No-Code Agentist

#4 on my list I keep as a sticky on the desktop. Copy pasta, anyone down⬇️ Hermes Top 20 Slash Commands 1. /goal <text> Alias: — What it does: Sets a persistent goal that Hermes auto-continues until done (with judge model) Why useful: Turns Hermes into an autonomous agent for big tasks Best for: Long/complex projects 2. /btw <question> Alias: /bg, /background What it does: Runs an ephemeral side question using session context (no tools, not persisted) Why useful: Quick clarifications without polluting main context Best for: Side questions, gut checks 3. /queue <prompt> Alias: /q What it does: Queues a message for the next turn without interrupting current work Why useful: Stack follow-ups while agent is working Best for: Multi-step workflows 4. /steer <prompt> Alias: — What it does: Injects a note mid-tool loop (after next tool call) Why useful: Nudge direction without stopping the agent Best for: Mid-task corrections 5. /cron Alias: — What it does: Manage scheduled/recurring tasks (daily briefs, monitoring, etc.) Why useful: True automation and "set and forget" jobs Best for: Recurring work 6. /model <name> Alias: — What it does: Switch models/providers instantly (e.g. /model claude-sonnet-4) Why useful: Change model without leaving the session Best for: Experimenting / cost control 7. /new [name] Alias: /reset What it does: Start a completely fresh session Why useful: Clean context reset Best for: New tasks 8. /compress Alias: — What it does: Manually summarize + flush old context Why useful: Save tokens on very long conversations Best for: Long sessions 9. /stop Alias: — What it does: Immediately kills background tasks and interrupts the agent Why useful: Emergency brake Best for: When things go wrong 10. /status Alias: — What it does: Shows model, tokens, files touched, recent activity (no LLM call) Why useful: Quick situational awareness Best for: Every session 11. /skills Alias: — What it does: Search, install, manage, and approve skills Why useful: Extend Hermes with new capabilities Best for: Power users 12. /tools Alias: — What it does: List, enable, or disable specific tools Why useful: Fine-tune what the agent can do Best for: Security / control 13. /rollback Alias: — What it does: List and restore filesystem checkpoints Why useful: Undo file/code changes safely Best for: Coding & file work 14. /branch [name] Alias: /fork What it does: Create a branch of the current session Why useful: Explore alternatives without losing main thread Best for: Experimentation 15. /sessions Alias: /switch (TUI) What it does: Browse and resume previous named sessions Why useful: Jump between different projects easily Best for: Multi-project work 16. /yolo Alias: — What it does: Toggle YOLO mode (skip all dangerous command approvals) Why useful: Faster execution when you trust the agent Best for: Power users 17. /undo Alias: — What it does: Remove the last user + assistant exchange Why useful: Quick correction of mistakes Best for: Everyday fixes 18. /retry Alias: — What it does: Re-send the last message to the agent Why useful: When the last response was bad Best for: Quick recovery 19. /kanban Alias: — What it does: Full Kanban board commands (create, list, comment, etc.) Why useful: Built-in task/project management Best for: Productivity workflows 20. /curator Alias: — What it does: Background skill maintenance (status, run, pin, archive) Why useful: Keep your skills clean and up to date Best for: Long-term maintenance --- Just copy everything above and paste it straight into Apple Stickies. It will look clean and well-structured.

Your AI agent doesn't need more memory. It needs taste. This system gives it one. It's called a Taste Index. Two open source pieces, two messages to set up. Hermes is the operating layer. It coordinates the tools, files, memory, and workflows. It's the agent you talk to. GBrain is the knowledge layer. Open source, built by Garry Tan to run his own agents. It runs locally, no server. Durable ideas and references live there as connected markdown pages. The Taste Index sits inside GBrain. Every entry stores the thing you liked, what you liked about it, and why it should shape future work. → The link is the receipt. The why is the asset. The rule that keeps it sharp: no signal, no storage. Send the agent a random link and nothing gets saved. It waits for you to explicitly say this one crossed the bar. ↳ Useful once is not the same as durable. Every capture answers two questions: what I liked, and why it's useful. If either is missing, the capture isn't ready. Then the agent reads it at the right time: Before writing a post, it checks your writing taste. Before proposing product ideas, it checks your product taste. Before saving a new note, it checks the capture rules. One capture from the source: no generic AI demos that just swap the noun. The agent now kills those ideas before they reach you. Once a week, the agent audits its own index. Missing whys, duplicate pages, task status that snuck in: one message, you answer in one line. Silence means healthy. The curator never ingests. It only audits. A maintenance job that adds material is just another way around the gate. Setup, no code: 1. Tell your agent to install GBrain. 2. Send it the article with a short briefing. The article is the spec. Your agent is the builder. Works with any agent that runs commands and manages files: Claude Code, Codex, OpenClaw. GBrain speaks MCP. Twenty strong captures beat two thousand weak notes. Save this. What's the first taste rule you'd give your agent?

Building an AI agent used to mean writing code. Actionist changes that. Instead of building integrations or writing scripts, you can create AI agents that interact with websites just like a human. No code. No APIs. No engineering team. Build workflows visually, deploy them, and let your AI automate work across virtually any web platform. With 250,000+ active users already contributing to the @ActionModelAI ecosystem, the next step isn't just earning from AI. It's building AI employees that can work for you. What repetitive task would you automate first with an AI agent? 👾👾👾 Learn more 👇 https://t.co/NBPLCT4RFH