2026-05-29

Denoise

The AI agent ecosystem is consolidating around Anthropic's Claude Code, with a flood of plugins and skills defining the new developer platform.

Watch how developers are building a modular ecosystem around Anthropic's `claude-code` agent, using a new "skills" and "plugin" architecture to extend its capabilities.

2026-05-292026-05-29T16:02:16Zrules v1Healthyrepos 46signals 46

Top 3 changes

  • anthropics/claude-code shows a successful platform launch, pulling the entire agent ecosystem into its orbit.
  • twentyhq/twenty shows the "open-source, AI-native alternative" pattern targeting enterprise SaaS like Salesforce.
  • harry0703/MoneyPrinterTurbo shows continued high developer interest in fully automated, AI-driven content generation.

Strategic insights

#01The agent ecosystem is rapidly consolidating around `anthropics/claude-code`. The volume of new plugins (`cursor/plugins`, `EveryInc/compound-engineering-plugin`) and official directories (`anthropics/claude-plugins-official`) signals a significant platform shift.
#02"Skills" are emerging as a standardized, shareable primitive for augmenting agents. Repos like `taste-skill`, `stop-slop`, and `Anthropic-Cybersecurity-Skills` are not just prompts but structured capabilities.
#03Open-source, AI-native alternatives to established SaaS are gaining traction. `twentyhq/twenty` targets Salesforce, while `presenton/presenton` targets presentation software, both leveraging AI as a core differentiator.
#04A counter-movement against generic AI output is visible. The tandem rise of `taste-skill` and `hardikpandya/stop-slop` indicates a maturing demand for higher quality, less robotic AI-generated content.

Trend tracking

Today

Today's trend is driven by high-profile new entries, with `anthropics/claude-code` and `DataTalksClub/data-engineering-zoomcamp` leading a wave of projects making their first appearance.

3 Strengthening · 6 Continuous · 1 Stable · 7 First seen
Expand list (17)
ProjectYesterday ⭐Today ⭐ΔState
anthropics/claude-code128k🆕First seen
DataTalksClub/data-engineering-zoomcamp41k🆕First seen
Crosstalk-Solutions/project-nomad27k🆕First seen
run-llama/liteparse6.9k🆕First seen
harry0703/MoneyPrinterTurbo66k69k+3350Strengthening
Biohub/esm2.5k🆕First seen
microsoft/markitdown127k129k+1933Continuous
Leonxlnx/taste-skill26k28k+1848Strengthening
byoungd/English-level-up-tips48k50k+1347Continuous
affaan-m/ECC197k198k+1318Continuous
cursor/plugins1.2k🆕First seen
DigitalPlatDev/FreeDomain170k172k+1135Continuous
galilai-group/stable-worldmodel1.1k🆕First seen
codecrafters-io/build-your-own-x506k507k+776Stable
hardikpandya/stop-slop6.2k6.8k+585Strengthening
twentyhq/twenty48k48k+557Continuous
EveryInc/compound-engineering-plugin18k18k+339Continuous

This week

Projects like `affaan-m/ECC` and `harry0703/MoneyPrinterTurbo` show sustained momentum, solidifying their presence after recently appearing on the trending charts.

11 Strengthening · 7 Continuous · 1 First seen
Expand list (19)
ProjectYesterday ⭐Today ⭐ΔState
affaan-m/ECC198k🆕First seen
harry0703/MoneyPrinterTurbo66k69k+3352Strengthening
Leonxlnx/taste-skill26k28k+1848Strengthening
Lum1104/Understand-Anything42k44k+1786Strengthening
colbymchenry/codegraph31k33k+1563Strengthening
ruvnet/RuView67k68k+903Continuous
rohitg00/ai-engineering-from-scratch24k24k+885Strengthening
hardikpandya/stop-slop6.2k6.8k+585Strengthening
mukul975/Anthropic-Cybersecurity-Skills11k12k+468Strengthening
anthropics/knowledge-work-plugins18k18k+322Continuous
HKUDS/ViMax8.0k8.2k+234Continuous
can1357/oh-my-pi8.2k8.4k+232Continuous
BenedictKing/ccx2.3k2.5k+220Strengthening
anthropics/claude-plugins-official28k29k+195Continuous
microsoft/agent-governance-toolkit3.1k3.3k+185Strengthening
presenton/presenton7.3k7.4k+167Continuous
cursor/plugins1.1k1.2k+145Strengthening
dograh-hq/dograh3.5k3.7k+135Strengthening
p-e-w/heretic22k22k+128Continuous

This month

Educational and skill-building repositories like `Lum1104/Understand-Anything` and `mattpocock/skills` are entrenched, showing consistent, long-term accumulation of interest over the month.

3 Strengthening · 12 Continuous · 3 Stable
Expand list (18)
ProjectYesterday ⭐Today ⭐ΔState
Lum1104/Understand-Anything42k44k+1786Strengthening
colbymchenry/codegraph31k33k+1563Strengthening
mattpocock/skills110k111k+1355Continuous
multica-ai/andrej-karpathy-skills160k161k+1175Continuous
rohitg00/ai-engineering-from-scratch24k24k+885Strengthening
Imbad0202/academic-research-skills23k24k+503Continuous
rohitg00/agentmemory19k20k+348Continuous
CloakHQ/CloakBrowser22k22k+294Continuous
ruvnet/ruflo56k56k+292Continuous
TauricResearch/TradingAgents80k81k+240Stable
anthropics/financial-services28k29k+177Continuous
AIDC-AI/Pixelle-Video20k20k+162Continuous
decolua/9router15k15k+152Continuous
soxoj/maigret31k31k+149Stable
yikart/AiToEarn17k17k+92Continuous
bytedance/UI-TARS-desktop36k36k+72Stable
1jehuang/jcode6.7k6.7k+48Continuous
LearningCircuit/local-deep-research8.1k8.1k+46Continuous

Categories· 5

AI Coding Tools & Agents(22)

This category is overwhelmingly dominated by the launch of Anthropic's `claude-code` and its nascent ecosystem. Nearly every trending repository is a plugin, skill, harness, or proxy for this specific agent, showcasing a rapid platform consolidation rather than a diversity of tools.

  • An AI-powered tool for one-click short video generation. Its top ranking indicates massive and sustained interest in automated content creation tools, running parallel to the trend in agent-based coding assistants.

    rising⭐ 69k
  • This code visualizer turns codebases into interactive knowledge graphs. Its continued presence on the trend charts highlights the persistent need for tools that help developers comprehend complex systems, especially in an AI-assisted context.

    repeated⭐ 44k
  • A pre-indexed knowledge graph for various coding agents, including Claude Code. It aims to improve agent performance by reducing token usage and API calls, representing a common optimization pattern in the agent ecosystem.

    repeated⭐ 33k
  • An official plugin for Claude Code and other agents from Compound Engineering. Its appearance is a direct signal of the ecosystem forming around Anthropic's new agent, with third-party companies building integrations.

    new⭐ 18k
  • The official terminal-based coding agent from Anthropic. Its launch is the central event today, acting as a gravitational center for dozens of other trending plugin, skill, and tooling repositories.

    new⭐ 128k
  • A persistent memory solution for AI coding agents. Though cooling, its long-term trend indicates that providing agents with effective long-term memory remains a critical and unsolved problem in the field.

    cooling⭐ 20k
  • The plugin specification and official examples for the Cursor editor. This repo is gaining traction as developers look to extend agent-native IDEs, fitting into the broader theme of building modular agent capabilities.

    rising⭐ 1.2k
  • The official, curated directory of plugins for Claude Code from Anthropic. This is a clear platform move, creating a centralized, trusted marketplace to structure and encourage ecosystem development around their agent.

    new⭐ 29k
  • A set of prompts and workflows structured as "skills" for academic research using Claude Code. This repository exemplifies the trend of packaging domain-specific expertise into shareable modules for AI agents.

    cooling⭐ 24k
  • A collection of over 750 structured cybersecurity skills for AI agents, mapped to industry frameworks. It's another strong example of creating standardized, domain-specific capabilities for agents like Claude Code.

    new⭐ 12k
  • A proxy that routes requests to free tiers of various LLM providers for coding agents. It represents a user-side effort to abstract away API costs, though such tools can be fragile and depend on provider policies.

    cooling⭐ 15k
  • A single markdown file containing English learning advice. Its high ranking for a non-code repository suggests it is likely being amplified by social media or a specific community, rather than being a developer tool.

    new⭐ 50k
  • An agent orchestration platform specifically for Claude. It focuses on building complex, multi-agent workflows, indicating a move towards more sophisticated, production-level agent systems beyond single-agent setups.

    cooling⭐ 56k
  • A terminal-based AI coding agent. As another entry in a crowded field, it's worth noting for its focus on specific terminal-centric features like hash-anchored edits, competing for developer adoption.

    new⭐ 8.4k
  • An automated short video generation engine using AI. Similar to `MoneyPrinterTurbo`, its presence confirms a strong, ongoing developer interest in tools that automate the creation of social media content.

    cooling⭐ 20k
  • A performance optimization system or "harness" for coding agents like Claude Code. This is part of the wave of secondary tooling emerging to enhance and manage the core agent's performance and capabilities.

    rising⭐ 198k
  • A toolkit from Microsoft for managing AI agent security, policy, and reliability. Its release from a major player signals that as agent capabilities grow, enterprises are shifting focus to governance and safety frameworks.

    new⭐ 3.3k
  • A `CLAUDE.md` file designed to improve Claude Code's behavior, based on Andrej Karpathy's writing. It's a simple yet illustrative example of community efforts to codify expert knowledge for agent consumption.

    cooling⭐ 161k
  • A system that uses WiFi signals for spatial intelligence and presence detection without video. This is a novel application of existing technology, showing interest in privacy-preserving monitoring systems.

    new⭐ 68k
  • Another coding agent harness. Its continued presence, though cooling, indicates the ongoing exploration and competition in finding the best architecture to manage and extend AI coding agents.

    cooling⭐ 6.7k
  • A proxy for Claude, Codex, and Gemini APIs. Tools like this emerge to help developers manage or circumvent API limitations and costs, forming a layer of unofficial infrastructure around major AI platforms.

    new⭐ 2.5k
  • An agentic video generation framework that assigns roles like director and screenwriter to different AI components. This structured approach to creative generation is more sophisticated than one-click tools and points toward more controllable AI media.

    new⭐ 8.2k

Other(21)

This section is a mix of practical utilities, open-source SaaS alternatives, and educational content. Projects like `twentyhq/twenty` and `microsoft/markitdown` show a focus on building AI-native versions of established business and developer tools, while `build-your-own-x` reflects a persistent interest in foundational learning.

  • A Python tool from Microsoft for converting various document formats to Markdown. A practical, focused utility that addresses a common developer and content creator workflow need, showing continued investment in fundamental tools.

    new⭐ 129k
  • A repository from Anthropic, likely containing tools or data related to financial services applications for their models. Its presence, though undescribed, reinforces their push into enterprise verticals.

    cooling⭐ 29k
  • An educational repository that remains popular. Its persistence indicates a strong, unmet demand for fundamental, hands-on learning materials in AI engineering, beyond just using high-level APIs.

    repeated⭐ 24k
  • A stealth version of Chromium designed to bypass bot detection, with a Playwright-compatible API. This tool caters to the web scraping and automation communities that constantly contend with anti-bot measures.

    cooling⭐ 22k
  • An open-source CRM positioned as an AI-native Salesforce alternative. This exemplifies a key strategy: competing with incumbent SaaS by building from the ground up with a modern, AI-centric architecture.

    new⭐ 48k
  • An official Anthropic repository of plugins for knowledge workers. This, along with their code-focused plugins, shows a clear strategy to capture both technical and business user segments with their agent platform.

    new⭐ 18k
  • A "skill" file for AI agents designed to prevent them from generating generic, boring content. Its rise, along with `stop-slop`, signals a user base that is becoming more sophisticated and demanding higher quality output.

    rising⭐ 28k
  • A skill file intended to remove tell-tale AI phrasing from generated text. Its appearance alongside `taste-skill` highlights a growing user-driven movement to refine and humanize AI-generated content for better readability.

    rising⭐ 6.8k
  • A document parser from LlamaIndex. As RAG and agent systems rely heavily on quality data ingestion, high-performance parsing tools like this become critical, yet often overlooked, pieces of infrastructure.

    new⭐ 6.9k
  • A platform for world model research. This is a more academic and research-oriented project, indicating interest in building and evaluating foundational models that can simulate and understand environments.

    new⭐ 1.1k
  • An open-source AI presentation generator, positioned as an alternative to services like Gamma. This fits the pattern of building open, AI-powered versions of established productivity software.

    new⭐ 7.4k
  • This repository is undescribed but from Biohub, suggesting it relates to biological research, likely involving evolutionary scale modeling or protein language models. Its trending suggests activity in the specialized Bio-AI field.

    new⭐ 2.5k
  • A repository focused on using AI to earn money. These types of repositories often aggregate low-effort automation scripts and can be a source of noise, attracting attention with financial promises.

    cooling⭐ 17k
  • An offline, self-contained survival computer project. This is a niche but interesting project catering to the prepper and off-grid communities, combining knowledge archives with local AI capabilities.

    new⭐ 27k
  • A repository claiming to offer free domains. This is highly likely to be a low-quality or misleading project, as domain registration has hard costs. Its trending status is suspicious.

    new⭐ 172k
  • An OSINT tool for collecting information on a person by username across thousands of sites. This is a mature tool in the open-source intelligence space, and its trending suggests ongoing interest in digital investigation tools.

    cooling⭐ 31k
  • A framework for using multi-agent LLMs in financial trading. While the finance-AI intersection is a popular goal, the effectiveness of such systems is hard to verify, and they remain largely experimental.

    cooling⭐ 81k
  • A free course on data engineering. The high visibility of educational content like this, alongside `build-your-own-x`, confirms a strong demand for structured, practical learning paths in technical fields.

    new⭐ 41k
  • A tool for removing censorship from language models. This represents a faction of the developer community focused on uncensored AI, highlighting the ongoing technical and ideological tug-of-war over model alignment and safety.

    new⭐ 22k
  • A curated list of tutorials for recreating popular technologies from scratch. Its perennial popularity underscores a fundamental belief among developers that deep understanding comes from building things yourself.

    new⭐ 507k
  • A framework for performing deep research using local LLMs and various search engines. This caters to users who prioritize privacy and data control by running the entire research pipeline on their own hardware.

    cooling⭐ 8.1k

AI Infra & Protocols(1)

The single entry, `dograh-hq/dograh`, points to the growing need for self-hosted infrastructure for real-time, voice-based AI interaction. This represents a move to bring the operational control of complex AI systems like voice bots in-house.

  • An open-source, self-hosted voice AI platform alternative to commercial services. This addresses the enterprise need for control over conversational AI infrastructure, particularly for data privacy and custom integrations.

    new⭐ 3.7k

Prompt & Skill Libraries(1)

Though sparse with only one entry, `mattpocock/skills` reinforces the day's main theme. It shows the trend of formalizing agent instructions into reusable "skills," a pattern mirrored across numerous repos in the main AI agent category.

  • A collection of Claude skills from a prominent developer. This repo is significant not just for its content but for who it's from, showing how influential developers can shape best practices in the emerging agent-skill ecosystem.

    cooling⭐ 111k

On-device & Multimodal AI(1)

The lone repository, `bytedance/UI-TARS-desktop`, highlights ongoing work to standardize the stack for multimodal agents that operate on desktops. This is an important but not yet dominant area focused on connecting models to device-level infrastructure.

  • An open-source stack for multimodal AI agents on the desktop. Coming from ByteDance, this project is a serious attempt to define a standard architecture for agents that can interact with UIs and other local resources.

    cooling⭐ 36k

Recent reports

  • 2026-06-03

    generated 2026-06-03T17:05:52Z · rules v1 · repos 45 · signals 45

  • 2026-06-02

    generated 2026-06-02T16:49:13Z · rules v1 · repos 43 · signals 43

  • 2026-06-01

    generated 2026-06-01T17:57:29Z · rules v1 · repos 44 · signals 44

  • 2026-05-31

    generated 2026-05-31T14:03:33Z · rules v1 · repos 44 · signals 44

  • 2026-05-30

    generated 2026-05-30T13:57:40Z · rules v1 · repos 48 · signals 48

  • 2026-05-29 · current

    generated 2026-05-29T16:02:16Z · rules v1 · repos 46 · signals 46

  • 2026-05-28

    generated 2026-05-28T16:19:16Z · rules v1 · repos 48 · signals 48

  • 2026-05-27

    generated 2026-05-27T16:04:14Z · rules v1 · repos 45 · signals 45

  • 2026-05-26

    generated 2026-05-26T16:01:07Z · rules v1 · repos 45 · signals 45

  • 2026-05-25

    generated 2026-05-25T15:24:58Z · rules v1 · repos 45 · signals 45

  • 2026-05-24

    generated 2026-05-24T13:51:52Z · rules v1 · repos 43 · signals 43

  • 2026-05-23

    generated 2026-05-23T13:55:04Z · rules v1 · repos 42 · signals 42

  • 2026-05-22

    generated 2026-05-22T14:56:21Z · rules v1 · repos 40 · signals 40

  • 2026-05-21

    generated 2026-05-21T15:46:27Z · rules v1 · repos 41 · signals 41

  • 2026-05-20

    generated 2026-05-20T15:48:11Z · rules v1 · repos 36 · signals 36

  • 2026-05-19

    generated 2026-05-19T15:42:42Z · rules v1 · repos 37 · signals 37

  • 2026-05-18

    generated 2026-05-18T15:51:10Z · rules v1 · repos 39 · signals 39

  • 2026-05-17

    generated 2026-05-17T13:49:34Z · rules v1 · repos 45 · signals 45

  • 2026-05-16

    generated 2026-05-16T13:49:33Z · rules v1 · repos 34 · signals 34

  • 2026-05-15

    generated 2026-05-15T14:26:57Z · rules v1 · repos 38 · signals 38

  • 2026-05-14

    generated 2026-05-14T14:32:26Z · rules v1 · repos 42 · signals 42

  • 2026-05-13

    generated 2026-05-13T14:53:18Z · rules v1 · repos 44 · signals 44

  • 2026-05-12

    generated 2026-05-12T14:42:52Z · rules v1 · repos 36 · signals 36

  • 2026-05-11 · fallback

    generated 2026-05-11T15:30:34Z · rules v1 · repos 40 · signals 40

  • 2026-05-10

    generated 2026-05-10T13:46:39Z · rules v1 · repos 37 · signals 37

  • 2026-05-09

    generated 2026-05-09T13:43:42Z · rules v1 · repos 40 · signals 40

  • 2026-05-08

    generated 2026-05-08T14:08:16Z · rules v1 · repos 38 · signals 38

  • 2026-05-07

    generated 2026-05-07T14:38:09Z · rules v1 · repos 37 · signals 37

  • 2026-05-06

    generated 2026-05-06T14:34:27Z · rules v1 · repos 36 · signals 36

  • 2026-05-04

    generated 2026-05-04T14:22:31Z · rules v1 · repos 36 · signals 36

  • 2026-05-03

    generated 2026-05-03T13:40:38Z · rules v1 · repos 29 · signals 29

  • 2026-05-02 · fallback

    generated 2026-05-02T13:39:14Z · rules v1 · repos 30 · signals 30

  • 2026-05-01 · fallback

    generated 2026-05-01T13:46:05Z · rules v1 · repos 32 · signals 32

  • 2026-04-30

    generated 2026-04-30T14:19:05Z · rules v1 · repos 36 · signals 36

  • 2026-04-29

    generated 2026-04-29T14:23:30Z · rules v1 · repos 36 · signals 36

  • 2026-04-28

    generated 2026-04-28T14:34:52Z · rules v1 · repos 37 · signals 37

  • 2026-04-27

    generated 2026-04-27T14:20:15Z · rules v1 · repos 38 · signals 38

  • 2026-04-26

    generated 2026-04-26T13:24:10Z · rules v1 · repos 37 · signals 37

  • 2026-04-25

    generated 2026-04-25T13:22:57Z · rules v1 · repos 41 · signals 41

  • 2026-04-24

    generated 2026-04-24T13:58:04Z · rules v1 · repos 40 · signals 40

  • 2026-04-23

    generated 2026-04-23T14:04:35Z · rules v1 · repos 43 · signals 43

  • 2026-04-22

    generated 2026-04-22T14:02:49Z · rules v1 · repos 41 · signals 41

  • 2026-04-21

    generated 2026-04-22T07:58:11Z · rules v1 · repos 40 · signals 40

  • 2026-04-20

    generated 2026-04-21T09:23:28Z · rules v1 · repos 40 · signals 40

  • 2026-04-19

    generated 2026-04-19T08:51:11Z · rules v1 · repos 36 · signals 36

  • 2026-04-18

    generated 2026-04-18T08:45:02Z · rules v1 · repos 39 · signals 39

  • 2026-04-17

    generated 2026-04-17T09:14:47Z · rules v1 · repos 40 · signals 40

  • 2026-04-03

    generated 2026-05-13T03:24:00Z · rules v1 · repos 26 · signals 26

  • 2026-04-02 · degraded

    generated 2026-04-03T19:29:39Z · rules v1 · repos 26 · signals 26

  • 2026-04-01 · fallback

    generated 2026-04-03T19:29:39Z · rules v1 · repos 26 · signals 26