agent-forgeCreate and deploy independent OpenClaw agents via an 11-step interview, generating personalized files, configuring tools, channels, permissions, and updating...
Install via ClawdBot CLI:
clawdbot install limoxt/agent-forgeGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 21, 2026
A company deploys dedicated agents for handling tier-1 support inquiries via Discord or Telegram, each configured with specific tools like web_search for knowledge base lookups and sessions_send for escalating complex issues to human agents. This reduces response time and ensures consistent, personalized interactions.
An agency uses Agent Forge to create specialized agents for tasks like social media posting, blog writing, and SEO analysis, with each agent having isolated workspaces and tailored tool permissions (e.g., write for drafting, web_fetch for research). This streamlines content pipelines and maintains brand voice across channels.
A biotech firm sets up agents for data analysis, literature review, and experiment tracking, using models like google/gemini-3.1-pro-preview for long-text processing and tools such as memory_search for accessing past findings. Agents communicate via sessions_spawn for asynchronous tasks, enhancing collaboration.
An online retailer creates agents that interact with customers on Feishu or Telegram, offering product recommendations based on user preferences stored in memory_get and using exec for inventory checks. This provides a personalized shopping experience and boosts sales through automated engagement.
A bank deploys agents to monitor transactions and generate reports, configured with sandbox exec-only for security and tools like cron for scheduled audits. Agents update AGENTS.md to track team interactions and ensure regulatory compliance through automated checks.
Offer monthly plans where businesses pay to deploy and maintain custom agents for specific roles like support or marketing, with tiered pricing based on agent complexity and tool usage. Revenue comes from recurring fees and optional premium features like advanced analytics.
Provide one-time or project-based services to design, interview, and deploy agents tailored to client needs, including configuration of gateway settings and skill paths. Revenue is generated through fixed project fees or hourly rates for setup and ongoing optimization.
Sell pre-configured agent packages for common use cases (e.g., sales bots, code reviewers) on a platform, with optional customization and support. Revenue streams include template sales, licensing fees, and commissions from third-party skill integrations.
💬 Integration Tip
Ensure gateway config updates are tested post-deployment to avoid communication issues between agents, and always verify tool permissions align with agent roles for security.
Scored Apr 19, 2026
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version f...
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions.
Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when users ask about skills, 插件, or capabi...
Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new s...
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.