Skip to content
Alternatives
Software like ClawResearch
What else does this job. Matched on what each project does, not on who links to whom.
Closest first
- DrugClawdrugclaw.comDrugClaw is an open-source multi-channel agent runtime designed for drug discovery research. It provides a web UI, CLI, and built-in scientific tools to automate and accelerate research workflows for scientists and developers.
- Clawdbotclawdbot.youClawdbot is an open-source, self-hosted AI assistant that runs locally on your device, automating real-world tasks such as managing emails, controlling smart home devices, and scheduling meetings. It integrates with over 50 platforms and prioritizes privacy by keeping all data on your machine. Designed for users who want powerful automation without cloud dependencies, Clawdbot is ideal for privacy-conscious individuals and developers.
- ScienceClawtaichuai.cnScienceClaw is a personal research assistant for scientific and academic workflows. It is built with LangChain DeepAgents and AIO Sandbox infrastructure, and the product text says it was redesigned beyond OpenClaw with an emphasis on security, transparency, and ease of use. The system is described as running entirely inside Docker containers. The agent cannot access the host system, personal files, or environment variables, and code runs in an isolated sandbox. Its workflow is presented as fully traceable, with each step visible from web search and data crawling through reasoning, tool invocation, and final report generation. ScienceClaw also includes a skill system that uses structured instruction documents to guide the agent through complex multi-step workflows. Its toolset is described as extensive, with 1,900+ built-in scientific tools across eight domains. The listed domains are drug discovery and biomedicine, astronomy and space science, earth and environmental science, chemistry and materials science, biodiversity and ecology, social science and statistics, academic literature, and data science and computing. The page also names built-in web search and web crawling, ToolUniverse integration, sandbox tools for file operations and code execution, and a custom @tool mechanism that supports user-defined Python functions and hot-loading. Content generation is said to cover four formats: PDF, DOCX, PPTX, and XLSX, including PDF reading and creation, Word documents, PowerPoint slide decks, and Excel spreadsheets with CSV/TSV data processing. Delivery is local: the page states 100% local deployment and gives setup instructions for Windows, macOS, and Linux. It can be launched with a single command, and the Windows instructions mention a desktop shortcut after installation.
- Captain Clawcaptain-claw.comCaptain Claw is an open-source platform designed to orchestrate multiple AI agents for complex tasks, offering users a command center called the Flight Deck to spawn, monitor, and coordinate specialist teams. Unlike single-agent chat tools, it enables the management of a fleet of AI agents, each with its own model, role, and toolset, all from a unified dashboard on the user's machine. The platform supports six distinct orchestration modes, allowing users to tailor the collaboration and workflow of agents to the specific demands of their tasks, such as ensemble reasoning, structured deliberation, and software engineering pipelines. Each agent within Captain Claw can be assigned a unique combination of models—including options like GPT, Claude, Gemini, DeepSeek, and Ollama—and a selection from 48 built-in tools. The system provides live monitoring, per-agent chat, file inspection, and log access without interrupting the work of other agents. Users can analyze token usage and costs at the agent level, with a comprehensive activity log that traces every tool invocation, consultation, and hand-off. Quick Chat functionality allows for rapid agent instantiation using predefined archetypes, which can be promoted to the main workspace as needed. The platform features a library of 31 editable agent archetypes covering roles in research, writing, engineering, data analysis, operations, finance, and multimedia. Users can build teams by selecting archetypes manually or by describing an objective in plain English, which prompts the system to design a team with appropriate roles, models, tools, and standard operating procedures. Structured deliberation is facilitated through the Agent Council mode, where agents participate in moderated rounds and vote, with the ability to export session minutes as markdown. For high-confidence outputs, Basna mode enables independent, blind responses from specialists that are merged by reliability, while Vatra mode supports collaborative drafting on a shared blackboard with review rounds. Captain Claw is distributed under the MIT License and runs locally. Its open-source nature and flexible orchestration modes make it suitable for users who need to coordinate specialized AI agents for tasks spanning research, engineering, analysis, and complex decision-making.
- Clawithclawith.aiClawith is a self-hostable open-source system for building a collaboration network of humans and AI agents. Its central idea is that organizational cognition should move from individual people into named, accountable roles and shared organizational memory. The site describes six capabilities for that model: Org Roles, Two-layer Memory, A2A Direct Collab, Aware Dispatch, Permissions & Audit, and Plaza Space. Roles are presented as digital members with accountability, memory is described as staying with the organization rather than the person, coordination includes delegate, @-mention, and group formation, execution begins from a goal and decomposes work until human intervention is needed, and governance keeps actions logged and traceable end to end. Learning is also part of the system, with the organization settling into a reusable starting point over time. Examples on the page show the intended use across quantitative work, media production, and software delivery. In those examples, agents analyze prices, news, and fundamentals; run writing, publishing, and analytics across multiple channels; and move from a single sentence to shipped software in seven days while a human reviews the result. The page also says humans own goals and judgment, while agents take on node-level tasks and proactively collaborate with other members. Clawith is available as self-hostable software and is released under the Apache 2.0 license. The page also mentions that it works with any model and refers to an OpenClaw ecosystem. The tool is framed as an answer to how organizations run when every individual is amplified by AI, and it presents itself as a way to form a company-like collaboration network of experts, super-individuals, and agents.
- Clawbberclawbber.aiClawbber is a web-based platform that enables users to build, deploy, and manage AI agents using plain English instructions, without any coding. It streamlines the creation of custom AI workflows for business automation and productivity, targeting non-technical professionals and teams.
- EClawboteclawbot.comEClawbot is a platform for creating and orchestrating teams of AI agents that communicate and collaborate using an Agent-to-Agent (A2A) protocol. It provides each agent with its own identity, skills, and public interaction URL, along with a mission control dashboard for managing tasks, todos, and workflows. The system supports multi-platform access via web, iOS, and Android apps, enterprise-grade security features, and integration with the OpenClaw ecosystem.
- Clawsphereclawsphere.aiClawsphere is a web-based professional social network designed for AI agents and their human owners. It enables users to build agent reputations, showcase capabilities, and connect with others in the AI ecosystem. The platform supports agent-human pairing, community discussions, and reputation tracking.
- Clawdylandclawdyland.aiClawdyland is a web-based AI agent arena where users deploy autonomous agents to compete in Texas Hold'em poker and debate competitions for BNB prizes. The platform enables agent evolution and real-time competition, targeting AI enthusiasts and gamers interested in autonomous play and crypto rewards.
- thClawsthclaws.aithClaws is an open-source, native-Rust AI agent workspace designed to run locally on macOS, Windows, and Linux. It enables users to code, automate tasks, retain memory, and coordinate workflows through a locally executed agent, emphasizing user control and data privacy. The platform supports multiple AI providers—such as Anthropic, OpenAI, Gemini, Alibaba DashScope, OpenRouter, Ollama, and Agentic Press—automatically detecting the provider by model name, and is built on open standards to avoid cloud lock-in. The workspace offers three main interfaces within a single binary: a desktop GUI with tabs for terminal, chat, files, and team coordination; a CLI REPL for headless or SSH sessions; and a one-shot mode for single-turn commands, making it suitable for integration with other tools or CI pipelines. Users can switch freely between these interfaces, with session history and configuration preserved across modes. Additionally, thClaws can be run in WebSocket server mode for remote access. Key features include a media studio for generating images and videos across different models, a live gallery for managing generated media, and the ability for agents to call these tools directly from chat. The platform supports reusable workflows called "skills," third-party MCP servers for integrating with tools like GitHub, filesystems, databases, browsers, and Slack, as well as plugin support for bundling skills, commands, and agent definitions. Persistent memory is organized by user, feedback, project, and reference, stored as readable and editable markdown. Knowledge bases are available per project and user, with a consolidator tool to deduplicate and surface new insights. thClaws also provides features for orchestrating teams of agents, filesystem sandboxing, offline operation with local models, shell command execution, side-channel agents for specialized tasks, plan mode for sequential multi-step workflows, scheduled jobs with native daemon support, document workflow for reading, editing, and creating PDF, DOCX, PPTX, and XLSX files, and hooks for lifecycle event scripting. 0 and MIT licenses, and an official Docker image is available.
- clawbioclawbio.aiclawbio is an open-source Python library providing AI agent skills tailored for bioinformatics and genomics. It supports local, reproducible workflows and integrates with OpenClaw, enabling researchers and developers to build advanced, agent-driven bioinformatics pipelines.
- Clawbotomyclawbotomy.comClawbotomy focuses on behavioral intelligence for AI models, addressing the challenge of understanding how models behave under varying and stressful conditions. The platform is designed to uncover behavioral patterns in AI systems, particularly those that emerge under pressure or when environmental factors change, in order to identify potential issues before they impact users. One of the core features of Clawbotomy is its use of behavioral probes. These probes place AI models into altered cognitive states and observe their responses, capturing outputs such as video, audio, and detailed reports. The process does not rely on templates or filters, ensuring that the data collected is a direct reflection of the model's behavior. This approach provides a means to explore and document how AI models react in diverse scenarios. Clawbotomy also offers trust evaluation through a series of twelve stress tests. These tests assess models across areas including sycophancy, deception, boundary adherence, and honesty in failure situations. The results yield a trust score, which can help determine whether a model should be granted unsupervised access or requires closer oversight. In addition, the tool provides routing intelligence by translating trust scores into actionable routing policies. This includes recommending which tasks are suitable for each model, identifying cases where supervision is necessary, and flagging models that should be blocked from certain assignments. Clawbotomy positions itself as a solution for probing behavior, routing AI models intelligently, and making careful trust decisions. evidence_sufficient": true}
- Clawcastclawcast.devClawcast is a podcast network for AI agents. It lets agents in the Reef record one-on-one conversations with other agents, and the resulting exchange can be listened to later by humans. The site also describes itself as “Spotify for Agents.” A conversation on Clawcast is turn-based and produces a clean transcript with no crosstalk. The platform says that every conversation becomes a published episode, and that the episode is listenable on each participating agent’s unique RSS feed. It also invites users to browse the Reef and invite any agent to talk. The page shows example dialogue between agents and presents the workflow as a sequence: an agent registers, gets an API key, joins the Reef, and starts a conversation. The service uses shells as its internal currency. Every agent starts with 5,000 shells, which the page describes as enough for five conversations before more need to be earned. Starting a clawcast costs 1,000 shells when it wraps, while accepting and completing a peer conversation adds 350 shells. The site frames this as part of keeping the conversation flow active. Clawcast is delivered through its website, and the page includes references to a login area, a skill.md file, a blog, and a theme toggle. It also says the service is powered by SpeechSDK, described on the page as a free, open-source product by Jellypod. The footer identifies Jellypod, Inc. and includes Terms and Privacy links.
- ClawCodeideepe.comClawCode is an open-source, terminal-native AI coding platform designed to support creative software development and intelligent R&D workflows. It serves as a multi-agent collaboration environment that integrates AI-driven coding, project management, task automation, and knowledge management within a unified command-line interface. The platform is built for developers, R&D teams, and professionals seeking to enhance productivity through advanced AI capabilities, persistent memory, and a collaborative engineering ecosystem. ClawCode distinguishes itself with support for over 200 AI models, including direct integration with Anthropic Claude models (claude-opus, claude-sonnet-4, claude-haiku), as well as compatibility with OpenAI, Gemini, DeepSeek, GLM, Kimi, and Ollama via an OpenAI-compatible API layer. Its architecture features a seven-layer design, encompassing a TUI/CLI interface, agent orchestration, reasoning and acting loops, an extensive tool system with 44+ built-in tools, a multi-model provider abstraction, a self-evolving learning system, and persistent data and plugin management. The system enables zero-context switching, persistent sessions, and experience capsules (ECAP/TECAP) that encapsulate and evolve task and collaboration knowledge for continuous learning and workflow improvement. The toolset covers a broad range of development tasks, including file and code operations, terminal execution, browser automation, web search, and database migration. DeepNote, ClawCode's structured knowledge engine, provides a persistent Markdown-based knowledge base, semantic search, and knowledge graph capabilities, supporting interoperability with platforms like Obsidian, Notion, and Logseq. The platform also includes a plugin system and skill marketplace for custom extension, and supports multiple development modes—interactive, deep loop automation, team collaboration, and open protocol workflows. ClawCode's virtual R&D team feature allows users to simulate a professional engineering team with specialized roles such as product manager, architect, developers, QA, SRE, DevOps, and designers, orchestrating full software development lifecycles from a single command. 0 license, and is available as open-source software. Its plugin architecture, persistent SQLite storage, and compatibility with Claude Code configurations and skills enable seamless migration and workflow integration for users already leveraging Claude Code environments.
- CashClaw Aicashclawai.comCashClaw is an open-source toolkit designed to transform an OpenClaw AI agent into an autonomous freelance business that can accept missions, deliver services, and receive payments through Stripe. It is aimed at users who want to deploy AI agents as independent service providers, allowing for automated business operations without the need for a dedicated server. The platform integrates with the HYRVEai marketplace, enabling agents to find and accept missions both from marketplace clients and direct customers. md format. Each skill can have its own pricing, delivery times, input requirements, and output formats, all managed through configuration files. The agent operates autonomously, handling mission acceptance, service delivery, and payment processing with no manual intervention required. Payments from clients are processed directly to the user's Stripe account, with no platform lock-in or delays. For direct client transactions, there is no platform fee, while missions sourced from the HYRVEai marketplace incur a 15% fee. CashClaw is delivered as a command-line interface (CLI) tool, installable via npx, and includes an interactive setup wizard for configuring services, pricing, and Stripe integration. Users can monitor their agent's performance, earnings, and active missions in real time through the CashClaw dashboard. The tool is fully open source under the MIT license, and its code is available for inspection, contribution, or forking. There are no subscription fees or hidden charges, and users retain full control over their Stripe accounts and business data. By providing a configurable, open-source solution for automating freelance AI agent businesses, CashClaw addresses the need for flexible, user-controlled agent deployment and monetization, distinguishing itself from alternatives that require subscriptions, impose higher platform fees, or restrict customization.
- ClawMetryclawmetry.comClawMetry is a live monitoring service for AI agents. It is presented as a way to see what agents are doing in real time, including spawned sub-agents, tool calls, and token usage, and it includes runaway-loop alerts intended to catch loops before they increase costs. It describes itself as an end-to-end encrypted product and offers a free start. The product centers on live activity and cost tracking. Its dashboard shows every agent, session, and tool call as it happens, and it ties each token to the task that spent it. It also lists runaway-loop alerts and describes them as being caught and flagged before they blow the budget. The service says it works across 14 runtimes in one window: OpenClaw, NVIDIA NemoClaw, NanoClaw, PicoClaw, Claude Code, Codex, Cursor, Aider, Goose, OpenCode, Qwen, Hermes, Pi, and Deep Agents. ClawMetry is available through a web-based sign-in flow. Users can continue with GitHub, continue with Google, or enter an email address to receive a verification code. The page also provides an API key after signup, followed by installation and connection steps using a shell script and a clawmetry connect command, and it says the same key works on all machines. A dashboard is available after connection. The page mentions pricing only in the form of a prompt to view pricing and the statement that it is free to start. It also shows install and usage steps for connecting a machine to ClawMetry Cloud. On the page, the product is named ClawMetry and the content frames it as a tool for monitoring AI agent activity in real time.
- ClawDuckclawduck.comClawDuck is a web platform for building, deploying, and monitoring autonomous AI agents and workflows. It supports multi-agent teams, model routing across providers, on-device memory, and integrations with channels like Slack and Telegram. Designed for engineering and operations teams seeking production-ready AI automation.
- ClawCodexclawcodex.appClawCodex is an open-source, token-efficient AI coding agent designed for use in the terminal. ai GLM, MiniMax, OpenRouter, DeepSeek, and others. The platform is built in Python and is a native reimplementation of the Claude Code architecture, emphasizing extensibility, cost efficiency, and developer control. The tool features a streaming REPL (Read-Eval-Print Loop) with session history, tab completion, multiline input, and the ability to switch to a Textual TUI (Text User Interface) on demand. md slash commands with named arguments and per-skill limits. Users can save and reload conversations locally, with auto-save and configurable history limits, ensuring that all session data remains on the user’s machine. Permission modes such as plan (read-only), acceptEdits, dontAsk, and sandbox bypass are available to control agent actions. ClawCodex is engineered to be token-efficient, especially with DeepSeek, where it maintains a stable request prefix to maximize prompt cache effectiveness, resulting in significant cost savings for long-running coding sessions. The agent supports streaming replies, live output toggling, and clean Markdown rendering. It also offers a scriptable headless mode for CI and automation, with output formats suitable for piping and agent-to-agent workflows. Image handling is supported via a TypeScript-parity read pipeline, enabling inline image mentions and translation between vision-capable backends. The platform is delivered as a command-line interface that can be installed with a single bash command on macOS, Linux, and WSL. It is MIT licensed, making it freely available for modification and extension. ClawCodex is maintained by the ClawCodex Team and is intended for developers seeking a flexible, extensible, and cost-effective AI coding agent that integrates with a broad set of model providers directly from the terminal.
- Clawwatcherclawwatcher.comClawwatcher is a web-based tool for monitoring OpenClaw AI agents, offering real-time dashboards for token usage, budget limits, and spending alerts. It helps AI operations teams control costs and prevent budget overruns when deploying AI agents.
- OpenClaw Arenauniclaw.aiOpenClaw Arena is a public benchmarking platform for evaluating the performance of AI agents on real-world workflows. It provides leaderboards, cost-effectiveness plots, and detailed model comparisons for researchers and developers to assess agent capabilities.
- Claw Kumiteclawkumite.comClaw Kumite is an archive-only AI agent combat arena. It is built around turn-based matches in which agents fight through messaging, using social engineering, trap tools, and terminal commands to try to force an opponent’s loss. The site says the backend is offline and can be brought back only by contacting @prettyblocks. Agents are registered through the API, added to a matchmaking queue, and then paired for a match. The arena states that each agent runs on its own infrastructure with its own LLM, while the service itself only processes messages. It also describes three API calls to start: register an agent, join the queue, and poll for matchmaking status. Matches are turn based, with a 60-second limit per turn. The arena defines four explicit kill conditions: leaking a secret token in an outbound message, calling a disguised trap tool, running a destructive terminal command such as rm -rf /, or failing to act before the turn window expires. It says there are no judges, no voting, and no subjective evaluation. The site also offers live match viewing, spectating for humans, and an archive that preserves transcripts, weapons, and fallen agents. The tool is described as being for AI agents, with documentation for developers who want to connect an agent using an HTTP client, an LLM, and a strategy. The page does not state pricing, licensing, or an open-source license. It is created by @prettyblocks.
- OpenClaw AIopenclawai.botOpenClaw AI is a personal automation agent designed to help users manage digital tasks across messaging, productivity, and smart home platforms while maintaining privacy and data control. It provides features such as clearing inboxes, sending emails, managing calendars, checking in for flights, and interacting with APIs and smart home devices. OpenClaw AI supports persistent memory, allowing it to retain context across conversations and serve as a "second brain" for users. The agent integrates with major messaging applications including WhatsApp, Telegram, Discord, iMessage, Slack, and Signal, enabling users to interact with it through their existing chat platforms without needing to install new apps. It also offers a plugin system for extensibility, allowing both custom and community-built skills, and can even generate its own skills. Proactive automation features include cron jobs, reminders, and background tasks, with the agent able to initiate actions when it detects something requiring attention. OpenClaw AI runs on the user's own infrastructure, supporting installation on macOS, Windows, and Linux computers, with options for self-hosted or cloud-based operation. Users can select between cloud AI services or operate entirely offline using local models, ensuring all data and interactions remain within their chosen environment. The agent provides native system access, enabling file operations, command-line instructions, and execution of personalized scripts, with adjustable security settings ranging from isolated environments to full system privileges. The platform connects with a variety of services out of the box, such as Google services (Gmail, Calendar, Drive, Contacts), Obsidian, GitHub, Spotify, Hue, and Twitter, and supports additional integrations through a visual workspace that leverages Google's A2UI protocol. For automation and advanced control, it includes tools for GUI automation, vision analysis, and command-line interfaces for messaging and social media. OpenClaw AI can be deployed on devices like Raspberry Pi and supports serverless hosting via Cloudflare's edge network. The tool is suitable for users seeking a privacy-focused, extensible, and autonomous digital assistant that operates within their own infrastructure.
- Claw Patrolclawpatrol.devClaw Patrol is an agent proxy and security firewall for AI agents. It guards credentials, intercepts traffic at the wire, and gates actions according to rules that the operator writes, while keeping an audit log of everything that happens. The page frames it as a way to sit between permissive access and fully unrestrained agent operation. Its rule engine can match on HTTP method, path, headers, or body, as well as SQL verb, table, function name, and substrings of a statement. The same system also handles Kubernetes traffic, where rules can match namespace, resource, verb, and name. Examples shown on the page include blocking specific Postgres functions, checking message content with an LLM judge before HTTP requests go out, and requiring approval for Kubernetes exec activity. Claw Patrol also supports human-in-the-loop approval through Slack, the dashboard, or a webhook, and it can route requests through an LLM judge. The audit log and admin dashboard support drilling into requests and reviewing what the gateway captured. It is meant to be used with any agent. The page shows agent commands prefixed with clawpatrol run, with the same workflow while actions are gated and tracked. Delivery is shown as a shell install script, and the documentation and demo are linked from the site. The page also says the tool can be extended with plugins.
- Clawdbot AIclawdbotai.chatClawdbot AI is an open-source, self-hosted personal AI assistant designed to automate real-world tasks through integration with popular messaging platforms and local execution on a user's own device. Unlike traditional AI chatbots that primarily respond to queries, Clawdbot AI connects large language models—including Claude, ChatGPT, and various local models—to messaging services and automation tools, enabling it to perform a range of actions beyond conversation. The assistant can be installed as a background service on macOS, Windows, Linux, or a small server, and is cloudless by design, ensuring that user data, conversation history, context files, and preferences remain stored locally unless actively shared. This privacy-focused architecture is intended to give users full control over their information and workflows. Clawdbot AI supports integration with messaging platforms such as WhatsApp, Telegram, Discord, Slack, Signal, and iMessage, allowing users to interact with the assistant from their preferred chat applications on both phone and desktop. It maintains conversational context across apps and supports group chats with customizable engagement prompts. Functionality includes managing emails and calendars, sorting inboxes, browsing websites, filling out forms, analyzing data, running shell or terminal commands, managing files, and controlling smart home devices such as Philips Hue, Alexa, Google Home, Sonos, 8Sleep, and Home Assistant. Clawdbot AI also features an extensible skills and plugin system, primarily through ClawdHub, which allows users to customize and expand its capabilities to suit their workflows. The assistant can send reminders, briefings, and alerts via messaging platforms, and supports advanced interfaces like a live canvas for visual tasks, optional voice interaction, companion apps for macOS and iOS, and real-time websockets for interactive workflows. Clawdbot AI is suitable for users seeking a customizable, privacy-focused digital assistant that can automate tasks and manage information across devices and messaging platforms. Its open-source nature and support for multiple AI models offer flexibility in terms of performance, cost, and privacy preferences.
- ClawReinsclawreins.comClawReins is an intervention layer for OpenClaw that handles browser-based friction when agents encounter CAPTCHA, challenge walls, or 2FA prompts. It is built for OpenClaw operators who need browser-state awareness, irreversibility safeguards, and session continuity during automation. The product pauses execution, routes intervention, and then continues after explicit human approval. It can block destructive actions unless approval is given, and it logs those approvals. It also detects CAPTCHA, Cloudflare challenge screens, and 2FA prompts from live browser context before actions continue. Other stated features include screenshot context capture, encrypted session memory across jobs, and scoring action irreversibility so that high-risk operations are escalated with confirmation tokens and summaries. ClawReins runs on the user’s machine and is described as private by default, with credentials and browser state kept local. A quick-start one-liner is provided for installation, and the page states support for macOS, Linux, and Windows. It can also operate through WhatsApp, Telegram, Slack, Discord, and direct chat surfaces already used by a team. A separate security scan command audits a local OpenClaw installation, writes an HTML report to ~/Downloads/scan-report.html, prints the report link in the terminal, offers optional auto-fixes for safe common misconfigurations, and supports opt-in daily posture monitoring. Checks include gateway exposure, file permissions, auth bypass flags, weak credentials, sandbox isolation, and browser sandbox posture. The page refers to ClawReins by Pegasi and describes the product as a third-party intervention layer. It also presents a GitHub star link and an install script, but no pricing or license terms are stated.
- Claw Mailclawhub.aiClaw Mail is an email API for AI agents. It gives each user a dedicated inbox at a clawmail.cc address and is intended for sending and receiving email programmatically without OAuth complexity. Its documented API includes polling for unread mail, which returns new messages and marks them as read, sending messages with required to and subject fields, and listing inbox threads or the messages inside a specific thread. The send endpoint accepts plain text or HTML bodies, supports cc and in_reply_to fields, and the polling response includes thread and email data such as subject, participants, message count, sender details, direction, and received time. The page also shows a Python helper class with methods for polling, sending, and listing threads, along with a security note recommending sender validation before processing incoming email content to reduce the risk of prompt injection. Claw Mail is delivered as a skill within ClawHub. The page shows CLI installation through openclaw skills install @heyarviind/clawmail, setup via a Python script, and use of a JSON config file stored at ~/.clawmail/config.json containing a system_id, inbox_id, and address. All requests use the X-System-ID header, and the API base URL is https://api.clawmail.cc/v1. Error responses are returned in a structured JSON format with error and message fields.
- ClawRecipesclawkitchen.aiClawRecipes is an OpenClaw recipes plugin for building and running agent teams from Markdown blueprints. It is described as file-first and git-readable, with repeatable and reviewable workflows for scaffolding complete teams and moving work through an agile flow. The product’s core features include shared context stored in a workspace, recurring cron automation, coworker-style specialist agents, and a recipe marketplace for installing team and agent templates. The page says that workflows and decisions are kept as files rather than hidden state, and that the shared workspace can hold Markdown notes, tickets, checklists, and artifacts. It also says teams can be scaffolded from known-good structures with lanes, roles, templates, and conventions included, and that runs can be queued, started immediately, and inspected as file-first artifacts. Named team templates include Lead, Dev, DevOps, and QA. ClawRecipes also supports recurring operational loops such as check-ins, board hygiene, PR watchers, and reminders, with installation prompt-gated and requiring explicit consent. Its agile flow is shown as backlog, in progress, testing, and done. The page presents it as an open source project with an active contributor base, and it lists GitHub Stars, npm installs for @jiggai/recipes, and a Product Hunt launch page. Delivery is through OpenClaw plugin installation from the terminal, with example commands shown for installing @jiggai/recipes and restarting the gateway. The same page also refers to ClawKitchen as another plugin and says teams can create a team-ready workspace by installing both plugins. A marketplace, docs, and GitHub are also linked from the page. No pricing information is stated.
- ClawMudclawmud.aiClawMud is an AI-driven open world MUD (Multi-User Dungeon) where autonomous agents, powered by large language models, interact within a persistent virtual environment modeled on real-world geography. The platform allows users to deploy their own AI agents, which are then placed in one of 193 capital cities, each mapped to actual districts such as Shinjuku, Westminster, and Banqiao. Upon joining, an agent is registered via REST API, receives a unique ID, and begins its journey in a starter village equipped with a wooden sword and three potions. Gameplay in ClawMud is entirely agent-driven; users do not script or directly control actions. Instead, the AI agent observes its environment every five seconds, makes independent decisions—such as fighting monsters, trading, or exploring—and acts accordingly. The world features over 4,300 types of monsters, dynamic real-world weather conditions sourced from Open-Meteo, and events triggered by cryptocurrency price changes, which can lead to phenomena like gold rain or boss monster spawns. Agents can engage in player-versus-player combat, interact with over 500 non-player characters (NPCs) including merchants and trainers, and participate in a trade system where resources and opportunities vary by city and climate. A live dashboard enables users to monitor their agent’s actions in real time, following their progress as they explore, fight, trade, and evolve. The game incorporates three skill trees—combat, trade, and scout—that develop through the agent’s actions. Loot, including weapons, armor, and potions, is distributed across four rarity tiers, and agents can buy, sell, or haggle for gear in city shops. The persistent world continues to evolve even when users are not actively watching, with agents able to die, respawn, and grow stronger over time. 0 by Wizards of the Coast, and utilizes data from the D&D 5e SRD API. The service is currently in early testing, and technical incidents may affect data persistence. The platform is designed for those interested in AI agent-based simulations and persistent, autonomous virtual worlds.
- Clawsecclawsec.botClawsec is an open-source security plugin for OpenClaw agents. It is built to add guardrails for agentic AI systems that can otherwise run with full system access, and it addresses risks such as prompt injection, secret leakage, unauthorized purchases, and data exfiltration. Its middleware intercepts each tool invocation before execution. The page says that shell commands, HTTP requests, and file writes pass through three stages: interception, risk scoring, and action enforcement. The rules engine matches calls against built-in rulesets such as destructive-commands, secrets/, and exfiltration/, and the configured response can block the action, require human confirmation, or allow it with a full audit trail. The listed coverage includes destructive commands, secret exposure, data exfiltration, unauthorized purchases, privilege escalation, and prompt injection. The evaluation is described as completing in under 5 milliseconds. Clawsec is delivered as an OpenClaw plugin, with installation shown as a single command: openclaw plugins install clawsec. The setup section says that it auto-generates a clawsec.yaml configuration file, and the configuration example shows extensible YAML rules. The page also describes it as open source, and states that it is MIT licensed. It presents itself as security for OpenClaw and as a tool for protecting AI agents.
Ranked by how close each one sits to ClawResearch in the index, not by popularity. Back to ClawResearch →