Skip to content
AIMPLE
  • Platform capabilities
  • Workload placement
  • Deployment options
  • Implementation
Guides
  • Resources overview
  • Blog
  • News
  • AI Brief
  • Trending
Contact
  • English
  • 한국어
AIMPLE
Platform
  • Platform capabilities
  • Workload placement
Deployment
  • Deployment options
  • Implementation
Guides
Resources
  • Resources overview
  • Blog
  • News
  • AI Brief
  • Trending
Contact
Resources/Trending

Trending

Selected GitHub repositories, their recent momentum, practical uses, and adoption considerations.

Metrics observed on the edition date; they are not live GitHub counts.

  • Nov 16, 2026chromedevtools/chrome-devtools-mcp

    ChromeDevTools/chrome-devtools-mcp

    Key details An MCP server and CLI that connects agents to a running Chrome instance for control and inspection. Alongside ordinary page interactions, it handles DevTools performance traces, network requests, and console stacks with source maps applied. Use cases Record page performance traces from an MCP client and analyze network and console information. Instructions are also provided for navigating pages and capturing screenshots through the CLI. Costs and limitations The server and CLI code are licensed under Apache-2.0. Model API or subscription costs for the connected coding agent and execution equipment costs are separate. The supplied materials specify no mandatory paid plan for the tool itself. Pricing terms for external services need to be checked. Adoption considerations Node.js LTS, npm, and the current stable version of Chrome or later are required, and the range of officially supported browsers is defined. Browser data is exposed to the MCP client. Usage statistics are enabled by default, and performance tools may send URLs to CrUX, so check the relevant opt-out settings. Why it stands out It was observed at No. 5 on daily Trending, with an increase of 718. Version v1.13.0, listed on 2026-11-11, adds logpoints, page-scoped network mocking, and support for upstream mock network responses.

    Stars
    56,886
    Language
    TypeScript
    License
    Apache-2.0
    Daily
    rank 5 · +718 stars gained
  • Nov 16, 2026backnotprop/plannotator

    backnotprop/plannotator

    Key details A local browser tool for annotating agent-generated plans, documents, HTML, and code changes and sending feedback back to the agent. Inbox provides an asynchronous review workflow that collects questions and deliverables and forwards users' answers to the agent sessions that asked the questions. Use cases Annotate plans, specifications, and rendered HTML and send them to an agent, or review diffs for local changes and GitHub or GitLab PRs/MRs. In Inbox, review questions and files, then reply to the corresponding session. Costs and limitations The public local app is available under a choice of Apache-2.0 or MIT licenses. API or subscription costs for connected agents and Ask AI providers are separate, as are the operating costs of a self-hosted sharing service. Check the pricing terms for the separate hosted Workspaces product and external services. Adoption considerations Check agent-specific plugin, hook, and MCP settings and platform support. Storage is local by default, but release-check requests are made. URL reading, remote PR access, AI questions, and sharing each use external communications. Delivered answers cannot be recalled. Why it stands out It was observed at No. 4 on daily Trending with an increase of 860, and No. 4 on weekly Trending with an increase of 818. Version v0.28.65, listed on 2026-11-15, adds withdrawal of answers that have not yet been delivered and tags across connected devices, and restricts Tailscale access to the owner's account.

    Stars
    11,806
    Language
    TypeScript
    License
    Apache-2.0
    Daily
    rank 4 · +860 stars gained
    Weekly
    rank 4 · +818 stars gained
  • Nov 16, 2026nvidia/skillevaluator

    NVIDIA/SkillEvaluator

    Key details A CLI that evaluates agent skills in stages, covering static quality, instruction duplication, and their impact on actual task outcomes. It distinguishes comparisons before and after applying a skill from comparisons between versions, and records evaluation budgets, incomplete evidence, and failure causes in reports. Use cases First inspect the static quality of a skill directory, then optionally add duplication checks and evaluations using actual agents in a sandbox. GitHub and GitLab CI configurations are also provided for checking skills changed in PRs. Costs and limitations The basic static quality-check example is documented to run without an API key, GPU, or Docker. Model-based evaluations and managed sandboxes may incur separate charges, and self-managed execution resource costs should also be considered. NVIDIA Build's free prototyping is subject to eligibility, access conditions, and call limits. Adoption considerations Check Python 3.12–3.14 requirements and the dependencies for each stage. Full static checks require external scanners, while actual evaluations require provider authentication, a supported agent, and a sandbox. Support is experimental, and static scores alone do not establish security or real-world effectiveness. Why it stands out It was observed at No. 12 on daily Trending, with an increase of 205. Version 0.9.0, listed on 2026-11-13, expands reusable baseline runs, version comparisons, token, judging-call, and cost budgets, and reporting of evaluation evidence.

    Stars
    1,634
    Language
    Python
    License
    Apache-2.0
    Daily
    rank 12 · +205 stars gained
  • Nov 16, 2026dream-num/univer

    dream-num/univer

    Key details An Office SDK for embedding spreadsheet and document editing capabilities in products. The public core provides formula calculation, editing, rendering, and a Facade API, while reusing the same content model and command system for headless processing in Node.js. Use cases Embed an editor in a browser application using the Sheets Core preset and connect cell data through the Facade API. It also describes a path for content editing, snapshots, and automation in Node.js without an editing UI. Costs and limitations The public Sheets editor example does not require a commercial Univer license or the Server SDK. Commercial Web plugins, the Server SDK, and commercial AI extensions require separate licenses. Self-hosted infrastructure and connected model costs are also separate. Free allowances and watermark conditions for native output must not be generalized to the entire public core. Adoption considerations A browser bundler and development integration are required. Related packages must use compatible versions. When adopting collaboration, Office import/export, or new chart features, check the commercial scope and compatibility of native components and readers for older data. Why it stands out It was observed at No. 1 on daily Trending, with an increase of 1,041. Version v1.5.0, listed on 2026-11-14, includes improvements to formula calculation memory usage and interaction settings. Extensions such as charts and Office conversion should be assessed with a clear distinction between the public core and commercial offerings.

    Stars
    25,576
    Language
    TypeScript
    License
    Apache-2.0
    Daily
    rank 1 · +1,041 stars gained
  • Nov 16, 2026vincentwei1021/video-shotcraft

    Vincentwei1021/video-shotcraft

    Key details A Remotion-based tool for creating editable promotional videos from product screenshots and copy. It provides 124 recipe cards, implementations of 150 shots, and runnable templates. Shots, captions, and audio tracks can be edited afterward in Motion Workbench. Use cases Insert product screenshots, logos, and copy into the Ink Press template to create promotional videos, or select shots from the gallery to assemble feature demonstrations. Outputs include MP4 and Remotion source, with optional JianYing editing project output. Costs and limitations The repository's code and documentation are licensed under Apache-2.0. Agent model fees, equipment and execution costs for self-managed rendering, and Remotion's own licensing terms must be checked separately. The Freesound tool is described as usable without an API key, but individual audio licenses and attribution requirements apply. Pricing terms for the optional Upload-Post service also need to be checked. Adoption considerations Node.js, npm, and ffmpeg/ffprobe are required. Beat analysis uses uv, and page capture uses puppeteer. A browser is downloaded during the first render. Check the Linux execution configuration, JianYing support across platforms, screen data, and audio rights before publishing. Why it stands out It was observed at No. 13 on monthly Trending, with an increase of 7,617. Its workflow spans actual page capture, video creation, and subsequent editing. The release listed on 2026-11-12 distributes user showcase media rather than introducing features.

    Stars
    20,043
    Language
    TypeScript
    License
    Apache-2.0
    Monthly
    rank 13 · +7,617 stars gained
  • Nov 13, 2026addyosmani/agent-skills

    addyosmani/agent-skills

    Key Features An agent workflow pack organized by development stage. Its executable features include a hook that restores protected blocks during code simplification and a CI blocking gate for security reports. Beyond a collection of instructions, the release specifically describes protected code restoration and failure handling based on high and critical findings. Use Cases It provides a workflow in which a hook restores blocks marked with simplify-ignore during code simplification. In the constraints workflow, quality criteria written based on Semgrep and axe results are configured to trigger CI failures. Costs and Limitations The pack is licensed under MIT. Subscription or API costs for the coding agent and model serving as the execution host, as well as CI infrastructure costs, are separate. Cost conditions for the checking tools used need to be confirmed. Adoption Considerations Command exposure and integration methods differ by host. Installing only individual skills may omit the repository's shared references directory. The guidance recommends checking that gates actually fail on deliberately introduced violations, and there is no evidence that they behave identically across all hosts. Why It Stands Out It was observed at No. 9 on daily Trending, with a star increase of 812. Version 0.6.15, listed on 2026-10-31, fixed a bug that corrupted comments during protected code restoration and an issue that allowed security and accessibility check examples to pass CI, providing a basis for reviewing how the gates actually operate.

    Stars
    116,639
    Language
    JavaScript
    License
    MIT
    Daily
    rank 9 · +812 stars gained
  • Nov 13, 2026qwenlm/qwen-code

    QwenLM/qwen-code

    Key Features A coding agent for terminals, editors, desktops, and the web, supporting APIs from multiple providers and local models through Ollama and vLLM. A daemon manages multiple workspaces and active sessions, allowing browser, editor, and SDK clients to share and reconnect to the same agent session. Use Cases An example shows opening a session in a project and asking it to explain the repository structure and starting points. Workflows are also provided for connecting headless mode to scripts, CI, and batch jobs, or receiving repository summaries through the SDK. Costs and Limitations The framework code is licensed under Apache-2.0. The Qwen account authentication route requires a Plus or Pro subscription, and external provider API charges are separate. Because the README also explicitly offers local model alternatives, the tool itself was not regarded as paid-only, but local model licenses and hardware costs must be checked separately. Adoption Considerations Installation through npm requires Node.js 22 or later. The web UI and daemon are experimental. By default, the daemon exposes a code execution API on loopback without bearer authentication, so token and authentication settings should be checked on shared hosts. Installation instructions are based on main, while the latest release is Preview. Why It Stands Out It was observed at No. 6 on daily Trending, with a star increase of 151. Version v1.0.0-preview.1, listed on 2026-11-12, fixed model usage errors after subscription login and model list synchronization. Its multiple interfaces and shared session setup are concrete, but the usage conditions for Preview and main need to be considered separately.

    Stars
    29,777
    Language
    TypeScript
    License
    Apache-2.0
    Daily
    rank 6 · +151 stars gained
  • Nov 13, 2026googlechrome/modern-web-guidance-src

    GoogleChrome/modern-web-guidance-src

    Key Features A tool that supplies coding agents with guidance on modern web APIs, accessibility, and browser compatibility. In addition to a collection of guidance files, it explicitly describes workflows for using the CLI to search and retrieve relevant guides and scan codebases for legacy patterns. Use Cases Guides can be searched by the feature to be implemented, such as dialog backdrop animation, or retrieved by ID. Examples also show how to scan a codebase for legacy patterns to identify candidates for migration to modern web features. Costs and Limitations The code is licensed under Apache-2.0, and the supplied information states no paid requirement for the CLI itself. Cost conditions need to be confirmed. API or subscription costs for connected coding agents and models must be checked separately. Adoption Considerations Check the environment for running the npx-based CLI and how it integrates with the agent in use. For the latest web features covered by the guidance, review target browser support and fallbacks. The supplied materials do not verify scan accuracy or the resulting improvements. Why It Stands Out It was observed at No. 1 on daily Trending, with a star increase of 799. Its ability to connect scans that identify patterns suitable for replacement with native web features to retrieval of the necessary guides is a point of interest. The supplied change description for v1.0.0, listed on 2026-11-10, is automatic updating of the README's evaluation and scope.

    Stars
    2,831
    Language
    TypeScript
    License
    Apache-2.0
    Daily
    rank 1 · +799 stars gained
  • Nov 13, 2026nvm-sh/nvm

    nvm-sh/nvm

    Key Features A version manager for installing and switching between multiple Node.js versions from the command line. It is installed per user and loaded per shell, and a recent release added version selection by categories such as alpha, LTS, and non-LTS. Use Cases The README provides examples of installing or switching between Node.js 24, 22, and 20. For non-interactive Docker and CI environments, it explains that normal shell profiles are not loaded automatically and describes a separate environment-loading configuration. Costs and Limitations The code is licensed under MIT, and there is no statement that basic local use requires a paid API or subscription. Cost conditions for separate tools need to be confirmed. Local storage and infrastructure costs for CI and container execution are separate. Adoption Considerations It is intended for POSIX-compatible shells; Windows users should check requirements such as WSL. It is loaded as a shell function rather than an executable, and Fish is not directly supported. A C++ compiler is required in environments without prebuilt Node binaries. Why It Stands Out It was observed at No. 3 on daily Trending, with a star increase of 107. Version v0.41.0, listed on 2026-11-05, includes version category selection, caching after checksum verification, and fixes to authentication header forwarding and path handling, making its practical changes to version management worth reviewing.

    Stars
    95,999
    Language
    Shell
    License
    MIT
    Daily
    rank 3 · +107 stars gained
  • Nov 13, 2026ashhart/tensorfold

    ashhart/TensorFold

    Key Features An inference engine whose Zig binary reads checkpoints, tokenizes requests, and serves language models through Metal and CUDA kernels. Core serving does not require Python or MLX installation, and it provides Responses and Anthropic Messages APIs, request queuing, and concurrency limits. Use Cases The documentation explains how to download a model, serve it through a local server, and send requests to the chat API, as well as how to connect existing local checkpoints or a Hugging Face cache. A separate local web app supports model selection, execution, and chat. Costs and Limitations The engine code is licensed under Apache-2.0, while model weights have separate licenses. Local serving should be distinguished from external paid APIs; the default examples use local models. Hardware, memory, storage, and electricity costs are separate, and model-specific cost conditions need to be confirmed. Adoption Considerations The Linux NVIDIA distribution requires glibc 2.28 or later and an R580 or later driver. Check each model's supported backends and memory requirements; the web app may require a separate installation. Living Weights is experimental, modifies checkpoint files, and has stated recall and speed limitations. Why It Stands Out It was observed at No. 7 on daily Trending, with a star increase of 94. Version 1.2.7, listed on 2026-11-12, describes improved state restoration for long conversations, WebSocket mode for the Responses API, and LightOnOCR-3 image chat on CUDA, providing reasons to examine its API integration and conversation resumption features.

    Stars
    1,923
    Language
    Zig
    License
    Apache-2.0
    Daily
    rank 7 · +94 stars gained
  • Nov 13, 2026ggml-org/llama.cpp

    ggml-org/llama.cpp

    Key Features Runs LLM and VLM inference in C/C++ and provides a CLI, an OpenAI-compatible API server, and a built-in web UI. Notable features include support for various quantization formats, mixed CPU/GPU inference, and multiple backends such as Metal, CUDA, HIP, and Vulkan. Use Cases The README presents workflows for downloading a GGUF model from Hugging Face and running it through the CLI, or launching an OpenAI-compatible server with the same model. The server also includes a built-in web UI for browser use. Costs and Limitations The code is licensed under MIT, and a local inference option is available. Each model's terms of use and cost conditions need to be confirmed. Self-hosting incurs hardware, storage, and electricity costs, while cloud execution incurs separate infrastructure costs. Adoption Considerations Check the binary or build configuration appropriate to the selected model format, size, and execution backend. The supplied information alone cannot establish whether a particular device has sufficient memory or what processing performance it will deliver. Why It Stands Out It was observed at No. 13 on daily Trending, with a star increase of 287. Build b12332, listed on 2026-11-12, connects operations previously limited to the scalar CPU path to SpacemiT RVV kernels, illustrating continued refinement of backend-specific implementations.

    Stars
    134,525
    Language
    C++
    License
    MIT
    Daily
    rank 13 · +287 stars gained
  • Nov 13, 2026openai/codex-security

    openai/codex-security

    Key Features A CLI and TypeScript SDK that investigate vulnerabilities across an entire repository, selected paths, or Git changes, and connect candidate validation, patch generation, and verification of existing fixes. They support deduplication of saved findings and SARIF, JSON, and CSV exports, allowing investigation results to feed into follow-up work. Use Cases The documentation describes a workflow for scanning a repository with a focus on authentication and authorization, reviewing source evidence and excluded scope in saved reports, and requesting patches or verification of existing fixes. It also provides an example of scheduled scans through GitHub Actions. Costs and Limitations The CLI and SDK code is licensed under Apache-2.0, with model provider API charges billed separately. The Actions example uses an estimated limit of $5 per scan but explicitly states that in-flight requests can cause it to be exceeded. Pricing terms for the account login route need to be confirmed. Adoption Considerations Requires Node.js 22.x starting at 22.13.0, or 24.x or 26.x, and Python 3.10 or later; Python 3.10 also requires tomli. CI requires an API key, and some security requests and protected findings require Trusted Access for Cyber. Why It Stands Out It was observed at No. 2 on daily Trending, with a star increase of 663. Version 0.10.0, listed on 2026-11-12, added resumption of interrupted Standard scans and shared estimated budgets across multiple repositories and components, making the operational conditions for repeated investigations more concrete.

    Stars
    12,378
    Language
    TypeScript
    License
    Apache-2.0
    Daily
    rank 2 · +663 stars gained
PreviousPage 2 of 4Next
AIMPLE

Planning an AI rollout?

Tell us what you want to run and where it needs to run.

Discuss a deployment

Platform

  • Platform capabilities
  • Workload placement

Deployment

  • Deployment options
  • Implementation

Resources

  • Guides
  • Blog
  • News
  • AI Brief
  • Trending

Emotionwave

  • emotionwave.com

RIMA

  • enter.rima.ai
  • rima.ai
  • RIMA Star
  • RIMA Lodestar

NVEX

  • nvex.kr
  • mew31.com
  • MEW Music Place
  • MEWZ
  • Klavix
  • MEW Drum
  • MEW Piano
  • MEW Tutor
  • Artificial Academy
  • Vocco

Infidity

  • infidity.ai
  • tangle.infidity.ai

© 2026 Emotionwave Inc.

Back to top