OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.
First seen: April 03, 2026 | Streak: 1d
Analysis
Oh My Codex (OMX) is a specialized workflow orchestration layer designed to enhance the OpenAI Codex CLI by providing a structured environment for AI-driven software development. It functions as a wrapper that maintains Codex as the primary execution engine while introducing standardized workflows, project state management, and reusable agent skills through a hidden `.omx/` directory. By utilizing specific commands like `$deep-interview` for scoping, `$ralplan` for architecture, and `$team` or `$ralph` for execution, the project transforms raw CLI interactions into a cohesive, persistent development lifecycle.
This project is ideal for developers who already utilize Codex but desire a more robust, repeatable, and organized runtime to manage complex, multi-step coding tasks. It is gaining traction because it bridges the gap between chaotic prompt-based coding and disciplined software engineering by offering features like parallel team execution, durable state tracking, and professional-grade workflow templates. Ultimately, OMX appeals to power users looking to scale their AI development efforts by turning a manual command-line interface into a sophisticated, agentic coding platform.
Open Source AI Platform - AI Chat with advanced features that works with every LLM
First seen: April 03, 2026 | Streak: 1d
Analysis
Onyx is a comprehensive, self-hostable AI platform designed to provide a feature-rich chat interface that integrates with virtually any Large Language Model, including both commercial providers and local instances like Ollama or vLLM. The platform distinguishes itself through advanced capabilities such as autonomous AI agents, multi-step deep research, and a sophisticated RAG engine that utilizes hybrid search and knowledge graphs. Technically, it supports high-scale document indexing from over 40 external connectors and enables complex workflows through Model Context Protocol (MCP) and built-in code interpretation.
This project is highly beneficial for organizations and developers seeking to deploy private, enterprise-grade AI solutions that maintain strict data sovereignty and security, such as SSO and role-based access control. It is currently trending because it bridges the gap between simple chatbot interfaces and complex enterprise knowledge management systems, offering a "one-command" deployment path that appeals to both individual power users and large teams. By providing an open-source Community Edition alongside a robust Enterprise tier, Onyx positions itself as a versatile, scalable infrastructure layer for teams looking to implement secure and contextual AI workflows.
3. google-research/timesfm Not new today
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
First seen: February 21, 2026 | Streak: 3d
Analysis
TimesFM is a decoder-only foundation model developed by Google Research designed to perform robust time-series forecasting across diverse datasets. The latest 2.5 version utilizes a streamlined 200M parameter architecture that significantly increases context length support to 16k while introducing optional continuous quantile forecasting via a dedicated head. Technically, the model processes time-series input sequences to generate point and probabilistic forecasts, offering compatibility with both PyTorch and Flax backends for flexible deployment across various hardware accelerators.
Data scientists and machine learning engineers working on predictive analytics will find this project highly beneficial due to its ability to generalize across unknown domains without requiring extensive task-specific retraining. The repository is currently trending because it represents a major advancement in moving time-series analysis toward a generative foundation model paradigm, reducing the complexity of building custom forecasting pipelines. By providing an open-access implementation of state-of-the-art research, Google enables practitioners to integrate sophisticated, large-scale forecasting capabilities directly into their own applications.
Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.
First seen: April 03, 2026 | Streak: 1d
Analysis
OpenScreen is an open-source desktop application designed to simplify the creation of professional-grade product demos and screen recordings. Built using Electron, React, TypeScript, and PixiJS, the tool offers essential editing capabilities such as automatic and manual zooming, motion blur, video cropping, and timeline-based trimming. It further allows users to enhance their content with annotations, custom backgrounds, and variable playback speeds, all while supporting both microphone and system audio capture.
This project is primarily intended for developers, content creators, and marketers who seek an accessible alternative to expensive, subscription-based screen recording software like Screen Studio. It is currently gaining traction because it provides a "no-gotchas" free model that permits both personal and commercial use without watermarks or restrictive licensing. By offering a lightweight and transparent open-source solution, OpenScreen empowers users to produce high-quality walkthroughs while maintaining complete control over their workflow and assets.
The fastest and the most accurate file search toolkit for AI agents, Neovim, Rust, C, and NodeJS
First seen: April 03, 2026 | Streak: 1d
Analysis
FFF.nvim is a high-performance, opinionated fuzzy file-finding and grepping tool designed specifically for Neovim and AI agent workflows. Built with a focus on speed and accuracy, it utilizes a robust binary backend to deliver typo-resistant search results based on complex factors like file size, git status, and "frecency" (frequency and recency). Technically, the project operates as a versatile toolkit that integrates seamlessly into development environments through a flexible configuration system, supporting advanced features like live grep, globbing, and multi-threaded indexing.
This project is primarily intended for developers who rely on Neovim for efficient code navigation and AI agents that need a lightweight, memory-aware way to parse large codebases. By allowing AI agents to perform faster searches with fewer round-trips and reduced token consumption, it addresses a critical bottleneck in AI-assisted coding. It is currently trending because it optimizes developer productivity by bridging the gap between traditional text editors and modern AI tooling through a fast, reliable, and highly customizable interface.
6. f/prompts.chat Not new today
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
First seen: February 24, 2026 | Streak: 3d
Analysis
Prompts.chat is an extensive, open-source repository designed to curate and share high-quality prompt examples for modern AI models. Technically, the project functions as a versatile platform that provides prompts through web interfaces, downloadable CSV datasets, and seamless integrations like CLI tools and MCP servers for AI-powered development environments. Users can easily self-host their own private, branded prompt libraries using a straightforward setup wizard that supports custom authentication and enterprise-grade configurations.
This project is an invaluable resource for developers, educators, and enterprise teams seeking to standardize and optimize their interactions with AI assistants. It is trending because it bridges the gap between basic prompting and advanced prompt engineering through its interactive guides, while its public domain licensing and extensive academic recognition establish it as a foundational industry standard. By providing both educational content for children and robust infrastructure for organizations, Prompts.chat has cemented its status as the go-to repository for the global AI community.
7. sherlock-project/sherlock Not new today
Hunt down social media accounts by username across social networks
First seen: March 30, 2026 | Streak: 1d
Analysis
Sherlock is an open-source command-line tool designed to identify the presence of a specific username across hundreds of different social media platforms. By utilizing a collection of unique URL structures for each site, the application sends HTTP requests to verify if a profile exists and parses the server responses to confirm matches. This automated process replaces the tedious manual effort of searching for an individual's digital footprint, allowing users to consolidate OSINT (Open Source Intelligence) data efficiently.
This project is highly valuable for cybersecurity professionals, investigative journalists, and researchers who need to verify identities or map an individual’s online presence during background checks. It is trending because of the increasing importance of digital identity verification and the tool's accessibility, which allows users with varying levels of technical expertise to perform complex reconnaissance tasks. As data privacy concerns rise, Sherlock provides a transparent and powerful utility for those looking to understand the breadth of information publicly available across the internet.