{"reportDate":"2026-05-23","heroSummary":"Watch how platform owners like Anthropic and language maintainers like .NET are building official skill libraries, while developers focus on knowledge graphs for deeper code context.","topChanges":["anthropics/claude-plugins-official shows major model providers are now building curated, App Store-like ecosystems to control quality and distribution.","Lum1104/Understand-Anything shows the shift in context augmentation from basic RAG to structured knowledge graphs for complex codebases.","supertone-inc/supertonic shows a parallel trend of pushing high-performance AI tasks like TTS onto local devices, contrasting with the cloud-centric agent model."],"categoryBlocks":[{"category":"AI Coding Tools & Agents","summary":"This category is dominated by ecosystem-building rather than new model creation. The focus is on tooling to make agents useful: knowledge graphs for code understanding (`Understand-Anything`, `codegraph`), official skill/plugin directories (`claude-plugins-official`), and standardized skill formats (`dotnet/skills`).","repos":[{"repoName":"Lum1104/Understand-Anything","repoUrl":"https://github.com/Lum1104/Understand-Anything","summary":"Transforms codebases into interactive knowledge graphs for AI agents. This approach to providing context is more structured than simple file retrieval, representing a move toward deeper, semantic code understanding. Its rise signals a key direction for improving agent capabilities.","signalBadge":"rising","spanPresence":["daily","weekly"],"stars":19983},{"repoName":"colbymchenry/codegraph","repoUrl":"https://github.com/colbymchenry/codegraph","summary":"Similar to Understand-Anything, this project creates a code knowledge graph. It emphasizes pre-indexing and local operation to reduce token usage and improve performance for various agents. Trending alongside a similar tool confirms the pattern of structured context becoming critical.","signalBadge":"rising","spanPresence":["daily","monthly","weekly"],"stars":18175},{"repoName":"anthropics/claude-plugins-official","repoUrl":"https://github.com/anthropics/claude-plugins-official","summary":"This is Anthropic's official, managed directory for Claude Code plugins. It's a significant platform play, aiming to create a curated, high-quality ecosystem similar to an app store, which could centralize and control the distribution of agent capabilities.","signalBadge":"new","spanPresence":["daily"],"stars":25960},{"repoName":"Imbad0202/academic-research-skills","repoUrl":"https://github.com/Imbad0202/academic-research-skills","summary":"A structured collection of prompts and workflows for academic research, packaged as 'skills' for Claude Code. It exemplifies the trend of codifying domain expertise into reusable components for AI agents, though it is a content library rather than a tool.","signalBadge":"repeated","spanPresence":["monthly","weekly"],"stars":19458},{"repoName":"ruvnet/RuView","repoUrl":"https://github.com/ruvnet/RuView","summary":"This project uses commodity WiFi signals for spatial intelligence and presence detection without cameras. It's an interesting application of signal processing, but its presence on a list dominated by software-based AI agents is an anomaly.","signalBadge":"new","spanPresence":["weekly"],"stars":64454},{"repoName":"rohitg00/agentmemory","repoUrl":"https://github.com/rohitg00/agentmemory","summary":"Provides persistent memory for AI coding agents, a critical component for building stateful, multi-step autonomous systems. Its repeated appearance on trending lists indicates sustained developer interest in solving the core challenge of agent continuity.","signalBadge":"repeated","spanPresence":["monthly","weekly"],"stars":16630},{"repoName":"multica-ai/andrej-karpathy-skills","repoUrl":"https://github.com/multica-ai/andrej-karpathy-skills","summary":"A single markdown file containing prompts and instructions for Claude Code, based on Andrej Karpathy's analysis of LLM pitfalls. It highlights the demand for expert-curated 'skills' to improve agent reliability and behavior.","signalBadge":"repeated","spanPresence":["daily","monthly"],"stars":148607},{"repoName":"dotnet/skills","repoUrl":"https://github.com/dotnet/skills","summary":"An official Microsoft repository for .NET and C# skills for AI coding agents. This is a strong signal that major programming ecosystems are formally embracing the 'skill' abstraction and building first-party integrations for AI agents.","signalBadge":"new","spanPresence":["daily"],"stars":2667},{"repoName":"ComposioHQ/awesome-codex-skills","repoUrl":"https://github.com/ComposioHQ/awesome-codex-skills","summary":"A curated list of skills for the Codex agent. While useful, the 'awesome-list' format is a common pattern in maturing technology areas and is less indicative of innovation than a new framework or tool.","signalBadge":"cooling","spanPresence":["monthly"],"stars":11165},{"repoName":"ChromeDevTools/chrome-devtools-mcp","repoUrl":"https://github.com/ChromeDevTools/chrome-devtools-mcp","summary":"This repository provides Chrome DevTools specifically for coding agents. It's an initiative by a major platform player (Google) to provide better integration points for agents, signaling the importance of browser automation in agent workflows.","signalBadge":"new","spanPresence":["daily"],"stars":41209},{"repoName":"HKUDS/ViMax","repoUrl":"https://github.com/HKUDS/ViMax","summary":"An agentic video generation framework that divides the task among specialized agents (Director, Screenwriter, etc.). Its repeated trend shows continued interest in structured, multi-agent approaches for complex creative tasks beyond code generation.","signalBadge":"repeated","spanPresence":["monthly","weekly"],"stars":6844},{"repoName":"mukul975/Anthropic-Cybersecurity-Skills","repoUrl":"https://github.com/mukul975/Anthropic-Cybersecurity-Skills","summary":"A large, structured collection of cybersecurity skills for agents, mapped to industry frameworks like MITRE ATT&CK. This demonstrates the application of the 'skill' concept to a highly specialized, compliance-driven domain.","signalBadge":"new","spanPresence":["daily"],"stars":6985},{"repoName":"multica-ai/multica","repoUrl":"https://github.com/multica-ai/multica","summary":"An open-source platform for managing coding agents as if they were team members. It aims to solve the orchestration problem, moving beyond single-agent scripts to coordinated, task-driven workflows. Addresses a key operational challenge for agent deployment.","signalBadge":"new","spanPresence":["daily"],"stars":31673},{"repoName":"AIDC-AI/Pixelle-Video","repoUrl":"https://github.com/AIDC-AI/Pixelle-Video","summary":"An automated short video generation engine. Like ViMax, it represents interest in applying agent-based systems to content creation, a popular but crowded space. Its value depends on the quality of its output compared to established alternatives.","signalBadge":"cooling","spanPresence":["monthly"],"stars":19289},{"repoName":"decolua/9router","repoUrl":"https://github.com/decolua/9router","summary":"A tool to route API calls for AI coding assistants to free or cheaper model providers. This is a cost-arbitrage utility, reflecting user sensitivity to API pricing but not contributing new capabilities to the agent ecosystem itself.","signalBadge":"cooling","spanPresence":["monthly"],"stars":13694},{"repoName":"NVlabs/LongLive","repoUrl":"https://github.com/NVlabs/LongLive","summary":"An infrastructure project from NVIDIA Labs for long video generation. Coming from a major research lab, it's worth monitoring, but as an infrastructure piece, its immediate utility for general developers may be limited.","signalBadge":"new","spanPresence":["daily"],"stars":1695},{"repoName":"can1357/oh-my-pi","repoUrl":"https://github.com/can1357/oh-my-pi","summary":"A command-line AI coding agent with features like LSP integration and sub-agent support. It represents a more developer-centric, terminal-first approach to building agents, appealing to users who prefer CLI workflows.","signalBadge":"new","spanPresence":["weekly"],"stars":6620},{"repoName":"yt-dlp/yt-dlp","repoUrl":"https://github.com/yt-dlp/yt-dlp","summary":"A well-known and long-maintained command-line video downloader. Its appearance on the trending list is likely due to external events or mentions rather than any fundamental innovation within the project itself. This is background noise.","signalBadge":"new","spanPresence":["daily"],"stars":164723},{"repoName":"ruvnet/ruflo","repoUrl":"https://github.com/ruvnet/ruflo","summary":"An agent orchestration platform, similar in goal to multica. The presence of multiple orchestration tools indicates that managing and coordinating agents is becoming a significant problem as developers move from experiments to production systems.","signalBadge":"cooling","spanPresence":["monthly"],"stars":54321},{"repoName":"addyosmani/agent-skills","repoUrl":"https://github.com/addyosmani/agent-skills","summary":"A collection of engineering-focused skills for coding agents from a well-known developer. Like other skill libraries, it contributes to the ecosystem, but its value is in the curated content rather than a novel technical approach.","signalBadge":"cooling","spanPresence":["monthly"],"stars":45058},{"repoName":"mattpocock/sandcastle","repoUrl":"https://github.com/mattpocock/sandcastle","summary":"A TypeScript library for orchestrating sandboxed coding agents. It focuses on safety and isolation, a critical concern for autonomous agents that execute code. This addresses a practical security need in the growing agent ecosystem.","signalBadge":"cooling","spanPresence":["monthly"],"stars":4809}],"insight":"This category is dominated by ecosystem-building rather than new model creation. The focus is on tooling to make agents useful: knowledge graphs for code understanding (`Understand-Anything`, `codegraph`), official skill/plugin directories (`claude-plugins-official`), and standardized skill formats (`dotnet/skills`)."},{"category":"Uncategorized","summary":"A diverse group showing niche AI applications and developer tooling. `CloakHQ/CloakBrowser` tackles the persistent bot detection problem, while `humanlayer/12-factor-agents` attempts to establish best practices for a maturing field. The presence of older, well-known repos like `odoo` and `the-book-of-secret-knowledge` points to recycled interest rather than new trends.","repos":[{"repoName":"tinyhumansai/openhuman","repoUrl":"https://github.com/tinyhumansai/openhuman","summary":"Presents itself as a 'Personal AI super intelligence' focused on privacy. The claims are broad and need verification. This type of project often attracts initial interest based on its ambitious premise rather than demonstrated capability.","signalBadge":"new","spanPresence":["weekly"],"stars":26072},{"repoName":"anthropics/financial-services","repoUrl":"https://github.com/anthropics/financial-services","summary":"An empty repository from Anthropic. Its trending status is likely due to speculation or a mistake. It holds no functional value at present but indicates interest in Anthropic's moves in the finance vertical.","signalBadge":"cooling","spanPresence":["monthly"],"stars":26917},{"repoName":"rohitg00/ai-engineering-from-scratch","repoUrl":"https://github.com/rohitg00/ai-engineering-from-scratch","summary":"An educational repository for learning AI engineering concepts. Its popularity reflects a strong demand for foundational knowledge as more developers enter the AI space. It's a learning resource, not a production tool.","signalBadge":"rising","spanPresence":["daily","weekly"],"stars":12941},{"repoName":"CloakHQ/CloakBrowser","repoUrl":"https://github.com/CloakHQ/CloakBrowser","summary":"A stealth-focused Chromium browser designed to defeat bot detection systems. It operates at the source code level to modify fingerprints. This is a specialized tool in the continuous arms race between automation and detection.","signalBadge":"repeated","spanPresence":["monthly","weekly"],"stars":19248},{"repoName":"Fincept-Corporation/FinceptTerminal","repoUrl":"https://github.com/Fincept-Corporation/FinceptTerminal","summary":"A financial analysis application. Its presence, along with other finance-related repos, suggests that finance is a key area where developers are applying modern data analysis and AI techniques.","signalBadge":"new","spanPresence":["daily"],"stars":22920},{"repoName":"humanlayer/12-factor-agents","repoUrl":"https://github.com/humanlayer/12-factor-agents","summary":"An attempt to define a set of principles for building production-ready LLM applications, analogous to the classic '12-Factor App'. This signals that the field is maturing and looking for established engineering best practices.","signalBadge":"new","spanPresence":["weekly"],"stars":21838},{"repoName":"presenton/presenton","repoUrl":"https://github.com/presenton/presenton","summary":"An open-source AI presentation generator. This is an application of generative AI to a common business task, competing in a space with established commercial players. Its value lies in its open-source nature.","signalBadge":"new","spanPresence":["daily"],"stars":6103},{"repoName":"soxoj/maigret","repoUrl":"https://github.com/soxoj/maigret","summary":"An OSINT tool that collects information on individuals by searching usernames across thousands of websites. This is a long-standing tool in the cybersecurity and privacy community, not a new development.","signalBadge":"cooling","spanPresence":["monthly"],"stars":30004},{"repoName":"datawhalechina/easy-vibe","repoUrl":"https://github.com/datawhalechina/easy-vibe","summary":"A coding course for beginners. As an educational resource, its trend is likely driven by a new cohort of students or a promotional event in its target community, rather than a technical innovation.","signalBadge":"new","spanPresence":["weekly"],"stars":14153},{"repoName":"TauricResearch/TradingAgents","repoUrl":"https://github.com/TauricResearch/TradingAgents","summary":"A framework for building multi-agent systems for financial trading. This combines two major trends: agentic AI and algorithmic trading. It represents a specialized, high-stakes application of agent technology.","signalBadge":"cooling","spanPresence":["monthly"],"stars":78779},{"repoName":"trimstray/the-book-of-secret-knowledge","repoUrl":"https://github.com/trimstray/the-book-of-secret-knowledge","summary":"A very large, long-standing curated list of tools, cheatsheets, and hacks for developers and administrators. Its periodic trending is a sign of evergreen content discovery, not a new development.","signalBadge":"new","spanPresence":["daily"],"stars":223563},{"repoName":"odoo/odoo","repoUrl":"https://github.com/odoo/odoo","summary":"A popular open-source suite of business management apps (ERP, CRM). Its appearance on GitHub trending is unusual for a mature project and likely tied to a major new release or conference.","signalBadge":"new","spanPresence":["daily"],"stars":51323},{"repoName":"janestreet/magic-trace","repoUrl":"https://github.com/janestreet/magic-trace","summary":"A high-resolution tracing tool from Jane Street for analyzing process behavior. This is a sophisticated, low-level performance analysis tool, appealing to developers working on high-performance systems. Its relevance is to systems engineering, not the mainstream AI trend.","signalBadge":"new","spanPresence":["daily"],"stars":5671},{"repoName":"Z4nzu/hackingtool","repoUrl":"https://github.com/Z4nzu/hackingtool","summary":"An all-in-one collection of hacking tools. These types of repositories, which bundle existing tools, are common but often of mixed quality. They cater to beginners in cybersecurity but rarely offer novel capabilities.","signalBadge":"cooling","spanPresence":["monthly"],"stars":76258}],"insight":"A diverse group showing niche AI applications and developer tooling. `CloakHQ/CloakBrowser` tackles the persistent bot detection problem, while `humanlayer/12-factor-agents` attempts to establish best practices for a maturing field. The presence of older, well-known repos like `odoo` and `the-book-of-secret-knowledge` points to recycled interest rather than new trends."},{"category":"Prompt & Skill Libraries","summary":"This category highlights the community's effort to standardize agent capabilities. Rather than just lists of prompts, projects like `mattpocock/skills` and `obra/superpowers` provide structured frameworks, treating 'skills' as first-class citizens in agent development.","repos":[{"repoName":"mattpocock/skills","repoUrl":"https://github.com/mattpocock/skills","summary":"A collection of practical skills for agents, curated by a prominent developer. Its popularity highlights the demand for high-quality, trusted prompt engineering, and reinforces the 'skill' as the key unit of agent enhancement.","signalBadge":"cooling","spanPresence":["monthly"],"stars":101883},{"repoName":"obra/superpowers","repoUrl":"https://github.com/obra/superpowers","summary":"This project proposes a framework and methodology for developing with 'agentic skills'. It attempts to formalize the process of building agent capabilities, moving beyond ad-hoc prompt collections to a more systematic software development lifecycle.","signalBadge":"new","spanPresence":["weekly"],"stars":203596},{"repoName":"K-Dense-AI/scientific-agent-skills","repoUrl":"https://github.com/K-Dense-AI/scientific-agent-skills","summary":"A set of agent skills specifically for scientific and financial tasks. This follows the pattern of creating domain-specific skill libraries, suggesting the agent ecosystem is fragmenting into specialized verticals.","signalBadge":"new","spanPresence":["weekly"],"stars":25281}],"insight":"This category highlights the community's effort to standardize agent capabilities. Rather than just lists of prompts, projects like `mattpocock/skills` and `obra/superpowers` provide structured frameworks, treating 'skills' as first-class citizens in agent development."},{"category":"On-device & Multimodal AI","summary":"This small set highlights the push for local AI execution. `supertone-inc/supertonic` provides on-device TTS via ONNX, a tangible example of moving complex models to the edge. This contrasts with wrappers like `free-claude-code`, which simply provide alternative access to cloud models.","repos":[{"repoName":"supertone-inc/supertonic","repoUrl":"https://github.com/supertone-inc/supertonic","summary":"An on-device, multilingual text-to-speech engine using the ONNX runtime. This is a practical implementation of running sophisticated AI models locally, offering speed and privacy benefits over cloud-based APIs. It represents a significant trend in edge AI.","signalBadge":"new","spanPresence":["weekly"],"stars":9657},{"repoName":"Alishahryar1/free-claude-code","repoUrl":"https://github.com/Alishahryar1/free-claude-code","summary":"A wrapper that provides free access to the claude-code model through various interfaces like a CLI and VSCode extension. This is a utility for circumventing API costs, not a foundational technology.","signalBadge":"cooling","spanPresence":["monthly"],"stars":28346},{"repoName":"bytedance/UI-TARS-desktop","repoUrl":"https://github.com/bytedance/UI-TARS-desktop","summary":"An open-source stack for multimodal AI agents from ByteDance. As a contribution from a major tech company, it provides an integrated infrastructure for building agents that can understand and interact with user interfaces.","signalBadge":"cooling","spanPresence":["monthly"],"stars":35029}],"insight":"This small set highlights the push for local AI execution. `supertone-inc/supertonic` provides on-device TTS via ONNX, a tangible example of moving complex models to the edge. This contrasts with wrappers like `free-claude-code`, which simply provide alternative access to cloud models."},{"category":"Memory, RAG & Context","summary":"The single entry, `refactoringhq/tolaria`, is a desktop application for managing local knowledge bases. Its presence suggests a demand for private, user-controlled knowledge management, running parallel to the developer-focused, programmatic memory solutions like `rohitg00/agentmemory` seen in other categories.","repos":[{"repoName":"refactoringhq/tolaria","repoUrl":"https://github.com/refactoringhq/tolaria","summary":"A desktop application for managing markdown-based knowledge bases. It caters to the need for local, private knowledge management, a user-centric parallel to the programmatic agent memory solutions seen elsewhere.","signalBadge":"cooling","spanPresence":["monthly"],"stars":11334}],"insight":"The single entry, `refactoringhq/tolaria`, is a desktop application for managing local knowledge bases. Its presence suggests a demand for private, user-controlled knowledge management, running parallel to the developer-focused, programmatic memory solutions like `rohitg00/agentmemory` seen in other categories."}],"meta":{"generatedAt":"2026-05-23T13:55:04Z","rulesVersion":"v1","degraded":false,"fallbackUsed":false,"repoCount":42,"signalCount":42},"vibeSummary":"The AI agent ecosystem is standardizing around \"skills\" as the portable unit of capability, moving from simple prompts to structured, shareable toolsets.","strategicInsights":["The term 'skill' has become the dominant abstraction for extending AI agents, adopted by Anthropic, Microsoft (.NET), and independent developers like mattpocock. This signals convergence on a standard for packaging agent capabilities.","Model providers are becoming platform builders. Anthropic's `claude-plugins-official` and Google's `chrome-devtools-mcp` are moves to create walled gardens or curated ecosystems, shifting value from open models to controlled platforms.","Knowledge graphs are emerging as the preferred method for providing deep context to code agents. The rise of `Lum1104/Understand-Anything` and `colbymchenry/codegraph` indicates a move beyond simple file-based context retrieval.","The trend list contains significant noise. Perennial utilities like `yt-dlp` and long-standing curated lists like `the-book-of-secret-knowledge` are trending again, indicating a lack of novel breakthroughs and recycling of established tools."],"trendSection":{"daily":{"rows":[{"repoName":"multica-ai/andrej-karpathy-skills","repoUrl":"https://github.com/multica-ai/andrej-karpathy-skills","yesterdayStars":null,"todayStars":148607,"delta":148607,"state":"first"},{"repoName":"multica-ai/multica","repoUrl":"https://github.com/multica-ai/multica","yesterdayStars":null,"todayStars":31673,"delta":31673,"state":"first"},{"repoName":"mukul975/Anthropic-Cybersecurity-Skills","repoUrl":"https://github.com/mukul975/Anthropic-Cybersecurity-Skills","yesterdayStars":null,"todayStars":6985,"delta":6985,"state":"first"},{"repoName":"presenton/presenton","repoUrl":"https://github.com/presenton/presenton","yesterdayStars":null,"todayStars":6103,"delta":6103,"state":"first"},{"repoName":"janestreet/magic-trace","repoUrl":"https://github.com/janestreet/magic-trace","yesterdayStars":null,"todayStars":5671,"delta":5671,"state":"first"},{"repoName":"colbymchenry/codegraph","repoUrl":"https://github.com/colbymchenry/codegraph","yesterdayStars":15839,"todayStars":18175,"delta":2336,"state":"strengthening"},{"repoName":"Lum1104/Understand-Anything","repoUrl":"https://github.com/Lum1104/Understand-Anything","yesterdayStars":17713,"todayStars":19983,"delta":2270,"state":"strengthening"},{"repoName":"anthropics/claude-plugins-official","repoUrl":"https://github.com/anthropics/claude-plugins-official","yesterdayStars":24046,"todayStars":25960,"delta":1914,"state":"strengthening"},{"repoName":"NVlabs/LongLive","repoUrl":"https://github.com/NVlabs/LongLive","yesterdayStars":null,"todayStars":1695,"delta":1695,"state":"first"},{"repoName":"rohitg00/ai-engineering-from-scratch","repoUrl":"https://github.com/rohitg00/ai-engineering-from-scratch","yesterdayStars":11398,"todayStars":12941,"delta":1543,"state":"strengthening"},{"repoName":"yt-dlp/yt-dlp","repoUrl":"https://github.com/yt-dlp/yt-dlp","yesterdayStars":164041,"todayStars":164723,"delta":682,"state":"stable"},{"repoName":"trimstray/the-book-of-secret-knowledge","repoUrl":"https://github.com/trimstray/the-book-of-secret-knowledge","yesterdayStars":222986,"todayStars":223563,"delta":577,"state":"stable"},{"repoName":"Fincept-Corporation/FinceptTerminal","repoUrl":"https://github.com/Fincept-Corporation/FinceptTerminal","yesterdayStars":22423,"todayStars":22920,"delta":497,"state":"continuous"},{"repoName":"ChromeDevTools/chrome-devtools-mcp","repoUrl":"https://github.com/ChromeDevTools/chrome-devtools-mcp","yesterdayStars":40813,"todayStars":41209,"delta":396,"state":"continuous"},{"repoName":"odoo/odoo","repoUrl":"https://github.com/odoo/odoo","yesterdayStars":50972,"todayStars":51323,"delta":351,"state":"continuous"},{"repoName":"dotnet/skills","repoUrl":"https://github.com/dotnet/skills","yesterdayStars":2425,"todayStars":2667,"delta":242,"state":"strengthening"}],"analysis":"New AI skill-compilation repositories are surging, led by the massive debut of `multica-ai/andrej-karpathy-skills` and related projects like `Anthropic-Cybersecurity-Skills`."},"weekly":{"rows":[{"repoName":"K-Dense-AI/scientific-agent-skills","repoUrl":"https://github.com/K-Dense-AI/scientific-agent-skills","yesterdayStars":null,"todayStars":25281,"delta":25281,"state":"first"},{"repoName":"Lum1104/Understand-Anything","repoUrl":"https://github.com/Lum1104/Understand-Anything","yesterdayStars":null,"todayStars":19983,"delta":19983,"state":"first"},{"repoName":"can1357/oh-my-pi","repoUrl":"https://github.com/can1357/oh-my-pi","yesterdayStars":null,"todayStars":6620,"delta":6620,"state":"first"},{"repoName":"colbymchenry/codegraph","repoUrl":"https://github.com/colbymchenry/codegraph","yesterdayStars":15839,"todayStars":18175,"delta":2336,"state":"strengthening"},{"repoName":"rohitg00/ai-engineering-from-scratch","repoUrl":"https://github.com/rohitg00/ai-engineering-from-scratch","yesterdayStars":11398,"todayStars":12942,"delta":1544,"state":"strengthening"},{"repoName":"obra/superpowers","repoUrl":"https://github.com/obra/superpowers","yesterdayStars":202552,"todayStars":203596,"delta":1044,"state":"continuous"},{"repoName":"ruvnet/RuView","repoUrl":"https://github.com/ruvnet/RuView","yesterdayStars":63632,"todayStars":64454,"delta":822,"state":"continuous"},{"repoName":"CloakHQ/CloakBrowser","repoUrl":"https://github.com/CloakHQ/CloakBrowser","yesterdayStars":18586,"todayStars":19248,"delta":662,"state":"strengthening"},{"repoName":"Imbad0202/academic-research-skills","repoUrl":"https://github.com/Imbad0202/academic-research-skills","yesterdayStars":18878,"todayStars":19458,"delta":580,"state":"strengthening"},{"repoName":"tinyhumansai/openhuman","repoUrl":"https://github.com/tinyhumansai/openhuman","yesterdayStars":25493,"todayStars":26072,"delta":579,"state":"continuous"},{"repoName":"rohitg00/agentmemory","repoUrl":"https://github.com/rohitg00/agentmemory","yesterdayStars":16252,"todayStars":16630,"delta":378,"state":"continuous"},{"repoName":"supertone-inc/supertonic","repoUrl":"https://github.com/supertone-inc/supertonic","yesterdayStars":9335,"todayStars":9657,"delta":322,"state":"strengthening"},{"repoName":"HKUDS/ViMax","repoUrl":"https://github.com/HKUDS/ViMax","yesterdayStars":6637,"todayStars":6844,"delta":207,"state":"strengthening"},{"repoName":"datawhalechina/easy-vibe","repoUrl":"https://github.com/datawhalechina/easy-vibe","yesterdayStars":13947,"todayStars":14153,"delta":206,"state":"continuous"},{"repoName":"humanlayer/12-factor-agents","repoUrl":"https://github.com/humanlayer/12-factor-agents","yesterdayStars":21696,"todayStars":21838,"delta":142,"state":"continuous"}],"analysis":"AI agent and skill-focused repositories show persistent weekly strength, with new entries `K-Dense-AI/scientific-agent-skills` and `Lum1104/Understand-Anything` establishing momentum."},"monthly":{"rows":[{"repoName":"ComposioHQ/awesome-codex-skills","repoUrl":"https://github.com/ComposioHQ/awesome-codex-skills","yesterdayStars":null,"todayStars":11165,"delta":11165,"state":"first"},{"repoName":"HKUDS/ViMax","repoUrl":"https://github.com/HKUDS/ViMax","yesterdayStars":null,"todayStars":6844,"delta":6844,"state":"first"},{"repoName":"mattpocock/sandcastle","repoUrl":"https://github.com/mattpocock/sandcastle","yesterdayStars":null,"todayStars":4809,"delta":4809,"state":"first"},{"repoName":"multica-ai/andrej-karpathy-skills","repoUrl":"https://github.com/multica-ai/andrej-karpathy-skills","yesterdayStars":145448,"todayStars":148606,"delta":3158,"state":"continuous"},{"repoName":"colbymchenry/codegraph","repoUrl":"https://github.com/colbymchenry/codegraph","yesterdayStars":15839,"todayStars":18175,"delta":2336,"state":"strengthening"},{"repoName":"mattpocock/skills","repoUrl":"https://github.com/mattpocock/skills","yesterdayStars":100507,"todayStars":101883,"delta":1376,"state":"continuous"},{"repoName":"CloakHQ/CloakBrowser","repoUrl":"https://github.com/CloakHQ/CloakBrowser","yesterdayStars":18586,"todayStars":19248,"delta":662,"state":"strengthening"},{"repoName":"Imbad0202/academic-research-skills","repoUrl":"https://github.com/Imbad0202/academic-research-skills","yesterdayStars":18878,"todayStars":19458,"delta":580,"state":"strengthening"},{"repoName":"Alishahryar1/free-claude-code","repoUrl":"https://github.com/Alishahryar1/free-claude-code","yesterdayStars":27824,"todayStars":28346,"delta":522,"state":"continuous"},{"repoName":"rohitg00/agentmemory","repoUrl":"https://github.com/rohitg00/agentmemory","yesterdayStars":16252,"todayStars":16630,"delta":378,"state":"continuous"},{"repoName":"TauricResearch/TradingAgents","repoUrl":"https://github.com/TauricResearch/TradingAgents","yesterdayStars":78499,"todayStars":78779,"delta":280,"state":"stable"},{"repoName":"decolua/9router","repoUrl":"https://github.com/decolua/9router","yesterdayStars":13429,"todayStars":13694,"delta":265,"state":"continuous"},{"repoName":"anthropics/financial-services","repoUrl":"https://github.com/anthropics/financial-services","yesterdayStars":26662,"todayStars":26917,"delta":255,"state":"continuous"},{"repoName":"addyosmani/agent-skills","repoUrl":"https://github.com/addyosmani/agent-skills","yesterdayStars":44815,"todayStars":45058,"delta":243,"state":"continuous"},{"repoName":"ruvnet/ruflo","repoUrl":"https://github.com/ruvnet/ruflo","yesterdayStars":54092,"todayStars":54321,"delta":229,"state":"stable"},{"repoName":"AIDC-AI/Pixelle-Video","repoUrl":"https://github.com/AIDC-AI/Pixelle-Video","yesterdayStars":19134,"todayStars":19289,"delta":155,"state":"continuous"},{"repoName":"Z4nzu/hackingtool","repoUrl":"https://github.com/Z4nzu/hackingtool","yesterdayStars":76112,"todayStars":76258,"delta":146,"state":"stable"},{"repoName":"refactoringhq/tolaria","repoUrl":"https://github.com/refactoringhq/tolaria","yesterdayStars":11230,"todayStars":11334,"delta":104,"state":"continuous"},{"repoName":"soxoj/maigret","repoUrl":"https://github.com/soxoj/maigret","yesterdayStars":29903,"todayStars":30004,"delta":101,"state":"stable"},{"repoName":"bytedance/UI-TARS-desktop","repoUrl":"https://github.com/bytedance/UI-TARS-desktop","yesterdayStars":34959,"todayStars":35029,"delta":70,"state":"stable"}],"analysis":"The AI \"skills\" compilation trend is entrenching itself, seen with new list `ComposioHQ/awesome-codex-skills`, while `colbymchenry/codegraph` shows sustained growth across all timeframes."}},"locale":"en"}