✨ Fully autonomous AI Agents system capable of performing complex penetration testing tasks
First seen: February 21, 2026 | Streak: 1d
Analysis
PentAGI is an autonomous, AI-driven penetration testing platform designed to automate complex security assessments within isolated, sandboxed Docker environments. The system utilizes a multi-agent architecture—delegating tasks among specialized researchers, developers, and executors—while integrating over 20 professional security tools like Nmap, Metasploit, and SQLmap. To enhance decision-making and reliability, the platform leverages a smart memory system, Neo4j-based knowledge graphs, and persistent vector storage, all managed through a scalable, microservices-oriented backend.
This project is highly beneficial for information security professionals, ethical hackers, and security researchers who require a sophisticated, self-hosted solution to streamline and scale vulnerability discovery. It is currently trending because it represents the cutting edge of "Agentic AI," moving beyond simple chatbots to perform complex, multi-step real-world actions. By providing comprehensive reporting, real-time observability through Grafana and Langfuse, and support for a wide array of LLM providers, PentAGI offers a powerful framework for those seeking to modernize their security testing workflows.
Build ultra fast, tiny, and cross-platform desktop apps with Typescript.
First seen: February 21, 2026 | Streak: 1d
Analysis
Summary not available.
3. HailToDodongo/pyrite64 Not new today
N64 Game-Engine and Editor using libdragon & tiny3d
First seen: February 19, 2026 | Streak: 3d
Analysis
Summary not available.
4. obra/superpowers Not new today
An agentic skills framework & software development methodology that works.
First seen: February 04, 2026 | Streak: 5d
Analysis
Superpowers is an agentic framework designed to standardize the software development lifecycle by integrating a library of composable, automated "skills" directly into coding agents like Claude Code and Cursor. Instead of jumping straight to code, the system enforces a structured workflow that begins with Socratic brainstorming, proceeds to detailed implementation planning, and culminates in a rigorous subagent-driven development cycle. Technically, it functions as a plugin that triggers mandatory engineering protocols—such as strict test-driven development (TDD), git worktree management, and iterative code reviews—ensuring that agents maintain high-quality standards and consistent progress without requiring manual intervention.
This project is highly beneficial for developers and software teams looking to minimize the "hallucination" and ad-hoc coding patterns often associated with AI-assisted programming. It is trending because it addresses a critical gap in the current AI developer tool ecosystem: the transition from simple code generation to reliable, autonomous project execution that mirrors professional engineering discipline. By embedding best practices like YAGNI and DRY into the agent's core decision-making loop, Superpowers provides a repeatable, scalable methodology for building robust software applications.
5. aquasecurity/trivy Not new today
Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more
First seen: February 06, 2026 | Streak: 1d
Analysis
Trivy is a comprehensive, open-source security scanner designed to identify vulnerabilities, misconfigurations, and sensitive data across diverse environments, including container images, filesystems, and Kubernetes clusters. By leveraging a variety of scanners, it can generate software bills of materials (SBOMs), detect exposed secrets, and identify infrastructure-as-code (IaC) issues or software license violations. Technically, it functions as a highly versatile CLI tool that supports a wide range of platforms and programming languages, providing actionable security insights through automated scanning processes.
Development teams, DevOps engineers, and security professionals benefit from Trivy’s ability to integrate seamlessly into existing CI/CD pipelines, IDEs, and Kubernetes workflows. The project is trending because it simplifies the complex task of securing modern cloud-native applications, offering a unified solution that replaces multiple fragmented security tools. Its widespread adoption is further driven by its ease of use, extensive ecosystem support, and its status as a robust, community-backed project from Aqua Security.
🦔 PostHog is an all-in-one developer platform for building successful products. We offer product analytics, web analytics, session replay, error tracking, feature flags, experimentation, surveys, data warehouse, a CDP, and an AI product assistant to help debug your code, ship features faster, and keep all your usage and customer data in one stack.
First seen: February 21, 2026 | Streak: 1d
Analysis
Summary not available.
Find and fix problems in your JavaScript code.
First seen: February 21, 2026 | Streak: 1d
Analysis
Summary not available.
Official, Anthropic-managed directory of high quality Claude Code Plugins.
First seen: February 21, 2026 | Streak: 1d
Analysis
The `anthropics/claude-plugins-official` repository serves as the central, curated marketplace for high-quality extensions designed for Claude Code. It categorizes tools into internal Anthropic-maintained plugins and verified third-party community submissions, providing a standardized framework for integrating new capabilities like custom commands, agents, and skills. Technically, the repository enforces a specific directory structure and metadata requirement via `plugin.json` and `mcp.json` files, allowing users to seamlessly install and manage these enhancements directly through the Claude Code CLI.
Developers and power users who utilize Claude Code for complex automation tasks will benefit most from this centralized hub of verified functionality. The project is trending because it creates a unified ecosystem for extending AI agent capabilities, directly addressing the growing demand for customized, task-specific workflows. By vetting external contributions while providing clear development standards, Anthropic is successfully fostering an extensible platform that enhances Claude's utility in specialized technical environments.
Core libraries and experimental work for Effect v4
First seen: February 21, 2026 | Streak: 1d
Analysis
Summary not available.
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: 1d
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.