All AI tools

ClaudeClaw is a persistent agent orchestration plugin based on Claude Code, originating from the NanoClaw project. It provides a continuously running message loop that listens to channels such as Slack, WhatsApp, and Telegram, routes messages to Claude agents running in isolated sandboxes, and maintains ongoing conversations through structured memory management. Core features include multi-channel routing, thread management, context accumulation, Webhook triggers, per-group agent configuration, cost tracking, an extension system, and OS-level sandbox isolation based on Anthropic sandbox-runtime (Seatbelt on macOS, bubblewrap on Linux), with container runtimes also supported. The project runs as a Claude Code plugin, the current directory is the instance, state files are stored in the working directory, the codebase is small enough to fit into a Claude context window, and it emphasizes customization through code modifications rather than configuration files.

claudecodenavi-mcp

Search and share Claude Code snippets, prompts, Q&A solutions, error fixes and MCP server configurations from the ClaudeCodeNavi community.

ClaudeDown

ClaudeDown is a website that tracks complaints from Claude AI users in real time. It collects tweets mentioning Claude on X (formerly Twitter), calculates the proportion of complaint tweets, and compares it with the historical baseline for the same period, flagging anomalous spikes in complaints to help users determine "is Claude getting dumber right now." The website also provides a status judgment (such as "all normal"), a comparative heatmap view by time slot, samples of recent high-engagement tweets, and email alerts when there is an anomalous spike (officially said to send no spam, only spike alerts). The data is estimated based on sampled tweets and is not full data; spikes are detected by an algorithm and may include false positives.

claudeForSafari

Control Safari via a web extension: navigate, read pages, click elements, fill forms and manage tabs, without Playwright or WebDriver.

ClaudeMind

Experience Claude AI without limits. Use our desktop app for everyday AI assistance, or boost your coding productivity with our JetBrains plugin.

claudescope

Local-first CLI (`npx claudescope`) that indexes your local Claude Code session transcripts (`.claude/projects/*.jsonl`) into a searchable dashboard with full-text search across your coding-session history. Zero dependencies, zero network calls — fully private and offline. MIT licensed.

claudeusage

Measure whether a Claude subscription pays off from local Claude Code logs: surviving Claude-written code, rate-limit drivers and chat usage.

claudexor

Local-first control plane for Claude Code, Codex, Cursor, and OpenCode with quota-aware profiles, cross-model review, and best-of-N runs.

claudia

AI productivity

Task management for Claude agents: hierarchical tasks, dependencies, sprints, acceptance criteria and multi-agent coordination.

claudia

opcode (formerly known as claudia) is a desktop GUI application and toolkit for Claude Code, built on Tauri 2. It combines the Claude Code command-line tool with a visual interface, allowing developers to manage Claude Code projects and sessions, create custom AI agents, run background agents, track API usage and costs, manage MCP servers, and edit and preview CLAUDE.md files in a graphical interface. The official description states that this project is an independent developer project and has no affiliation, endorsement, or sponsorship relationship with Anthropic; Claude is a trademark of Anthropic, PBC.

claudinho

Live scores, fixtures, standings and read-only prediction-market signals for the 2026 World Cup.

claw-code

Rust reimplementation of Anthropic's Claude Code agent harness, now renamed **agent-code** (the claw-code crate on crates.io is a deprecated stub that only prints a rename notice). Maintained autonomously by agents as a showcase project; for production use the maintainers recommend LazyCodex or Gaja

Claw-Eval

Claw-Eval: A Transparent Benchmark for Real-World Agents

claw-tsaver

MCP proxy that replaces oversized tool results with a preview and an on-demand handle to save tokens.

clawaimail

Email infrastructure for AI agents: create inboxes on the fly, send and receive email, search messages and manage threads.

ClawBench

ClawBench is an open-source benchmark released by TIGER-AI-Lab for evaluating the ability of browser AI agents to complete everyday online tasks on real websites, such as booking travel, ordering food, applying for jobs, managing email, and more. V1 contains 152 everyday tasks spanning 143 online websites; V2 contains 129 tasks across 63 online websites; in total, 281 tasks spanning 163 online websites and 15 life categories. The benchmark uses a five-layer recording pipeline and an agentic evaluator to compare each run against a human reference trajectory, measuring end-to-end task success rate, and provides a live leaderboard showing scores by corpus, execution framework, and scoring standard. The project is built on Python 3.11+ and uv, uses Docker or Podman to provide isolated containers, can run on any Chrome, and has released Hugging Face datasets containing task definitions and complete execution trajectories.

ClawBench

Live-site benchmark for browser agents completing everyday online workflows.

clawbot

Clawbot is a decision layer directory for the agentic web, helping users match a task with the right agent, the tools it needs, and the access it should have before connecting any agent. The site catalogs 164 agents and 51 MCP servers, presenting them through task matching, traceable sources, permission descriptions, and maintenance date labels. Starting from a target outcome, users can obtain an inspectable agent stack combination covering areas such as coding, research and browsing, operations automation, and system connectivity. The directory does not use paid rankings, and official sources always remain the final authority.

Clawd Bot

AI productivity

Clawd Bot is an open-source personal AI assistant that runs on the user's own machine and can be controlled through chat apps such as WhatsApp, Telegram, Discord, Slack, Signal, or iMessage. It can automatically handle email, manage calendars, check in for flights, control smart homes, and more. Key features include persistent memory, browser control, system access, and extension through skills and plugins. By default, data stays local and is only sent to external services when the user explicitly requests it. It supports models such as Claude, GPT, Gemini, Llama, and Mistral, and can also run local models via Ollama or LM Studio. Installation requires only a single command, supports macOS, Windows, and Linux, and basic setup can be completed in 5 minutes.

ClawdBot AI

ClawdBot AI is an open-source, self-hosted personal AI assistant that runs on the user's local machine and supports Windows, macOS, and Linux. Unlike ordinary chatbots, it can actually execute tasks such as managing email, browsing the web, running scripts, and automating workflows in more than 50 apps including WhatsApp, Telegram, Discord, Slack, Signal, iMessage, and Microsoft Teams. It emphasizes privacy first, keeps data local, supports Claude, GPT, Gemini, or running local models through Ollama, and features persistent memory, browser automation, a skills marketplace, and Docker deployment, making it suitable for developers and advanced users.

Clawdbot中文版

Clawdbot Chinese Version

clawdcall-mcp

🎖️ 📇 ☁️ - Place consent-based outbound phone calls and retrieve transcripts, summaries and outcomes.

ClawFleet

ClawFleet is an open-source multi-agent deployment and management tool for running two types of AI agents, OpenClaw and Hermes, as Docker containers on a personal Mac or Linux machine, managed centrally through a browser dashboard. The official description states that deployment can be completed in about 10 minutes (the introduction also mentions 5 minutes), supports using a ChatGPT subscription, and requires no cloud fees. Each instance has an independent file system and network isolation, can connect to model providers such as OpenAI, Anthropic, Google, and DeepSeek with a single API key, and offers capabilities including a role system, skill management, Soul Archive soul archive cloning, clawfleet shell terminal access, and version locking.

clawguard-mcp

Security scanner for AI agents that detects prompt injections using regex patterns.

ClawHub镜像站

ClawHub Mirror Site

ClawManager

ClawManager is a Kubernetes-native AI agent instance management control plane, designed for platform teams that need to run AI agent instances for multiple users. It provides governed AI access, runtime orchestration, and reusable resources across multiple agent runtimes, supports managed runtimes such as OpenClaw, Hermes, OpenCode, and DeepSeek Harness, and offers two deployment modes: Lite and Pro. Users work through a browser-based desktop, while administrators can perform visibility and policy control without exposing Kubernetes details. The platform also includes capabilities such as AI Gateway model governance, Agent Control Plane runtime orchestration, team collaboration, resource management, a skills center, and a security protection platform.

clawpay-mcp

Non-custodial x402 payments for AI agents on Base: agents sign transactions from their own wallet with on-chain spend limits.

ClawSkills

ClawSkills — Discover OpenClaw Skills

clawtouch-mcp

Physical USB HID keyboard and mouse control via a Raspberry Pi Pico 2: move, click, drag, type, key combos and scroll, with a mock mode for testing.

Clayai

AI images

AI tool to transform photos into unique avatars with various artistic styles.

Cleafive

AI office

AI-powered tool to automate LinkedIn job applications and generate personalized resumes and cover letters.

Clean inbox for gmail

AI marketing

Gmail add-on using GPT filters to avoid spam and unwanted emails.

Clean Paste

Clean Paste is a free online text cleaning tool whose main purpose is to remove invisible characters, hidden metadata, and AI watermarks from text. Users can paste content and quickly clean it, with no registration required, and the official claim is that there are no usage limits. The tool offers a watermark removal mode that can delete AI watermarks and invisible characters while keeping the original content unchanged. It is suitable for scenarios such as students cleaning up AI-assisted drafts before submitting assignments, and content creators and bloggers maintaining text formatting. The official page states that more than 480,000 users have used it.

Clean Voice

AI audio

Clean Voice is an AI-powered audio and video noise reduction tool that removes background noise from audio and video, making the sound of podcasts, voiceovers, interviews, courses, and social videos clearer. Users simply drag and drop files, the AI processes them automatically, and they can download the clean files without needing to learn editing software. It supports MP3, M4A, WAV, and AAC audio formats and MP4, MOV, and WebM video formats. Registration grants 10 free credits, enough to process up to 10 minutes of audio or about 3 minutes of video. Audio consumes 1 credit per minute, and video consumes 3 credits per minute (minimum 1 credit). Credits are deducted only when the output is valid; failed tasks do not consume credits. Files are not uploaded until confirmation, results are kept only in the account activity history, and time-limited signed links are used to protect privacy.

cleaner-code