also deploy it yourself, which will not affect other functions you use, such as drawing and voice.

VoiceBench is a repository containing code and data for benchmarking LLM-Based Voice Assistants. It includes a leaderboard with rankings of various voice assistant models based on different evaluation metrics. The repository provides setup instructions, datasets, evaluation procedures, and a curated list of awesome voice assistants. Users can submit new voice assistant results through the issue tracker for updates on the ranking list.

No-cost-ai is a repository dedicated to providing a comprehensive list of free AI models and tools for developers, researchers, and curious builders. It serves as a living index for accessing state-of-the-art AI models without any cost. The repository includes information on various AI applications such as chat interfaces, media generation, voice and music tools, AI IDEs, and developer APIs and platforms. Users can find links to free models, their limits, and usage instructions. Contributions to the repository are welcome, and users are advised to use the listed services at their own risk due to potential changes in models, limitations, and reliability of free services.

API Dash is an open-source cross-platform API Client that allows users to easily create and customize API requests, visually inspect responses, and generate API integration code. It supports various HTTP methods, GraphQL requests, and multimedia API responses. Users can organize requests in collections, preview data in different formats, and generate code for multiple languages. The tool also offers dark mode support, data persistence, and various customization options.

Free-LLM-Collection is a curated list of free resources for mastering the Legal Language Model (LLM) technology. It includes datasets, research papers, tutorials, and tools to help individuals learn and work with LLM models. The repository aims to provide a comprehensive collection of materials to support researchers, developers, and enthusiasts interested in exploring and leveraging LLM technology for various applications in the legal domain.

EVE is an official PyTorch implementation of Unveiling Encoder-Free Vision-Language Models. The project aims to explore the removal of vision encoders from Vision-Language Models (VLMs) and transfer LLMs to encoder-free VLMs efficiently. It also focuses on bridging the performance gap between encoder-free and encoder-based VLMs. EVE offers a superior capability with arbitrary image aspect ratio, data efficiency by utilizing publicly available data for pre-training, and training efficiency with a transparent and practical strategy for developing a pure decoder-only architecture across modalities.

Wanwu AI Agent Platform is an enterprise-grade one-stop commercially friendly AI agent development platform designed for business scenarios. It provides enterprises with a safe, efficient, and compliant one-stop AI solution. The platform integrates cutting-edge technologies such as large language models and business process automation to build an AI engineering platform covering model full life-cycle management, MCP, web search, AI agent rapid development, enterprise knowledge base construction, and complex workflow orchestration. It supports modular architecture design, flexible functional expansion, and secondary development, reducing the application threshold of AI technology while ensuring security and privacy protection of enterprise data. It accelerates digital transformation, cost reduction, efficiency improvement, and business innovation for enterprises of all sizes.

LightMem is a lightweight and efficient memory management framework designed for Large Language Models and AI Agents. It provides a simple yet powerful memory storage, retrieval, and update mechanism to help you quickly build intelligent applications with long-term memory capabilities. The framework is minimalist in design, ensuring minimal resource consumption and fast response times. It offers a simple API for easy integration into applications with just a few lines of code. LightMem's modular architecture supports custom storage engines and retrieval strategies, making it flexible and extensible. It is compatible with various cloud APIs like OpenAI and DeepSeek, as well as local models such as Ollama and vLLM.

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.