AI Agents & Automation

Fara-7B is Microsoft's first agentic small language model (SLM) specifically engineered for computer use. With only 7 billion parameters, it offers an ultra-compact solution for automating multi-step tasks on behalf of users. Unlike traditional chat models, Fara-7B interacts with computer interfaces visually, perceiving webpages and performing actions like scrolling, typing, and clicking directly on predicted coordinates without relying on accessibility trees. This design allows for efficient on-device deployment, reducing latency and enhancing privacy by keeping user data local. Fara-7B completes tasks efficiently, averaging only ~16 steps per task, and achieves state-of-the-art performance within its size class, competing with larger agentic systems. It is trained on 145K trajectories using a novel synthetic data generation pipeline built on the Magentic-One multi-agent framework, and is based on Qwen2.5-VL-7B with supervised fine-tuning.

Towhee Examples offers a diverse collection of applications designed to analyze unstructured data using the Towhee framework. These examples cover a wide range of tasks, such as reverse image search, reverse video search, audio classification, and question and answer systems. Additionally, it includes applications for molecular search and deepfake detection. The platform aims to democratize the process of generating embedding vectors (x2vec) by providing easily runnable examples that leverage machine learning models and operations. It supports various models like ResNet, VGG, EfficientNet, ViT for image tasks, DPR for NLP, and Pytorchvideo for video. This resource is ideal for developers and data scientists looking to implement advanced data analysis solutions.

open-llms is a comprehensive GitHub repository that serves as a curated list of open Large Language Models (LLMs) explicitly licensed for commercial use, including Apache 2.0, MIT, and OpenRAIL-M. This resource is invaluable for developers, researchers, and businesses looking to integrate open-source LLMs into their applications without licensing concerns. The repository details each model's release date, available checkpoints, associated research papers or blog posts, parameter sizes, context lengths, and specific licenses. It also includes a dedicated section for open LLMs tailored for code generation, offering insights into models like SantaCoder, CodeGen2, and StarCoder. Contributions to the list are welcomed, ensuring it remains up-to-date with the latest commercially viable open LLM releases.

rag-in-action is a comprehensive open-source code repository and training program focused on end-to-end RAG (Retrieval-Augmented Generation) system design, evaluation, and optimization. It breaks down RAG into 10 core components, offering practical projects to master the entire RAG workflow. The resource emphasizes tailoring RAG solutions to specific business needs and scenarios, rather than a one-size-fits-all approach. It covers modules from data loading and text chunking to vector embedding, retrieval processing, indexing, response generation, and system evaluation. The project supports both LangChain and LlamaIndex frameworks, with detailed environment configurations for GPU and CPU versions across Ubuntu, MacOS, and Windows.

Fuji-Web is an intelligent AI agent designed to automate web-based tasks directly from your browser's sidepanel. It understands user intent, navigates websites autonomously, and executes tasks on your behalf, providing explanations for each action taken. This transparency allows users to maintain control while leveraging AI for efficiency. The tool is installed as a browser extension, requiring an OpenAI or Anthropic API key for functionality. It supports complex and cross-tab workflows, with future plans for integration with browser automation frameworks like Puppeteer and Playwright, as well as features for saving and sharing workflows. Fuji-Web is open-source, allowing users to build the extension from source.

FunASR is a fundamental end-to-end speech recognition toolkit designed to bridge the gap between academic research and industrial applications. It offers a comprehensive suite of features including speech recognition (ASR), Voice Activity Detection (VAD), Punctuation Restoration, Language Models, Speaker Verification, Speaker Diarization, and multi-talker ASR. The toolkit provides convenient scripts and tutorials for both inference and fine-tuning of pre-trained models. FunASR boasts a vast collection of academic and industrial pre-trained models available on ModelScope and Hugging Face, including the highly accurate and efficient Paraformer-large. Recent updates include support for large models like Fun-ASR-Nano-2512 (31 languages), Whisper-large-v3-turbo, and Qwen-Audio multimodal models, alongside continuous improvements in real-time and offline transcription services, memory optimization, and multi-platform support.

NovaPlan AI is an intelligent study planning tool specifically designed for students. It leverages artificial intelligence to help users effectively organize their coursework, manage upcoming deadlines, and optimize their overall learning schedules. The platform creates personalized academic plans, taking into account individual learning styles and specific course requirements to ensure a tailored and efficient study experience. By automating the planning process, NovaPlan aims to reduce stress and improve academic performance for students.

free-llm-api-resources is a comprehensive list of services that provide free access or trial credits for API-based Large Language Model (LLM) usage. This resource is invaluable for developers, researchers, and students looking to experiment with LLMs without initial financial commitment. The list details various providers like OpenRouter, Google AI Studio, NVIDIA NIM, Mistral, HuggingFace, and others, specifying their free tiers, usage limits, and available models. It also includes providers offering trial credits such as Fireworks, Baseten, and AI21. The tool emphasizes legitimate services, explicitly excluding those that reverse-engineer existing chatbots, ensuring users find reliable and ethical resources for their projects.

Glow-TTS is an open-source generative flow model designed for text-to-speech (TTS) synthesis, utilizing a monotonic alignment search. Unlike many parallel TTS models, Glow-TTS does not require external aligners, making it a self-contained solution for generating mel-spectrograms from text. By combining the properties of flows and dynamic programming, it efficiently searches for the most probable monotonic alignment between text and the latent representation of speech. This approach ensures robust TTS, capable of generalizing to long utterances, and enables fast, diverse, and controllable speech synthesis. The model achieves significant speed-up over autoregressive models like Tacotron 2 with comparable speech quality and can be extended to multi-speaker settings. It also supports integration with vocoders like HiFi-GAN for improved synthesis quality.

ANIMA is a unique AI agent that distinguishes itself by simulating neurochemistry to drive its emotional responses and personality evolution. Unlike traditional AI models that rely on prompt engineering, ANIMA's emotions emerge organically from its internal biochemical state, which changes over time, similar to human circadian rhythms. This allows for a dynamic and evolving personality, where the AI might feel differently at dawn compared to midnight. Users can observe ANIMA's neurochemical levels (Serotonin, Dopamine, Oxytocin, Cortisol, Adrenaline, Endorphin, GABA) and mood in real-time, offering a transparent look into its internal processes. The platform also features Celeste, a voice tarot reader built on the ANIMA framework, demonstrating potential applications of this neurochemical simulation technology.

Twinning is an innovative AI platform designed for influencers and content creators to generate an AI clone of themselves. This digital twin can then interact with their followers, providing a unique way to engage and monetize their audience. Users provide information about their content and audience, record a 5-15 minute audio sample, and Twinning creates their AI twin. The platform supports unlimited interactions, professional voice cloning, audio messaging, texting, and analytics. It offers a tiered pricing structure based on follower count, with a 100% money-back guarantee if the user is not satisfied with their AI twin. This tool provides a novel method for influencers to scale their personal brand and generate income from fan interactions.

GeoTorchAI is a comprehensive spatiotemporal deep learning framework designed for machine learning practitioners. Built on top of PyTorch and Apache Sedona, it facilitates the easy and efficient implementation of deep learning models for various applications. The framework supports both raster imagery datasets, such as satellite imagery classification and segmentation, and spatiotemporal non-imagery datasets for prediction tasks like traffic volume, taxi/bike flow, and weather forecasting. GeoTorchAI includes modules for deep learning and data preprocessing, offering ready-to-use raster and grid datasets, PyTorch layers for popular models, and various transformation operations. It also supports scalable preprocessing on Apache Spark and Apache Sedona, making it a robust solution for large-scale spatiotemporal data analysis.

gpt-pro-mode offers a collection of notebooks designed to give users access to advanced 'Pro Mode' functionalities for different GPT models, including gpt-oss-pro-mode, gpt-5-pro-mode, and nemotron-pro-mode. Users can run these notebooks to explore and experiment with enhanced AI capabilities. The tool also provides an integrated Pro Mode API endpoint, allowing for programmatic access and integration into other applications. It supports a 'tournament mode' for generation and synthesis, which processes requests with a higher number of generations in groups for more comprehensive results. This open-source project encourages community contributions and feedback for feature additions.

Avanza Innovations is a global technology company focused on nascent technologies such as Blockchain, Artificial Intelligence, and Robotic Process Automation (RPA). They provide comprehensive services including consultancy, implementation, and program execution management. The company leverages its multi-award-winning blockchain platform, CIPHER, and its AI engine, IMPULSE, to deliver solutions for digital government transformation, financial regulation, trade, and supply chain management. Avanza Innovations also assists organizations in transitioning to Web 3.0, offering strategy, ideation, implementation, and tokenomics expertise. Their solutions cater to a wide range of sectors including government, real estate, healthcare, telecommunication, and finance, aiming to drive digital transformation and efficiency.

AgentStore functions as a dedicated online resource providing comprehensive information and various resources pertaining to 'agents'. While the specific nature of these agents is not detailed, the platform aims to be a primary source for users seeking knowledge and general interest topics within this domain. It appears to be a content-focused website designed to inform and guide visitors through various aspects of agent-related subjects, offering a centralized location for research and understanding.

gpt-3-experiments is a GitHub repository offering a collection of test prompts for OpenAI's GPT-3 API, alongside the resulting AI-generated texts. This resource is designed to showcase the robustness and capabilities of the GPT-3 model. The repository also features a Python script, `openai_api.py`, which enables users with OpenAI API access to efficiently query texts from the API, bypassing the web interface. All generated texts within the repository are presented in their original, unedited, and uncurated form, unless explicitly noted. The script allows for generating texts at various temperatures (0.0, 0.7, 1.0, 1.2) to explore different levels of 'creativity' in the AI's output. Users can configure their OpenAI API secret key and run the script from the command line to generate texts based on custom prompts or text files.

gpt4v-browsing is an open-source tool designed for web scraping and information extraction using the GPT-4 Vision API and Puppeteer. Users can ask questions, and the tool will browse to a specified website, take a screenshot, and then leverage the GPT-4 Vision API to analyze the image and provide answers. The JavaScript version offers enhanced functionality, allowing it to not only open URLs directly but also interact with web pages by clicking on links. This makes it a versatile solution for automating tasks that require visual understanding and interaction with web content, providing a powerful way to gather insights from dynamic web pages.

qomplement is an AI agent designed to automate desktop tasks across various software applications, significantly streamlining workflows by automating repetitive processes. This tool is particularly useful for tasks such as document filling and data entry, enhancing overall productivity for individuals and businesses. By leveraging AI, qomplement aims to reduce manual effort and potential errors associated with routine administrative work. Its focus on automating desktop interactions makes it a valuable asset for improving efficiency in daily operations.

GPTFuzz is an open-source tool designed for red teaming large language models (LLMs) by automatically generating jailbreak prompts. This process helps identify vulnerabilities and weaknesses in AI models, ultimately enhancing their robustness and security. The repository provides the official codebase for "GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts." It includes datasets for harmful questions and human-written templates, along with a finetuned RoBERTa-large model for judgment. Researchers can use GPTFuzz to generate their own adversarial templates and contribute to building a general black-box fuzzing framework for LLMs.

GraphNeuralNetwork is an open-source project offering implementations and experimental setups for popular graph neural network models. It currently supports Graph Convolutional Networks (GCN), GraphSAGE, and Graph Attention Networks (GAT). This tool is designed for researchers and developers who are working on graph-based machine learning tasks and need to experiment with or apply these advanced neural network architectures. The repository provides clear instructions on how to set up the environment and run examples for each model, facilitating quick adoption and experimentation. It serves as a valuable resource for understanding and utilizing the core concepts of graph neural networks.

RAGHub serves as a comprehensive, community-driven directory for the rapidly expanding field of Retrieval-Augmented Generation (RAG). It curates a living collection of new and emerging RAG frameworks, projects, and resources, addressing the challenge of keeping up with the constant influx of new tools. The platform aims to help users navigate the RAG ecosystem, providing a centralized place to discover innovations and assess the relevance of various tools. RAGHub categorizes resources into RAG Frameworks, Evaluation and Optimization Frameworks, Engines, Data Preparation Frameworks, Projects, and general Resources. It encourages community contributions, allowing users to add new tools and insights, fostering a collaborative environment for RAG development.

R-KV is a novel method for redundancy-aware KV cache compression specifically designed for large language models (LLMs) that rely on chain-of-thought (CoT) or self-reflection for reasoning tasks. It addresses the issue of bloated key-value (KV) caches during inference by ranking tokens on-the-fly for both importance and non-redundancy, retaining only the most informative and diverse ones. This approach allows for significant memory savings, up to 90%, and improved throughput (up to 6.6x) during long CoT generation, often with zero or even negative accuracy loss. R-KV is a plug-and-play, training-free solution that acts as a lightweight wrapper for any autoregressive LLM, making it easy to integrate into existing inference pipelines or RL roll-outs.

eesel.ai offers fully autonomous AI teammates designed to enhance support, content creation, and operational tasks. These AI agents seamlessly integrate into your existing applications such as Slack, Zendesk, and email, making them ready to use in minutes. The platform is ideal for automating responses, handling Tier 1 support tickets, and drafting content like blog posts. eesel.ai operates on a usage-based pricing model, charging per task with no platform or per-seat fees, and includes a $50 free trial to get started without a credit card. It supports various task complexities, from light dashboard questions to heavy blog post drafts, ensuring flexible and controlled spending with monthly usage limits.

SGLang is a high-performance serving framework designed for large language models and multimodal models, focusing on low-latency and high-throughput inference. It supports a wide range of hardware, including NVIDIA, AMD, Intel, Google TPUs, and Ascend NPUs, and is compatible with most Hugging Face models and OpenAI APIs. Key features include RadixAttention for prefix caching, a zero-overhead CPU scheduler, prefill-decode disaggregation, speculative decoding, continuous batching, paged attention, and various parallelism techniques. SGLang also supports structured outputs, chunked prefill, quantization, and multi-LoRA batching. It is an open-source project with an active community, adopted by leading enterprises and institutions, and serves as a proven rollout backend for training frontier models.