Search results for "open"

AstronClaw is a cloud based AI intelligent agent platform officially launched by iFlytek on March 12, 2026. It is built on the OpenClaw core architecture and focuses on security and usability. The product adopts a hybrid architecture of "cloud rapid deployment+local sandbox operation", supporting

2026-06-03

FlagEval: The internationally authoritative large model evaluation system and Libra open platform

159

FlagEval (Libra) is a large-scale model evaluation system and open platform initiated by Beijing Zhiyuan Artificial Intelligence Research Institute, aiming to establish scientific, fair, and open evaluation benchmarks and methods. The platform has innovatively constructed a three-dimensional

2026-05-31

AI Prompt Genius, ChatGPT prompt word management and dialogue export tool: Keep your AI

121

AI Prompt Genius is an open-source browser extension tool designed specifically for ChatGPT users. Its core functions include: automatically saving ChatGPT conversation history, importing/exporting prompt word templates, one click exporting conversations to PDF/image/Macrodown/JSON formats, local

2026-05-30

OpenCompass: An Open Source Large Model Comprehensive Evaluation System and Sinan Open Platform

118

OpenCompass is an open-source large model evaluation system launched by Shanghai Artificial Intelligence Laboratory, providing one-stop evaluation services for large language models, multimodal models, and scientific intelligence models. The platform supports one click distributed evaluation of

2026-05-31

OpenAI Operator， The world's first CUA intelligent agent, an AI assistant that simulates human

108

Operator is OpenAI's first AI agent product released on January 23, 2025. Unlike ChatGPT, which only outputs text, Operators can operate browsers autonomously like humans - they can view screenshots, move the mouse, click buttons, input text, and automatically complete complex tasks such as booking

2026-05-29

Tip Engineering Guide: A Systematic Learning Roadmap from Zero Foundation to AI Dialogue Master

The Tip Engineering Guide is the world's most popular open-source tip engineering learning project initiated by the renowned AI research institution DAIR.AI. It has accumulated over 30000 stars on GitHub and covers the entire knowledge system from basic principles to advanced technologies. The

2026-05-30

StableLM—an open-source AI model from the same family as Stable Diffusion, capable of running with only 3B parameters and commercially viable.

StableLM is an open-source large language model series launched by Stability AI. It is trained on The Pile extended dataset, which contains 1.5 trillion tokens. It offers multiple parameter versions, including 1.6B, 3B, 7B, and 12B, and supports text generation and code writing. It is licensed under the CC BY-SA 4.0 open-source license, allowing free commercial use. Stable LM 2 12B outperforms Llama 2 70B in some benchmark tests. It is suitable for developers, researchers, and small and medium-sized enterprises for private deployment.

2026-07-02

Codex: From code completion to cloud based intelligent agent command center

OpenAI Codex is an AI programming agent launched by OpenAI, with a cloud based software engineering agent as its core form, capable of independently completing the entire development process from requirement understanding to code delivery. After users describe the task objectives through natural

2026-06-03

Ginlix – an "AI construction team" tailored for Wall Street, enabling investment analysis to be continuously iterated like writing code.

Ginlix is an AI-powered company specializing in financial investment research. Its flagship product, LangAlpha, is an open-source investment research framework. Employing a Programmatic Tool Call (PTC) architecture, it allows AI agents to process financial data by writing and executing code, with a persistent workspace that enables research to accumulate like a codebase. It supports built-in models and can be deployed privately. It is suitable for individuals and institutions looking to leverage AI for deep, verifiable investment decisions.

LLaMA—Meta's open-source AI model revolution, with performance comparable to GPT-4 and completely free for commercial use.

LLaMA is an open-source family of large language models launched by Meta, evolving from LLaMA 1 in February 2023 to multimodal LLaMA 4. The 70B parameter version boasts performance close to GPT-4, while the 405B version rivals GPT-4o. It is completely open-source and commercially viable. Enterprises can download and deploy it on their own servers without data sharing, meeting compliance requirements in industries such as finance and healthcare. With over 1.2 billion downloads globally, it is suitable for developers and enterprises requiring private deployment and deep customization.

2026-07-02

Kortix – an AI operating system that puts your entire company into a single Git repository; open source, self-hosted, and entirely yours.

Kortix is an open-source AI command center that treats company operations as a Git repository. By deploying autonomous AI agents (Suna), it connects to 3000+ tools, executes multi-step tasks in an isolated sandbox, and generates actual outputs such as reports and code. Self-hosting is supported, giving you complete control over data and configuration. It's ideal for developers and teams looking to build autonomous AI workflows with full ownership.

Toby: A visual management tool that rescues you from tab chaos, helping your browser move past the mess of having "21 open tabs."

Toby is a visual tab management extension that transforms your new tab page into an intuitive Kanban-style workspace. It allows you to organize tabs into groups via drag-and-drop and supports one-click session saving, cross-device cloud syncing, and smart search. Say goodbye to the "save and forget" trap of traditional bookmarks; Toby is ideal for professionals and researchers who juggle multiple projects and frequently keep dozens of tabs open. The free version covers basic needs, while the Pro version unlocks team collaboration features.

2026-07-01

Public Prompts—a free and open-source repository of high-quality AI-generated prompts, a source of inspiration for Stable Diffusion gamers.

Public Prompts is a community-driven, free library of AI prompts, models, and embeddings designed for image generation tools like Stable Diffusion. The platform features carefully selected high-quality examples categorized by style, providing detailed parameter "recipes" to help users efficiently generate high-quality AI images. No registration is required; it's completely free.

Weige Cloud: The perfect hybrid of Excel and a database—say goodbye to project management chaos.

Weige Cloud is a next-generation data productivity platform that combines the ease of use of spreadsheets with the powerful capabilities of databases. It supports multiple view modes, cross-table linking, data synchronization, automation bots, and over 100 open APIs, covering 12 business scenarios such as project management and CRM. It is as ready-to-use as Excel yet as flexible and powerful as a database, enabling non-coders to build their own lightweight business systems. A free version is available, making it suitable for both team collaboration and personal data management.

2026-07-01

prompts.chat—a "free and open-source" AI-powered suggestion community—is reshaping sharing rules with its protocols and code.

prompts.chat is a free, open-source, and self-hosted AI-powered prompting word social platform. The community focuses on sharing and discovering high-quality prompts, covering content from various fields including code, image generation, and writing. The platform emphasizes data privacy and community-driven development, providing a decentralized communication space for AI creators and users.

H2O.ai – From a pioneer in open-source machine learning to a guardian of "sovereign AI," redefining enterprise-level intelligent agents with a converged architecture.

H2O.ai is a leading enterprise AI platform that integrates predictive and generative AI, focusing on AI deployments utilizing private, protected data. Its flagship products, h2oGPTe and H2O Super Agent, enable the creation of secure, autonomous agents in on-premises, VPC, and air-gapped environments. These agents consistently rank at the forefront of accuracy in authoritative benchmarks such as GAIA and FutureX. The company is trusted by more than half of the Fortune 500 and organizations within the world's most highly regulated industries.

2026-07-10

SuperCLUE—A benchmark for Chinese large models: from foundational capabilities to AI agents, a single test reveals who is "swimming naked."

SuperCLUE is a comprehensive evaluation benchmark for general-purpose Chinese large models, released by the CLUE team. It provides authoritative, multi-dimensional capability assessments and rankings for Chinese large models by regularly publishing monthly and semi-annual reports based on three key benchmarks—open-domain multi-turn dialogue, closed-domain objective questions, and anonymous head-to-head battles—as well as dimensions such as mathematical reasoning, code generation, and AI agents.

2026-07-10

Midjourney—the "automatic transmission" of an AI painting machine, a pinnacle of output quality praised by designers.

Midjourney is widely recognized as the AI painting tool with the highest output quality. It can generate artistic images using natural language simply by opening a webpage, without requiring local deployment.

2026-07-04

Cherry Studio – an all-in-one AI workstation, a desktop client that provides unified access to 300+ mainstream large-scale models.

Cherry Studio is a cross-platform AI desktop client that integrates over 300 mainstream models from OpenAI, Claude, Gemini, and other sources, as well as local Ollam models. It supports intelligent dialogue, autonomous agents, document processing, global search, and other functions, with local data storage for enhanced privacy and security. The community edition is completely free and open-source, supporting Windows, macOS, and Linux.

Stable Audio — An AI platform from Stability AI that uses open-source models to generate high-quality, commercially viable music locally.

Stable Audio is an AI music generation platform launched by Stability AI that supports the creation of up to six minutes of 44.1kHz stereo audio from text prompts. Its open-source models can be deployed locally, the training data is fully licensed, and the generated music is explicitly cleared for commercial use. It is suitable for music producers, content creators, and developers.

2026-07-11

Onlook—an open-source, visual React design editor that finally allows designers and developers to find common ground within the same codebase.

Onlook is an open-source visual design editor for React, positioned as "Cursor for designers." It enables users to edit production-grade React code directly via drag-and-drop, supporting AI-assisted design, real-time collaboration, version control, and one-click publishing. Designers can modify the UI without writing code, while developers benefit from clean, maintainable code output. It supports self-hosting and aims to bridge the gap between design and development.

2026-07-10

Noiz AI—More than just "voice cloning": recreating the "physicality" of the digital world through voice models.

Noiz AI is an AI technology company specializing in comprehensive audio generation, covering speech, sound effects, ambient sounds, and music. Its AudioX-Turbo model supports "Anything-to-Audio" capabilities, enabling the generation of 10 seconds of high-quality audio within 0.24 seconds from text, video, or image inputs; the model has been open-sourced and serves approximately 1.2 million users worldwide.

2026-07-11

AnythingLLM – Full-stack AI applications and private knowledge bases, enabling you to build your own ChatGPT with any model.

AnythingLLM is a full-stack AI application that supports any commercial or open-source LLM. It features built-in RAG, AI agents, and no-code agent builders. It can run locally or be remotely hosted, intelligently converse with documentation, and requires no cumbersome setup. Supporting the MCP protocol, it offers Desktop and Docker deployment options, making it suitable for individuals and businesses to build private, fully functional AI assistants.

iFlytek AI University – iFlytek's official AI learning and training platform, providing one-stop coverage from model fine-tuning to application development.

iFlytek AI University is an AI professional learning and training platform under iFlytek's open platform. Leveraging iFlytek's technological expertise in NLP, intelligent speech, and other fields, it offers a full-chain course from beginner to advanced model fine-tuning and agent development. The platform is deeply integrated with iFlytek's MaaS tools, supporting zero-code model customization and deployment. Upon completion, students receive official certification and it serves as a core hub for offline developer communities in multiple cities across China.

ModelScope – China's largest and most active open-source AI model platform, boasting a "model-as-a-service" ecosystem with over 30 million developers.

ModelScope is a leading open-source AI model platform in China, initiated by Alibaba DAMO Academy in conjunction with the CCF Open Source Development Committee. Adhering to the "Model as a Service" (MaaS) concept, the community has gathered over 200,000 open-source models, 30 million developers, and over 500 contributing organizations. It provides end-to-end services from model experience, download, fine-tuning, training to deployment, covering LLM, multimodal, speech, and AIGC fields. As a core infrastructure for AI developers in China, it is promoting the democratization of AI technology through "open source."

GPT-4o—OpenAI's all-around multimodal flagship model, featuring real-time voice and video interaction, and freely available to all users.

GPT-4o (“o” stands for Omni) is OpenAI's next-generation flagship multimodal large model, released in May 2024. It enables real-time inference across text, audio, images, and video, with an audio response time as fast as 232 milliseconds, approaching human conversational reaction speed. It possesses groundbreaking capabilities such as emotion perception, real-time translation, and image generation. Its API is twice as fast as GPT-4 Turbo, costs only half the price, and is available to all free ChatGPT users.

Replicate – a cloud platform that allows you to run open-source AI models with just one line of code; thousands of models are ready to use immediately.

Replicate is a cloud platform that allows developers to run, fine-tune, and deploy open-source AI models through a simple API. It offers thousands of community-contributed models covering areas such as image generation, large language models, and audio/video processing. No infrastructure management is required, and billing is based on actual computing power used. New users receive a free $25 credit.

Hugging Face – the "GitHub" of AI, the world's largest open-source model and dataset collaboration platform.

Hugging Face is a leading global AI open-source community and model hosting platform, widely hailed as the "GitHub of machine learning." It provides core services such as model libraries, datasets, and Spaces application hosting, aggregating over 2.7 million models, 950,000 datasets, and 1.2 million AI applications. Through open-source tool libraries like Transformers, the platform significantly lowers the barrier to AI development, becoming an indispensable infrastructure for modern AI developers.

Qdrant—a high-performance vector search engine written in Rust, designed for production-level AI retrieval.

Qdrant is an open-source vector similarity search engine designed for production-grade AI applications. It offers high-performance mixed dense and sparse vector retrieval, powerful metadata filtering, and real-time indexing capabilities. Its native Rust architecture ensures low latency and high throughput, making it widely used in scenarios such as RAGs, recommendation systems, and AI agents. It supports cloud, on-premises, and edge deployments.

There are 8 more tools not shown. Try more specific keywords.

AI News (10)

Meituan Open-Sources LongCat-2.0, a 1.6-Trillion-Parameter MoE Model; Full-Stack Execution on Domestic Computing Hardware Successfully Achieved

224

Meituan has officially open-sourced LongCat-2.0, a massive MoE model with 1.6 trillion parameters. This release achieves end-to-end training and inference deployment on a domestic computing cluster comprising 50,000 GPUs, thereby breaking reliance on overseas computing power. The announcement details LongCat-2.0's technical highlights, performance advantages, and industry value.

OpenAI's GPT-5.6 series preview remains in internal testing, with proprietary inference chips set for mass production by year-end.

154

OpenAI is officially advancing the limited beta testing of its GPT-5.6 model series and has announced a partnership with Broadcom to co-develop "Jalapeño," a dedicated inference ASIC. The project targets tape-out within nine months and large-scale deployment by the end of 2026, aiming to slash inference costs by 50% and effectively completing the company's vertically integrated strategy combining models and chips.

Anthropic's valuation has reached $965 billion, surpassing OpenAI for the first time.

145

The AI industry is undergoing a seismic shift as Anthropic’s post-investment valuation climbs to $965 billion, surpassing OpenAI for the first time. Its Claude Opus 4.8 model has reached the pinnacle of reasoning capabilities, while Claude Code captures over half the code-focused AI market with $6.3 billion in annual revenue; this analysis delves into the company's three core strengths: capital, technology, and commercialization.

Genesis World 1.0 is officially open source! Our self-developed simulation platform significantly shortens robot testing cycles.

131

Genesis AI, which gained fame for its robot frying tomatoes and eggs, has opened up its self-developed simulation platform, which greatly reduces the time required for robot evaluation and makes the simulation data closely match the real machine, thus helping to commercialize physical AI technology.

I don't understand programming, so I built a SaaS tool using OpenClaw and now I earn $200 a day

When you were still researching how to install "Lobster", someone had already used it to encapsulate AI capabilities into SaaS tools, achieving a stable daily income of $200 through subscription fees. This article fully disassembles the entrepreneurial model of "AI automation+SaaS subscription",

The wave of mandatory retirement is coming! Codex launches GPT-5.2/5.3-Code in June, developers

Sun Zhengyi was the richest man in Asia again, and fell again three days later: how to understand

To be honest, my first reaction when I saw this news was not "wow", but "is it again?" - because the last time he was so successful was in 2017. After that, everyone knows the story: WeWork went bankrupt, SoftBank Vision Fund suffered huge losses, his personal wealth once shrank to $21.1 billion,

Why does the DeepSeek model have a greater impact than the Qwen model when their performance is

I've been pondering this question for several days, really. Because my initial idea was very simple, wasn't it 'whoever has a high score is the best'? Later, I realized that I was too naive, a bit like when I thought 'the higher the pixel of the phone, the better the photo', and slapped my face.

OpenClaw Nanny Tutorial | Hand in Hand Teaching You How to Raise Lobsters on Xiaohongshu

While others are still watching to see what "Lobster" is, some people have already used it to run over 50000 views and 1000+comments in one night, all of which are "how to do it?" - This article will fully explain how to install and deploy OpenClaw (commonly known as "Lobster"), integrate it into

On May 28th, NVIDIA Polar announced a 594% surge in training performance for Codex

Career Skills (31)

Multi-agent task allocation and scheduling capabilities

Clawdtributor is a built-in multi-agent scheduling core component of OpenClaw. It automatically breaks down complex tasks and creates batches of sub-agents for parallel execution. Supporting various load-balancing strategies and consolidating the verification of all sub-task results, it significantly boosts processing efficiency in scenarios such as bulk research, code auditing, and distributed data collection.

39.9w 2026-07-12

ClawSweeper: Automated Warehouse Work Order Cleanup and Inspection Capability

ClawSweeper is an intelligent DevOps agent skill designed for OpenClaw to automate issue management in GitHub projects. It automatically scans repository issues and pull requests (PRs) to identify invalid items—such as those that are stale, unreproducible, or already resolved—and uses AI to generate standardized closing comments for batch archiving, thereby reducing manual maintenance effort. It features built-in safety safeguards to prevent the accidental closure of issues marked with protected labels, linked to active PRs, or created by administrators. Additionally, it supports scheduled polling, manual trigger commands, issue status queries, and the automatic submission of fix PRs.

39.0w 2026-07-12

Skills for comprehensive verification of release integrity

"Verify Release" is a read-only verification tool designed to confirm whether an OpenClaw release has been fully deployed across GitHub, npm, the plugin ecosystem, ClawHub, package smoke tests, and Live Gateway proxy calls. It does not perform any actual release operations (which are handled by `release-openclaw-maintainer`); instead, it simply answers questions such as "Has a specific version been fully released, deployed, and cleared for smoke and Live testing?" and provides a "yes" or "no" conclusion based on an evidence-driven checklist.

39.0w 2026-07-12

Parallels Discord Roundtrip Skill

Parallels Discord Roundtrip is a skill designed for the OpenClaw personal AI assistant, enabling seamless message round-tripping and task coordination between Discord and the Parallels desktop environment. This skill leverages Discord's real-time communication capabilities to interact with Parallels virtualization environments, supporting cross-platform command execution, file synchronization, and status monitoring. It is ideal for developers and operations personnel who need to manage multiple virtual machines and Discord collaboration scenarios simultaneously, with the AI agent automatically handling message routing and task scheduling to significantly boost productivity.

38.9w 2026-07-15

OpenClaw Testing Skill

The OpenClaw Testing Skill is an example skill within the OpenClaw personal AI assistant ecosystem, designed to demonstrate how to create, organize, and deploy agent skills. Located in the .agents/skills/openclaw-testing directory of the openclaw repository, it includes SKILL.md and other supporting files. This skill showcases the standard structure and best practices for skill development, making it ideal for developers to learn and reference, enabling them to quickly get started in creating their own AI Agent skills.

38.7w 2026-07-15

OpenClaw Secret Scanning Maintainer

OpenClaw Secret Scanning Maintainer is an AI assistant skill designed for the OpenClaw project, aimed at automatically detecting, scanning, and maintaining sensitive information (such as keys, tokens, passwords) in code. Based on scripts and configurations in the GitHub repository, it helps developers prevent sensitive data leaks and ensure code security. This skill is suitable for CI/CD environments, can be integrated into development workflows, and provides real-time scanning and alerting to enhance project security.

38.7w 2026-07-15

Control UI E2E

This is an Agent skill for end-to-end UI control, developed as part of the OpenClaw project. It enables AI assistants to directly manipulate graphical user interface elements via command line or scripts, enabling automated testing, interface operations, and workflow control. Core features include: simulating mouse clicks, keyboard input, window management, element locating, and state detection. It is suitable for cross-platform, cross-OS UI automation scenarios such as software testing, data entry, and repetitive interface task automation. The skill emphasizes safety and controllability, supports custom script extensions, and is ideal for developers and test engineers integrating into their workflows.

38.6w 2026-07-15

Heap Leaks Detection Skill

Heap Leaks Detection Skill is a professional tool provided by the OpenClaw platform, designed to automatically detect and diagnose heap memory leaks in applications. It analyzes memory allocation and deallocation patterns to identify unreleased memory blocks, helping developers quickly locate memory leak sources and optimize program performance. Suitable for C/C++, Rust and other languages requiring manual memory management, as well as large long-running server applications. Key features include: automatic heap memory operation scanning, leak report generation, custom detection rules, and CI/CD pipeline integration. Use cases include code review, performance tuning, and stability testing.

38.5w 2026-07-15

Discrawl — Discord Offline Archiving and Smart Search

Discrawl 是 OpenClaw 生态系统中的一个技能模块，用于将 Discord 服务器数据（频道、线程、消息、成员资料）离线同步到本地 SQLite 数据库，并提供全文搜索、成员目录、实时增量更新和 TUI 界面等功能。它优先使用本地归档数据回答 Discord 相关问题，仅在数据过时或范围不足时才回退调用 Discord API

Gitcrawl —— 本地GitHub归档搜索与PR状态同步技能

Gitcrawl is a tool designed for searching and interacting with GitHub issues and pull requests, prioritizing local archives. Its core philosophy is to utilize locally cached archive data before calling the live GitHub API, thereby improving search efficiency and reducing real-time dependency on the API. Built as a Go module, it can be installed using the command: `go install github.com/openclaw/gitcrawl/cmd/gitcrawl@latest`.

discord-clawd | OpenClaw Discord Interaction Gateway Skill

OpenClaw's official Discord bot interaction capabilities (natively integrated with Clawd) encapsulate the full Discord Bot API. This enables the OpenClaw AI agent to directly read, write, and manage Discord servers, channels, and direct messages, facilitating community automation, ChatOps, and intelligent message processing.

agent-transcript

Add a redacted agent transcript section to GitHub PR or issue bodies during OpenClaw agent-created PR/issue workflows.

38.1w 2026-07-12

Automated Code Review

"Autonomous Code Review" is a core AI code review agent capability built into OpenClaw, specifically designed to automate Git PR/MR code review workflows.

38.1w 2026-07-12

OpenClaw QA Testing Skill

The OpenClaw QA Testing Skill is a professional testing skill within the OpenClaw personal AI assistant ecosystem, designed for quality assurance and automated testing scenarios. Based on the OpenClaw platform, it supports running on any operating system and platform, helping developers efficiently execute test cases, verify software quality, and generate test reports. Key features include cross-platform compatibility, flexible test framework integration, and automated test process management. Suitable for regression testing, functional testing, integration testing, and other scenarios in the software development lifecycle, significantly improving testing efficiency and accuracy.

100 2026-07-14

HIPAA Compliance Skill

The HIPAA Compliance Skill is part of the ECC (Agent Harness Performance Optimization System), specifically designed to help AI agents and development tools meet the requirements of the Health Insurance Portability and Accountability Act (HIPAA). This skill provides guidelines, policies, and best practices for securely handling Protected Health Information (PHI), ensuring that AI applications developed in environments like Claude Code, Codex, Opencode, and Cursor comply with healthcare data privacy and security standards. Ideal for AI projects handling medical data, health tech applications, and healthcare IT systems.

0 2026-07-15

Skills in end-to-end release verification and CI monitoring

Release OpenClaw CI is a capability designed to execute, monitor, debug, and summarize the full release CI process for OpenClaw. Working in conjunction with `release-openclaw-maintainer` and `openclaw-testing`, it is utilized when release candidates require comprehensive validation, proof of installation/updates, real-time provider checks, or CI recovery. It handles the initiation, monitoring, troubleshooting, and evidence logging of full-matrix release validation but does not perform actual release operations—such as version bumps, tagging, `npm publish`, or GitHub releases—which require explicit operator approval.

39.9w 2026-07-12

End-to-end release process management skills

The Release OpenClaw Maintainer is a tool designed for the end-to-end management of OpenClaw stable and beta releases. It handles version number management, changelog generation, release note drafting, the execution of release commands, and artifact verification. Operating in coordination with release-openclaw-ci (for CI verification) and openclaw-changelog-update (for changelog generation), it serves as the core control layer for the OpenClaw release process.

39.0w 2026-07-12

GitHub Security Advisory Maintainer Skill

This skill is a component of the OpenClaw personal AI assistant ecosystem, specifically designed for maintaining GitHub Security Advisories (GHSA). It helps developers efficiently manage, create, and update security advisories, ensuring the security of open-source projects. By automating processes, it reduces manual errors and improves security response speed. Suitable for GitHub project maintainers who frequently handle security vulnerability reports, publish security patches, and coordinate security disclosures.

38.7w 2026-07-15

OpenClaw Test Performance Diagnostics

OpenClaw Test Performance is a specialized benchmarking, diagnostic, and optimization tool for OpenClaw test suites and plugin-suite runtimes. It helps developers quickly identify runtime hotspots, analyze CPU and RSS memory usage, detect heap growth trends, and uncover slow coverage paths. With one-click import into the Manus environment, developers can seamlessly integrate it into existing workflows for automated performance evaluation and tuning. This skill supports detailed metric collection, visual report generation, and intelligent optimization recommendations, making it ideal for continuous integration, performance regression testing, and code quality assurance scenarios.

38.6w 2026-07-14

Security Triage Skill

Security Triage is an Agent Skill from the OpenClaw project, designed to help AI assistants or users quickly perform initial classification and prioritization of security incidents, alerts, or potential threats. This skill uses a structured analysis process to identify the type of security issue (e.g., malware, network attack, data breach), assess its severity, and provide preliminary response recommendations. It is suitable for security operations personnel, incident response teams, and individuals or organizations looking to automate security classification workflows. Use cases include SOC (Security Operations Center) alert handling, penetration testing result classification, and preliminary vulnerability report analysis. This skill is based on an open-source project on GitHub and can be integrated into various AI platforms.

38.5w 2026-07-15

Techniques for batch-fixing high-certainty bugs within a limited scope

The "OpenClaw Small Bugfix Sweep" is a specialized workflow designed to batch-process issues and pull requests (PRs) in the OpenClaw repository by addressing minor, high-certainty bugs. Through in-depth code review, it targets only those bugs with clear root causes, unambiguous ownership, and minimal patch requirements. Upon fixing a bug, the system generates a "dirty diff" summary for manual review by Peter (the core maintainer); issues are submitted and closed only after his approval. Crucially, this process never involves pushing code, creating PRs, posting comments, closing issues, or applying tags during the review phase—all such actions are deferred until Peter grants explicit approval.

38.5w 2026-07-12

Alpha/Nightly Automated Release and Beta Triggering Capabilities

The OpenClaw Nightly release skill is an automated Alpha/Nightly release mechanism for OpenClaw/Tideclaw. It handles Alpha releases (triggered every 12 hours or manually), Beta release triggers, fixes on release branches, and forward-porting changes back to the `main` branch after a release. Working in tandem with the `release-private` skill, it utilizes the Tideclaw machine identity to execute releases on isolated branches, ensuring that a busy or broken state on the `main` branch does not impact the availability of Nightly builds.

38.5w 2026-07-12

Release a skill for automating changelog generation.

The OpenClaw Changelog Update is an automated utility designed to regenerate the OpenClaw release changelog from Git history. Prior to any beta or stable release (or re-release), it rewrites the relevant version section of `CHANGELOG.md` based on the complete history manifest, eliminating reliance on outdated draft notes. Used in conjunction with `release-openclaw-maintainer`, this utility manages changelog content, ordering, grouping, and attribution, serving as a mandatory step in the release process.

Maintainer Skills for Automated Review and Merging

OpenClaw PR Maintainer is a GitHub workflow automation tool designed for OpenClaw project maintainers to systematically review, triage, merge, and close issues and pull requests. It assists maintainers in efficiently managing external contributions while ensuring codebase quality and decision-making consistency through intelligent retrieval (prioritizing local archives), contributor identity analysis, deep code review (requiring an understanding of the full runtime context), and evidence-based merging criteria (mandating reproducible bug fixes).

Source-Audit-Driven Document Refactoring Skills

OpenClaw Refactor Docs is a skill designed for the source-audit-driven refactoring of existing OpenClaw documentation pages. Building upon the `openclaw-docs` skill—which handles style, page types, examples, and validation—it introduces a refactoring workflow that mandates the preservation and verification of all behavioral facts during rewriting, restructuring, splitting, or streamlining; this ensures that accurate descriptions of system behavior are not lost in the process. It requires source-based verification (against source code, tests, or schemas) for all behavior-sensitive information—such as configuration fields, commands, default values, and permission rules—rather than relying on inferences based on names or intent.

Skills for Mass-Producing Mergeable Bug-Fix PRs

OpenClaw Landable Bug Sweep is an automated, batch-oriented bug-fixing workflow designed for maintainers to generate high-quality, merge-ready (landable) bug-fix PRs from lists of issues or PRs. It employs strict candidate criteria—limiting scope to under 500 lines of code (LOC) and prohibiting new dependencies, configuration changes, or modifications to plugin SDK boundaries—alongside a systematic remediation loop and automated reviews ($autoreview). This process ensures that every generated PR is rebased onto the latest `main` branch, passes local tests and automated reviews, is successfully pushed, and clears GitHub CI checks. The workflow focuses exclusively on producing merge-ready PRs rather than generating analysis notes.

35.5w 2026-07-13

Telegram CrabBox E2E Proof Skill

The Telegram CrabBox E2E Proof Skill is a specialized skill within the OpenClaw personal AI assistant ecosystem, designed to automate end-to-end verification of CrabBox functionality through the Telegram messaging platform. Leveraging the agent capabilities of the OpenClaw framework, this skill automatically executes the complete verification flow from message reception, processing, to result feedback, ensuring the stability and correctness of CrabBox features in the Telegram environment. It is suitable for development testing, quality assurance, and automated operations, helping teams quickly identify and fix integration issues.

3.9w 2026-07-15

Skills in systematic debugging and problem localization

OpenClaw Debugging is a skill for systematically troubleshooting behavioral discrepancies in OpenClaw. When OpenClaw exhibits inconsistent performance across local testing, live models, different providers, code-mode, Tool Search, Crabbox, or CI environments, this skill enables you to pinpoint issues by selecting the appropriate logs, probing methods, and verification paths, rather than relying on blind guesswork.

3.8w 2026-07-12

Release OpenClaw Plugin Testing

This is a skill for publishing and testing OpenClaw plugins, designed to help developers quickly build, publish, and validate custom plugins within the OpenClaw ecosystem. With this skill, users can automate plugin packaging, version management, release workflows, and integration testing to ensure plugins run stably across multiple platforms. Core features include: one-click plugin source packaging, automatic release note generation, smoke and regression testing, and publishing to the OpenClaw plugin marketplace. Suitable for all OpenClaw plugin developers, especially teams that need frequent iteration and release of plugins.

100 2026-07-14

Channel Message Flows Skill

Channel Message Flows Skill is a core skill within the OpenClaw AI assistant ecosystem, designed to manage and process multi-channel message flows. This skill enables AI agents to seamlessly route and respond to messages across different channels (such as Slack, Discord, Telegram, etc.), supporting message filtering, priority sorting, auto-replies, and context retention. It is ideal for scenarios requiring unified message management, automated customer service, team collaboration, and intelligent notification distribution, significantly improving message processing efficiency and response speed.