No-Code Agentist

A daily digest of practical AI agent workflows for non-developers. We isolate actionable no-code guides from viral hype. Scored against human-defined standards.

Latest Oct 2 Oct 1 Sep 30 Sep 29 Sep 28 Sep 27 Sep 26 Sep 25 Sep 24 Sep 23 Sep 22 Sep 21 Sep 20 Sep 19 Sep 18 Sep 17 Sep 16 Sep 15 Sep 14 Sep 13 Sep 12 Sep 11 Sep 10 Sep 9 Sep 8 Sep 7 Sep 6 Sep 5 Sep 4 Sep 3 Sep 2 Sep 1 Aug 31 Aug 30 Aug 29 Aug 28 Aug 27 Aug 26 Aug 25 Aug 24 Aug 23 Aug 22 Aug 21 Aug 20 Aug 19 Aug 18 Aug 17 Aug 16 Aug 15 Aug 14 Aug 13 Aug 12 Aug 11 Aug 10 Aug 9 Aug 8 Aug 7 Aug 6 Aug 5 Aug 4 Aug 3 Aug 2 Aug 1 Jul 31 Jul 30 Jul 29 Jul 28 Jul 27 Jul 26 Jul 25 Jul 24 Jul 23 Jul 22 Jul 21 Jul 20 Jul 19 Jul 18 Jul 17 Jul 16 Jul 15 Jul 14 Jul 13 Jul 12 Jul 11 Jul 10 Jul 9 Jul 8 Jul 7 Jul 6 Jul 5 Jul 4 Jul 3 Jul 2 Jul 1 Jun 30 Jun 29 Jun 28 Jun 27 Jun 26 Jun 25 Jun 24 Jun 23 Jun 22 Jun 21 Jun 20 Jun 19 Jun 18 Jun 17 Jun 16 Jun 15 Jun 14 Jun 13 Jun 12 Jun 11 Jun 10 Jun 9 Jun 8 Jun 7 Jun 6 Jun 5 Jun 4 Jun 3 Jun 2 Jun 1 May 31 May 30 May 29 May 28 May 27 May 26 May 25 May 24 May 23 May 22 May 21 May 20 May 19 May 18 May 17 May 16 May 15 May 14 May 13 May 12 May 11 May 10 May 9 May 8 May 7 May 6 May 5 May 4 May 3 May 2 May 1 Apr 30 Apr 29 Apr 28 Apr 27 Apr 26 Apr 25 Apr 24 Apr 23 Apr 22 Apr 21 Apr 20 Apr 19 Apr 18 Apr 17 Apr 16 Apr 15 Apr 14 Apr 13 Apr 12 Apr 11 Apr 10 Apr 9 Apr 8 Apr 7 Apr 6 Apr 5 Apr 4 Apr 3 Apr 2 Apr 1 Mar 31 Mar 30 Mar 29 Mar 28 Mar 27 Mar 26 Mar 25 Mar 24 Mar 23 Mar 22 Mar 21 Mar 20 Mar 18 Mar 17 Mar 16 Mar 15 Mar 14 Mar 13 Mar 12 Mar 11 Mar 10 Mar 9 Mar 8 Mar 7 Mar 6 Mar 5 Mar 4 Mar 3 Mar 2 Mar 1 Feb 28 Feb 27 Feb 26

Daily Summary

5 curated | 8 evaluated

No-code agent builders are shifting from chatbots to autonomous systems that execute multi-step workflows while users focus elsewhere, as demonstrated by and combining dozens of plugins for end-to-end task automation. Meanwhile, Anthropic's new for Claude Managed Agents marks a fundamental change in how AI inference is billed, and emerging tools like Hermes Agent are rapidly gaining adoption despite .

•Fran_actua demonstrated three independent agents handling invoicing, payment management, and content creation that work autonomously without requiring apps to be open or user presence.

•MacopeninSUTABA shared construction documentation for an AI secretary that combines Code with 90 official plugins to automate workflows from morning issue triage to evening Slack summaries.

•GauravKara_koti highlighted no-code agent creation with multi-agent orchestration, on-chain settlement capabilities where agents carry wallets and execute blockchain transactions, and an emerging agent economy model.

Apr 27, 10:38 AM

No es un chatbot que responde preguntas. Es un agente que vive en tu ordenador y ejecuta tareas mientras tú haces otra cosa. En este ejemplo👇 Generé 3 agentes independientes, uno encargado de mis facturas, otro de la gestión de los cobros y otro de la creación de contenido. (FACTURACIÓN-COBROS-CONTENIDO) Son capaces de trabajar sin abrir ninguna app. Sin estar delante. Enlaces a los Agentes que he creado: https://t.co/zpasJ9H1Lz https://t.co/sIkBuSdvHs https://t.co/281SSPMu5t

Replied to Fran_actua:"La situación antes de encontrarlo: Tres side hustles corriendo en paralelo. Facturas que enviar, clientes que perseguir, contenido que publicar. Todo..."

agentic-orchestration88

high-signal-utility75

no-code-feasibility100

Apr 27, 2:37 PM

「AI秘書」の構築資料が有益。 Codeと90個の公式プラグインを組み合わせ、朝のIssueトリアージから夕方のSlack要約までを自動化する「AI秘書」の構築手順を余すことなく徹底公開。こちら👉 https://t.co/Le7uyyioh6

Apr 26, 3:42 PM

🔻 No-code agent creation Build and deploy AI agents without writing a single line of code... just describe your goal. 🔻 Multi-agent orchestration Agents coordinate in complex workflows together, not one-off scripts. Spaghetti logic is replaced by modular, reusable intelligence. 🔻 On-chain settlement Agents carry wallets and execute transactions. They can trade assets or pay for services directly on the blockchain. Every trade or payment is final and verifiable... no hidden fees or off-platform accounting. 🔻 Agent economy Kodeus turns each contribution into a revenue stream. As Sooryah Pokkali (CBO) explains, “Platforms scale with users; ecosystems scale with owners.” On Kodeus, build an agent -> earn when others use it; create a plugin -> earn on each invocation. All rewards flow in native $KODE tokens, making intelligent automation self-sustaining.

Replied to GauravKara_koti:"Kodeus’s architecture makes this possible. Agents are minted as NFTs with traceable logic and history, giving each agent a native identity and on-cha..."

Apr 27, 2:59 PM

Hermes Agent just overtook Claude Code in GitHub stars. It's already ahead of Codex. Yet people are still sleeping on it. If you work or tinker with AI and you haven't tried it yet, you owe it to yourself to try it. It's not going to take you a long time to set up. 5-15 mins max and another 30-45 mins testing it. Do so will dispel your doubts. It doesn't take long to form your own judgement of whether it's hype or substance. You'll be surprised. I was asking a friend who uses lots of Claude Code why he didn't try it yet. He said it's because it'll take him a long time to get it properly set up. NOPE. It's not true. This is not some IDE, Claw or CLI that takes a long time to get up and running. Once you have your tokens flowing, just start chatting and pointing it at things you need to get done. You'll be surprised. If you decide to stick with it, follow my quick post on how to make it even better. Takes another 10-15 mins and you really only need it if you commit to it. https://t.co/EWeSKhRo0I Try it. Don't be left behind.

Apr 27, 2:52 PM

Anthropic confirmed Claude Managed Agents pricing this week. Session runtime is $0.08 per session-hour, billed to the millisecond. Only running time counts. Idle time is free. Token costs continue at standard rates. For Opus 4.6 that is $5 per million input tokens and $25 per million output tokens. Web search inside a session is $10 per 1,000. Anthropic's worked example puts a one hour coding session at $0.705 total. The Code Execution container hour billing folds into session runtime. The pricing news is not the dollar number. The pricing news is the unit. For two and a half years, AI inference has been priced on tokens. A token measures the input or output piece of text the model processes. Every API call has a token meter on it. Every commercial integration is built around token cost as the variable line item. That is the unit of compute consumed per query. Session runtime is a different unit. A session is the agent residency held open against a user's intent. A coding agent that takes one hour to ship a pull request consumes session runtime for the full hour, even when it is reading documentation, navigating files, or waiting on a tool. The token meter on that same session captures the inference cost. The two units price two different things. Tokens price compute. Sessions price persistence. This matters because agentic AI does not match the token billing model cleanly. An agent that does the work of a knowledge worker does not consume tokens at a constant rate. It consumes them in bursts, with long stretches of orchestration, planning, and waiting. Token pricing alone underprices the cost of holding the agent open. Session pricing prices the cost of the agent being available to the workflow. The two together price the actual unit of work the agent performs. The first principles read is that the pricing primitive for agentic AI just moved one layer up the stack. From the inference call to the work session. From compute consumed to time the agent is the responsible party for a workflow. This is a small word change that has large procurement implications.