# hermes-agent

Hermes Agent is an open-source autonomous AI agent framework with persistent memory, automated skills, sandboxed execution, integrations, and developer-oriented tool support.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Give Hermes Agent a Long-Term Memory on Upstash Redis

DevFeed: [Give Hermes Agent a Long-Term Memory on Upstash Redis](<https://devfeed.tech/articles/give-hermes-agent-a-long-term-memory-on-upstash-redis-129331.md>)

Original publisher: [Read original article](<https://upstash.com/blog/hermes-agent-memory-upstash-redis>)

Author: Cahid Arda Oz

Published: 2026-11-06T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Redis](<https://devfeed.tech/topics/redis.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [chat](<https://devfeed.tech/tags/chat.md>), [free](<https://devfeed.tech/tags/free.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [hermes-agent](<https://devfeed.tech/tags/hermes-agent.md>), [memory](<https://devfeed.tech/tags/memory.md>), [redis](<https://devfeed.tech/tags/redis.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

upstash-hermes-memory extends Hermes Agent's small built-in memory files by storing memories and session transcripts in Upstash Redis. Before each turn it uses hybrid search to add the three most related memories; after the turn it appends new messages to the transcript. Chat transcripts can be searched with fuzzy full-text matching, while Redis Search creates embeddings without a separate embedding model or vector database. Built-in memory remains active and is synchronized to Redis when facts are added, corrected, or removed. The integration uses one Redis Search index, so it can run on Upstash's Free plan; sharing the database with the TypeScript AgentKit integration requires a plan that allows more than one index. Setup requires a Redis REST URL and token, entered through `hermes memory setup` or configured manually after installing the Python package. The article says the main agent writes memory, while subagents, cron jobs, and context flushes can read it.

### Source excerpt

upstash-hermes-memory gives Hermes Agent long-term memory and searchable chat history on Upstash Redis. It recalls related memories on every turn and runs on the Free plan.

## Use NVIDIA NeMo to Turn Agent Failures into Tests and Harness Fixes

DevFeed: [Use NVIDIA NeMo to Turn Agent Failures into Tests and Harness Fixes](<https://devfeed.tech/articles/use-nvidia-nemo-to-turn-agent-failures-into-tests-and-harness-fixes-117643.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/use-nvidia-nemo-to-turn-agent-failures-into-tests-and-harness-fixes/>)

Author: Patrick Moorhead

Published: 2026-11-04T16:00:00Z

Content type: tutorial

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [NeMo](<https://devfeed.tech/topics/nemo.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [NemoClaw](<https://devfeed.tech/topics/nemoclaw.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-evaluation](<https://devfeed.tech/tags/agent-evaluation.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [build-ai-agents](<https://devfeed.tech/tags/build-ai-agents.md>), [code](<https://devfeed.tech/tags/code.md>), [custom](<https://devfeed.tech/tags/custom.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [harness](<https://devfeed.tech/tags/harness.md>), [llms](<https://devfeed.tech/tags/llms.md>), [memory](<https://devfeed.tech/tags/memory.md>), [models](<https://devfeed.tech/tags/models.md>), [nemo](<https://devfeed.tech/tags/nemo.md>), [nemoclaw](<https://devfeed.tech/tags/nemoclaw.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-nemo](<https://devfeed.tech/tags/nvidia-nemo.md>), [production](<https://devfeed.tech/tags/production.md>), [skills](<https://devfeed.tech/tags/skills.md>), [tests](<https://devfeed.tech/tags/tests.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

The tutorial presents a repeatable agent-improvement loop: use NeMo Compass to analyze recorded traces against intended behavior, turn recurring failures into reviewed Harbor or NeMo Gym evaluations with NeMo Eval Author, change the agent harness, then compare development and held-out results. In the Hermes example, the agent sent a drafted message without confirmation; the harness instructions were changed to require review before sending, and Compass later surfaced a separate evidence-grounding issue. In a car-door engineering workflow, adding validation for misplaced QueryModel arguments reduced malformed calls from 142 to zero; accuracy stayed unchanged, with no reported regressions. Across six scenarios, the overnight run reported a 28% relative increase in overall evaluation score and 35% fewer tool calls per run. The tutorial advises retaining hidden held-out cases and adopting changes only when both development and held-out results improve; inconclusive results or regressions call for another trace analysis. The excerpt recommends broad production evaluation suites but does not provide full setup instructions.

### Source excerpt

Turn production evidence into prioritized issues and custom evaluations that help you improve prompts, tools, models, memory, skills, and harness code. When you...

## AI Agent Memory (Part 3): How Agents Turn Experience Into Reusable Skills

DevFeed: [AI Agent Memory (Part 3): How Agents Turn Experience Into Reusable Skills](<https://devfeed.tech/articles/ai-agent-memory-part-3-how-agents-turn-experience-into-reusable-skills-114848.md>)

Original publisher: [Read original article](<https://hackernoon.com/ai-agent-memory-part-3-how-agents-turn-experience-into-reusable-skills?source=rss>)

Author: ShaoTung Lien (練紹彤)

Published: 2026-11-03T15:04:42Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>)

Tags: [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-architecture](<https://devfeed.tech/tags/ai-agent-architecture.md>), [ai-agent-memory](<https://devfeed.tech/tags/ai-agent-memory.md>), [ai-agent-memory-systems](<https://devfeed.tech/tags/ai-agent-memory-systems.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-decision-making](<https://devfeed.tech/tags/ai-decision-making.md>), [ai-feedback-loops](<https://devfeed.tech/tags/ai-feedback-loops.md>), [ai-self-improvement](<https://devfeed.tech/tags/ai-self-improvement.md>), [ai-skills](<https://devfeed.tech/tags/ai-skills.md>), [experience](<https://devfeed.tech/tags/experience.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [learning](<https://devfeed.tech/tags/learning.md>), [process](<https://devfeed.tech/tags/process.md>), [skills](<https://devfeed.tech/tags/skills.md>)

### AI overview

An agent can find and follow a saved lesson yet still mislearn from experience: after one request for a shorter meeting update, it may infer a lasting preference for brief reports and omit evidence needed for a spending decision. The excerpt distinguishes the event from the lesson inferred from it, and outlines three stages: retain the event and setting, identify a possible pattern, then turn that pattern into a method. Each can lose context or overreach. Hermes can create and edit reusable Skills, while EvoMap's GEP protocol describes strategies with conditions, checks, and outcome records. Revising a single Skill fixes that lesson; improving how future lessons are formed requires feedback to change the system's judgment about evidence, context, and exceptions. The excerpt cites human studies as specific examples of experience changing how later information is handled, while emphasizing that a growing Skill library alone does not ensure this broader improvement.

### Source excerpt

AI agents can remember feedback but still learn the wrong lessons. Explore how agents turn experience into Skills and why improving that process matters.

## Memorix: Managing Memory Selections for AI Agents

DevFeed: [Memorix: Managing Memory Selections for AI Agents](<https://devfeed.tech/articles/memorix-managing-memory-selections-for-ai-agents-114975.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.00060>)

Author: Jing Zhang, Xiaguannan Song, Dong Du, Erhu Feng, Yubin Xia

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [long-running](<https://devfeed.tech/topics/long-running.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>)

Tags: [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-os](<https://devfeed.tech/tags/cs-os.md>), [memory](<https://devfeed.tech/tags/memory.md>)

### AI overview

Memorix precomputes project-specific memory selections for reuse across agent tasks, aiming to reduce costly assembly and avoid missing or outdated context. Its immutable, versioned Store pins sources by identity; a View separates selection (Derivations) from composition (Environment) for reproducible, shareable results; and Quests and Profiles keep delivered views refreshable as sources change. On SWE-ContextBench and LibEvolutionEval, the authors report up to 1.5x higher task resolution, correct library versions on every version-conditioned task, up to 100x lower amortized cost, and up to 38x shorter build time versus mainstream agent memory systems. These are reported maxima; the excerpt does not provide further evaluation details.

### Source excerpt

arXiv:2611.00060v1 Announce Type: cross Abstract: AI agents now handle a growing share of tasks across sessions within a persistent project. Their behavior depends not only on the model, but heavily on the persistent state they read from the environment. Existing systems assemble this memory at use time, splicing selected files into the prompt as a one-off payload. As a result, per-task assembly is costly and can still miss critical material, failures cannot be traced or replayed, and agents can read documentation written for the wrong version. Our key insight is that what an agent should read is mostly determined by its project, so the selection can be computed once, ahead of time, and reused across tasks. We propose Memorix, an agent memory system that realizes this insight. Memorix achieves this via three key mechanisms: (1) an immutable and versioned Store pins every source by identity and reproduces historical layouts cheaply, (2) a View that splits selection (Derivations) from composition (Environment), making the result reproducible and shareable, and (3) Quests and Profiles keep a delivered view refreshable and available inside the project as sources evolve. We implement Memorix and evaluate it on SWE-ContextBench and LibEvolutionEval against mainstream agent memory systems. Precomputed Environments raise resolved rate by up to 1.5X and deliver the correct library version on every version-conditioned task, while cutting amortized cost by up to 100X and build time by up to 38X.

## Build Specialized Agents on a Stack You Control with NVIDIA NemoClaw

DevFeed: [Build Specialized Agents on a Stack You Control with NVIDIA NemoClaw](<https://devfeed.tech/articles/build-specialized-agents-on-a-stack-you-control-with-nvidia-nemoclaw-109507.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/build-specialized-agents-on-a-stack-you-control-with-nvidia-nemoclaw/>)

Author: Nicola Sessions

Published: 2026-10-30T16:00:00Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [NemoClaw](<https://devfeed.tech/topics/nemoclaw.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [OpenShell](<https://devfeed.tech/topics/openshell.md>), [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Self Hosted AI Tools](<https://devfeed.tech/topics/self-hosted-ai-tools.md>), [NeMo](<https://devfeed.tech/topics/nemo.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [DGX Spark](<https://devfeed.tech/topics/dgx-spark.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [build](<https://devfeed.tech/tags/build.md>), [build-ai-agents](<https://devfeed.tech/tags/build-ai-agents.md>), [building](<https://devfeed.tech/tags/building.md>), [control](<https://devfeed.tech/tags/control.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [developers](<https://devfeed.tech/tags/developers.md>), [domain](<https://devfeed.tech/tags/domain.md>), [harness](<https://devfeed.tech/tags/harness.md>), [llms](<https://devfeed.tech/tags/llms.md>), [model](<https://devfeed.tech/tags/model.md>), [need](<https://devfeed.tech/tags/need.md>), [nemoclaw](<https://devfeed.tech/tags/nemoclaw.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [openshell](<https://devfeed.tech/tags/openshell.md>), [requires](<https://devfeed.tech/tags/requires.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [stack](<https://devfeed.tech/tags/stack.md>), [tools](<https://devfeed.tech/tags/tools.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

NemoClaw is a set of blueprints that assembles an open agent stack around a developer's chosen harness; it is neither a harness nor a runtime. Its blueprints combine a harness tuned for Nemotron, Nemotron models, NeMo optimization and observability tools, and OpenShell runtime policies governing access to files, networks, credentials, and tools. The text names OpenClaw, Hermes Agent, and LangChain Deep Agents, each with different capabilities, and says existing agents can use a blueprint without being rewritten. As one example, tuning LangChain Deep Agents for Nemotron 3 Ultra reportedly achieved near-frontier performance at about 10x lower cost per run than leading closed models, without retraining. A Hermes Chief of Staff recipe illustrates persistent memory, OpenShell controls, and NeMo Relay traces for audit and optimization. The stack is described as deployable across cloud, data centers, and supported NVIDIA systems; tools and policies can be customized for each workflow.

### Source excerpt

Building an autonomous agent requires a model, a harness, and domain-specific tools. To deploy an agent more securely, developers need a runtime that enforces...

## Better than Grok Bot: Running Customer Success with Hermes on Upstash Box

DevFeed: [Better than Grok Bot: Running Customer Success with Hermes on Upstash Box](<https://devfeed.tech/articles/better-than-grok-bot-running-customer-success-with-hermes-on-upstash-box-101491.md>)

Original publisher: [Read original article](<https://upstash.com/blog/hermes-on-upstash-box-customer-success>)

Author: Sertuğ Kaya

Published: 2026-10-26T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Bot](<https://devfeed.tech/topics/bot.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [always-on-assistant](<https://devfeed.tech/tags/always-on-assistant.md>), [app](<https://devfeed.tech/tags/app.md>), [apps](<https://devfeed.tech/tags/apps.md>), [automated](<https://devfeed.tech/tags/automated.md>), [background](<https://devfeed.tech/tags/background.md>), [billing](<https://devfeed.tech/tags/billing.md>), [board](<https://devfeed.tech/tags/board.md>), [box](<https://devfeed.tech/tags/box.md>), [browser](<https://devfeed.tech/tags/browser.md>), [build](<https://devfeed.tech/tags/build.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-success](<https://devfeed.tech/tags/customer-success.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [lean](<https://devfeed.tech/tags/lean.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [nous-research](<https://devfeed.tech/tags/nous-research.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-agent](<https://devfeed.tech/tags/open-source-agent.md>)

### AI overview

The author runs Hermes, Nous Research's open-source agent, on an always-on Upstash Box so scheduled briefs and meeting preparation continue while their laptop sleeps. Slack on mobile and Hermes Desktop share the same agent and memory; Upsy connects it to work apps and provides a cloud browser. Hermes monitors customer and account signals, prepares call briefs, triages email, and drafts outreach, while the author retains approval over sending messages or changing plans and billing. The author reports that a Small Box was sufficient for the setup's observed usage, with Medium suggested as a growth buffer, and describes using temporary Boxes for heavier jobs. Setup guidance includes completing Upsy sign-in through a local browser when the Box has no browser, limiting the Upstash MCP account to a sandbox because access covers all products in it, and writing explicit approval rules.

### Source excerpt

How I run Customer Success at a lean startup with Hermes, the open-source agent from Nous Research, living on an always-on Upstash Box and connected to my work apps through Upsy.

## Open-weight AI models are changing the equation. Here's what CIOs should experiment with next

DevFeed: [Open-weight AI models are changing the equation. Here's what CIOs should experiment with next](<https://devfeed.tech/articles/open-weight-ai-models-are-changing-the-equation-here-s-what-cios-should-experiment-with-next-97455.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4239186/open-weight-ai-models-are-changing-the-equation-heres-what-cios-should-experiment-with-next.html>)

Author: Matthew Finlayson

Published: 2026-10-23T10:00:00Z

Content type: opinion

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [ai-experiments](<https://devfeed.tech/topics/ai-experiments.md>), [gemma](<https://devfeed.tech/topics/gemma.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [OpenClaw](<https://devfeed.tech/topics/openclaw.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [Self Hosted AI Tools](<https://devfeed.tech/topics/self-hosted-ai-tools.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [advice](<https://devfeed.tech/tags/advice.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-strategy](<https://devfeed.tech/tags/ai-strategy.md>), [articles](<https://devfeed.tech/tags/articles.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-generative-ai-it-leadership-it-strategy](<https://devfeed.tech/tags/artificial-intelligence-generative-ai-it-leadership-it-strategy.md>), [calendar](<https://devfeed.tech/tags/calendar.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [cios](<https://devfeed.tech/tags/cios.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [contributor](<https://devfeed.tech/tags/contributor.md>), [control](<https://devfeed.tech/tags/control.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [it-leadership](<https://devfeed.tech/tags/it-leadership.md>), [it-strategy](<https://devfeed.tech/tags/it-strategy.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [models](<https://devfeed.tech/tags/models.md>), [open-weight-ai](<https://devfeed.tech/tags/open-weight-ai.md>), [open-weight-ai-models](<https://devfeed.tech/tags/open-weight-ai-models.md>), [storytype-opinion](<https://devfeed.tech/tags/storytype-opinion.md>)

### AI overview

The author recommends focused experimentation with open-weight models rather than a wholesale enterprise switch. Personal trials with OpenClaw and Ollama led to a Hermes/GLM 5.3 Flash assistant; team trials use Google's Gemma for standup reports, issue triage and log monitoring, locally or in the cloud. The author says these trials help assess task fit and costs, while closed models remain useful in production for compliance coverage, enterprise support and predictable performance. Enterprise agreements can support compliance, but modifying an open-weight model shifts compliance work to the organization, including legal review, audits and documentation; RAG may offer useful customization without modifying the model. The suggested path is to choose a specific use case, run a small team experiment, involve legal and compliance early, document findings and use them to inform strategy. Set explicit boundaries for data access and model actions, and keep the model advisory.

### Source excerpt

For years, enterprise AI strategy has been dependent on a small set of proprietary, closed model providers, a limitation that has carried cost, lock-in and opacity. Now, open-weight models from Meta, Google and other global competitors are challenging that default. As of July 2026, open-weight models accounted for 36% of Vercel's AI Gateway token volume, up from 11% in April, while share of spend more than doubled to 8.6%. Floyd DCosta and Allan Dabre have made compelling cases for greater enterprise control over AI, particularly for strategic and security reasons. I agree, but making the case is easier than moving an organization wholesale to open-weight models. My advice for technology leaders is to stop debating the theory and start experimenting. From personal to team experimentation My hands-on experience with open-weight models started with a mentor recommending OpenClaw, an open-source AI agent designed to be a personal assistant. So, I tried running it with my ChatGPT subscription and burned through my quota so fast I could barely use ChatGPT for development, let alone regular chats. Then I found Ollama, which lets you run open-weight models locally and in the cloud. For the same monthly fee, I got significantly more OpenClaw usage because of the lower token cost. Today, that setup has evolved to Hermes powered by GLM 5.3 Flash on Ollama's cloud offering. This configuration powers a personal assistant that helps manage my calendar, coordinate family logistics and surface relevant articles. If it went away, I wouldn't be doomed, but being able to play with this tool has been unexpectedly useful. My main takeaway from these experiments is that the performance gap between open-weight and frontier models is narrowing faster than many realize. That honestly surprised me. So, I've now expanded my experiment by encouraging my team to use Gemma, an open-weight model from Google that offers enterprise-grade compliance. Gemma runs locally on a MacBook or in the cloud

## Five AI agent harnesses took the same memory test. The results weren't even close.

DevFeed: [Five AI agent harnesses took the same memory test. The results weren't even close.](<https://devfeed.tech/articles/five-ai-agent-harnesses-took-the-same-memory-test-the-results-weren-t-even-close-96194.md>)

Original publisher: [Read original article](<https://thenewstack.io/letta-frontiermemory-agent-harness-benchmark/>)

Author: Amanda Caswell

Published: 2026-10-22T18:34:32Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>)

Tags: [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [agents-sdk](<https://devfeed.tech/tags/agents-sdk.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [claude-managed-agents](<https://devfeed.tech/tags/claude-managed-agents.md>), [claude-opus-5-5](<https://devfeed.tech/tags/claude-opus-5-5.md>), [cost](<https://devfeed.tech/tags/cost.md>), [gemini-4-argon](<https://devfeed.tech/tags/gemini-4-argon.md>), [glm-5-3](<https://devfeed.tech/tags/glm-5-3.md>), [memory](<https://devfeed.tech/tags/memory.md>)

### AI overview

Letta's FrontierMemory benchmark tests whether agents can use memories distilled from earlier successes and failures to improve on later tasks, rather than merely recall facts. In its 15-task evaluation, harness scores ranged from Letta Dream at 73.3% to Hermes Agent at 26.7%; Dream also outscored OpenAI Agents SDK with the same specified GPT models. In memory-generation tests, Claude Opus 5.5 and GLM-5.3 tied at 73.3%, while GPT-6.1 Sol cost less per task ($0.77 versus $2.80 and $3.58, respectively) but scored 60%. The excerpt's pricing-data example illustrates how reusable guidance can transfer across changed tasks, while narrowly stored details or hard-to-find skills may fail. Results are preliminary: there were only 15 tasks and one attempt each, and the benchmark does not yet cover ongoing memory updates.

### Source excerpt

AI agents are getting better at remembering past conversations and earlier tasks but remembering something doesn't guarantee an agent can The post Five AI agent harnesses took the same memory test. The results weren't even close. appeared first on The New Stack.

## My colleague Hermes: an AI agent on a VPS

DevFeed: [My colleague Hermes: an AI agent on a VPS](<https://devfeed.tech/articles/my-colleague-hermes-an-ai-agent-on-a-vps-146828.md>)

Original publisher: [Read original article](<https://blog.ovhcloud.com/en/posts/deploy-ai-agent-vps/>)

Author: Rémy Vandepoel

Published: 2026-10-22T06:00:00Z

Content type: tutorial

Language: en

Sources: [OVHcloud Blog](<https://devfeed.tech/sources/ovhcloud-blog.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [telegram-bot](<https://devfeed.tech/topics/telegram-bot.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [control](<https://devfeed.tech/tags/control.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [hermes-agent](<https://devfeed.tech/tags/hermes-agent.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [minutes](<https://devfeed.tech/tags/minutes.md>), [telegram](<https://devfeed.tech/tags/telegram.md>), [terraform](<https://devfeed.tech/tags/terraform.md>), [vps](<https://devfeed.tech/tags/vps.md>)

### AI overview

The article describes deploying Hermes Agent on an OVHcloud VPS with Terraform and a setup script, then pairing it with Telegram and a chosen model API. Hermes retains skills and conversation history between sessions, supports scheduled tasks, and connects through about 30 messaging platforms; its model can be changed among OpenRouter, OpenAI, Nous Portal, or a custom endpoint. The author says VPS hosting keeps memory, skills, history, and API keys on the user's machine, with an entry-level configuration costing under GBP 5 monthly excluding VAT. Setup requires an OVHcloud account with a default payment method, a Telegram BotFather token, and a model API key. The article recommends limiting access with a contact allowlist, an SSH-only inbound firewall, and scoped tokens. It presents Hermes as useful for diagnostics and confirmed ad hoc actions, while reproducible production changes should remain in version-controlled infrastructure and pipelines.

### Source excerpt

Discover how to host an AI agent on a VPS: use Terraform to deploy Hermes Agent that's contactable on Telegram and under your control, in just ten minutes.

## I'm Using My Hermes AI Agent to Build My Home Lab Inventory in NetBox

DevFeed: [I'm Using My Hermes AI Agent to Build My Home Lab Inventory in NetBox](<https://devfeed.tech/articles/i-m-using-my-hermes-ai-agent-to-build-my-home-lab-inventory-in-netbox-86287.md>)

Original publisher: [Read original article](<https://www.virtualizationhowto.com/2026/10/im-using-my-hermes-ai-agent-to-build-my-home-lab-inventory-in-netbox/>)

Author: Brandon Lee

Published: 2026-10-13T12:39:09Z

Content type: tutorial

Language: en

Sources: [Virtualization Howto](<https://devfeed.tech/sources/virtualization-howto.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Homelab](<https://devfeed.tech/topics/homelab.md>), [NetBox](<https://devfeed.tech/topics/netbox.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [home-lab](<https://devfeed.tech/tags/home-lab.md>), [home-server](<https://devfeed.tech/tags/home-server.md>), [netbox](<https://devfeed.tech/tags/netbox.md>), [virtualization](<https://devfeed.tech/tags/virtualization.md>)

### AI overview

The author describes connecting a Hermes AI agent to NetBox to automate home lab inventory and documentation. The setup uses an isolated network, a separate Linux tools server for network scans, and a NetBox account with an API token. The agent also records Proxmox host changes, virtualization details, and status reports.

### Source excerpt

If you have been following my home lab adventures lately, you will know that I have been playing around with a lot of different technologies and solutions. But as of... The post I'm Using My Hermes AI Agent to Build My Home Lab Inventory in NetBox appeared first on Virtualization Howto.

## 7 Hermes Agent Skills I'd Add to My Home Lab First

DevFeed: [7 Hermes Agent Skills I'd Add to My Home Lab First](<https://devfeed.tech/articles/7-hermes-agent-skills-i-d-add-to-my-home-lab-first-84574.md>)

Original publisher: [Read original article](<https://www.virtualizationhowto.com/2026/10/7-hermes-agent-skills-id-add-to-my-home-lab-first/>)

Author: Brandon Lee

Published: 2026-10-10T12:48:26Z

Content type: article

Language: en

Sources: [Virtualization Howto](<https://devfeed.tech/sources/virtualization-howto.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Homelab](<https://devfeed.tech/topics/homelab.md>), [ecosystem-security](<https://devfeed.tech/topics/ecosystem-security.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [containers](<https://devfeed.tech/tags/containers.md>), [hermes-agent](<https://devfeed.tech/tags/hermes-agent.md>), [home-lab](<https://devfeed.tech/tags/home-lab.md>), [home-server](<https://devfeed.tech/tags/home-server.md>), [virtualization](<https://devfeed.tech/tags/virtualization.md>)

### AI overview

The article recommends seven Hermes Agent skills for home lab use: Technitium DNS, Proxmox, Docker, Uptime Kuma, TrueNAS, Portainer, and an architecture diagram tool. It describes their capabilities and setup, and advises starting with read-only checks and verifying agent results against the underlying systems.

### Source excerpt

After I first setup my Hermes Agent in the home lab I started looking at some of the enhancements that can be made to the effectiveness of the Hermes agent.... The post 7 Hermes Agent Skills I'd Add to My Home Lab First appeared first on Virtualization Howto.

## NetClaw 1.8.0 Adds Protected Hermes Federation and Mobile Access

DevFeed: [NetClaw 1.8.0 Adds Protected Hermes Federation and Mobile Access](<https://devfeed.tech/articles/good-news-for-hermes-users-84595.md>)

Original publisher: [Read original article](<https://automateyournetwork.com/netclaw/good-news-for-hermes-users/>)

Author: John Capobianco

Published: 2026-10-10T12:00:00Z

Content type: release

Language: en

Sources: [Automate Your Network](<https://devfeed.tech/sources/automate-your-network.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [identity and access management](<https://devfeed.tech/topics/identity-and-access-management.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>)

Tags: [1-7](<https://devfeed.tech/tags/1-7.md>), [ai](<https://devfeed.tech/tags/ai.md>), [article](<https://devfeed.tech/tags/article.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [netclaw](<https://devfeed.tech/tags/netclaw.md>), [network-automation](<https://devfeed.tech/tags/network-automation.md>)

### AI overview

NetClaw 1.8.0 combines protected Hermes execution across its federation protocol with mobile access to a Hermes Border. The article describes bounded subnet-calculation delegation, execution ownership, reconnect and cancellation handling, and test evidence, while noting that the implementation had not yet been merged and the mobile app was not publicly released.

### Source excerpt

NetClaw 1.8.0 brings protected Hermes federation and Mobile Ask Border together, following the shared HUD work in 1.7.0. Five diagrams explain the design and its tested boundaries.

## How to organize persistent Pi sessions with ChatGPT tasks and MCP tools

DevFeed: [How to organize persistent Pi sessions with ChatGPT tasks and MCP tools](<https://devfeed.tech/articles/driving-pi-with-computer-using-chatgpt-sessions-82845.md>)

Original publisher: [Read original article](<https://workos.com/blog/chatgpt-pi-agent-workflow>)

Author: WorkOS

Published: 2026-10-09T06:30:00Z

Content type: tutorial

Language: en

Sources: [WorkOS](<https://devfeed.tech/sources/workos-blog.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [context](<https://devfeed.tech/tags/context.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-tools](<https://devfeed.tech/tags/mcp-tools.md>)

### AI overview

The author explains a workflow that pairs ChatGPT tasks with persistent Pi agent-harness sessions for drafting and editing articles. The guide covers MCP tool setup, session and draft identity handoffs, verifying saved changes, using computer control when a connector cannot perform an operation, and keeping review separate from publication.

### Source excerpt

How I use ChatGPT tasks to organize persistent Pi sessions, connect MCP tools, bridge gaps with computer use, and deliver work without losing context.

## Nvidia, Samsung back $90M round for AI agent startup Nous Research

DevFeed: [Nvidia, Samsung back $90M round for AI agent startup Nous Research](<https://devfeed.tech/articles/nvidia-samsung-back-90m-round-for-ai-agent-startup-nous-research-67067.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/07/nvidia-samsung-back-90m-round-for-ai-agent-startup-nous-research/>)

Author: Maria Deutscher

Published: 2026-10-08T00:14:38Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [samsung](<https://devfeed.tech/topics/samsung.md>), [Cloud and systems](<https://devfeed.tech/topics/cloud-and-systems.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [funding](<https://devfeed.tech/tags/funding.md>), [funding-round](<https://devfeed.tech/tags/funding-round.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [hermes-cloud](<https://devfeed.tech/tags/hermes-cloud.md>), [investment](<https://devfeed.tech/tags/investment.md>), [news](<https://devfeed.tech/tags/news.md>), [nous-research](<https://devfeed.tech/tags/nous-research.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [samsung](<https://devfeed.tech/tags/samsung.md>), [startup](<https://devfeed.tech/tags/startup.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>)

### AI overview

Nous Research raised $90 million in a Series B led by Robot Ventures, with Nvidia, Samsung and others participating. The company develops Hermes, an open-source AI agent that can use files, browsers, code and databases, and offers consumer and business services. Nous plans to use the funding to expand adoption of Hermes' business editions.

### Source excerpt

Nous Research Inc., the developer of the popular Hermes artificial intelligence agent, today announced that it has raised $90 million in funding. Early-stage startup fund Robot Ventures led the Series B round. It was joined by Nvidia Corp., Samsung Electronics Co., Y Combinator and several others. Nous is now valued at $1.5 billion. The company [...] The post Nvidia, Samsung back $90M round for AI agent startup Nous Research appeared first on SiliconANGLE.

## Tracing Agent Harness Behavior with NVIDIA NeMo Relay

DevFeed: [Tracing Agent Harness Behavior with NVIDIA NeMo Relay](<https://devfeed.tech/articles/tracing-agent-harness-behavior-with-nvidia-nemo-relay-62870.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/tracing-agent-harness-behavior-with-nvidia-nemo-relay/>)

Author: William Markito Oliveira

Published: 2026-09-30T16:00:00Z

Content type: tutorial

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [tracing](<https://devfeed.tech/topics/tracing.md>)

Tags: [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [build-ai-agents](<https://devfeed.tech/tags/build-ai-agents.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [featured](<https://devfeed.tech/tags/featured.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [llms](<https://devfeed.tech/tags/llms.md>), [nemo](<https://devfeed.tech/tags/nemo.md>), [nemoclaw](<https://devfeed.tech/tags/nemoclaw.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [tracing](<https://devfeed.tech/tags/tracing.md>)

### AI overview

The tutorial uses NVIDIA NeMo Relay to inspect Hermes Agent traces, including model and tool calls, errors, retries, duration, and token use. It shows how to combine trace evidence with task verification to assess agent behavior and harness changes.

### Source excerpt

An agent can finish a task and still take an inefficient path. A failed search can trigger another search. A truncated file read can lead to a command fetching...

## Local Agentic AI Workflows with Hermes + Ollama

DevFeed: [Local Agentic AI Workflows with Hermes + Ollama](<https://devfeed.tech/articles/local-agentic-ai-workflows-with-hermes-ollama-60993.md>)

Original publisher: [Read original article](<https://machinelearningmastery.com/local-agentic-ai-workflows-with-hermes-ollama/>)

Author: Shittu Olumide

Published: 2026-09-28T12:00:25Z

Content type: tutorial

Language: en

Sources: [MachineLearningMastery.com](<https://devfeed.tech/sources/machinelearningmastery-com.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [docker](<https://devfeed.tech/tags/docker.md>), [local](<https://devfeed.tech/tags/local.md>), [open-source](<https://devfeed.tech/tags/open-source.md>)

### AI overview

The tutorial explains how to run Hermes Agent with Ollama as a local model-serving layer, keeping files, code, and conversations on your own hardware. It covers setup, model selection, context-window configuration, and optional Telegram access with a cloud fallback.

### Source excerpt

In this article, you will learn how to build a fully local, zero-cost agentic AI workflow using Hermes Agent and Ollama, so that your files,...

## Setting Up a Personal Assistant in Your Messaging Apps with Hermes and Upstash Box

DevFeed: [Setting Up a Personal Assistant in Your Messaging Apps with Hermes and Upstash Box](<https://devfeed.tech/articles/setting-up-a-personal-assistant-in-your-messaging-apps-with-hermes-and-upstash-box-78690.md>)

Original publisher: [Read original article](<https://upstash.com/blog/personal-assistant-in-messaging-apps-hermes-upstash-box>)

Author: Ali Tarık Şahin

Published: 2026-09-28T00:00:00Z

Content type: tutorial

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Esp Box](<https://devfeed.tech/topics/esp-box.md>), [Messaging](<https://devfeed.tech/topics/messaging.md>), [telegram-bot](<https://devfeed.tech/topics/telegram-bot.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [Discord](<https://devfeed.tech/topics/discord.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Publish-subscribe pattern](<https://devfeed.tech/topics/pubsub.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [box](<https://devfeed.tech/tags/box.md>), [discord](<https://devfeed.tech/tags/discord.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [nous-research](<https://devfeed.tech/tags/nous-research.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [slack](<https://devfeed.tech/tags/slack.md>), [telegram](<https://devfeed.tech/tags/telegram.md>), [whatsapp](<https://devfeed.tech/tags/whatsapp.md>)

### AI overview

This tutorial shows how to run the open-source Hermes assistant on an always-on Upstash Box and connect it to WhatsApp. It covers setup, account pairing, allowlists, and restarting the gateway after a crash; other messaging platforms use a similar flow.

### Source excerpt

Hermes is an open-source agent from Nous Research that you can talk to from WhatsApp, Telegram, Slack, Discord and more. This post runs it on an Upstash Box so it stays online, then walks through connecting WhatsApp as an example. Every other messaging app follows the same flow.

## New Carbonato malware uses AI agents to hijack exposed Docker hosts

DevFeed: [New Carbonato malware uses AI agents to hijack exposed Docker hosts](<https://devfeed.tech/articles/new-carbonato-malware-uses-ai-agents-to-hijack-exposed-docker-hosts-59600.md>)

Original publisher: [Read original article](<https://www.bleepingcomputer.com/news/security/new-carbonato-malware-uses-ai-agents-to-hijack-exposed-docker-hosts/>)

Author: Bill Toulas

Published: 2026-09-24T20:10:48Z

Content type: news

Language: en

Sources: [BleepingComputer](<https://devfeed.tech/sources/bleepingcomputer.md>)

Topics: [Malware](<https://devfeed.tech/topics/malware.md>), [Docker](<https://devfeed.tech/topics/docker.md>), [Cybersecurity](<https://devfeed.tech/topics/cybersecurity.md>), [Cybercrime](<https://devfeed.tech/topics/cybercrime.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [C2](<https://devfeed.tech/topics/c2.md>), [OpenSSH](<https://devfeed.tech/topics/openssh.md>), [Server](<https://devfeed.tech/topics/server.md>), [systemd](<https://devfeed.tech/topics/systemd.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [botnet](<https://devfeed.tech/tags/botnet.md>), [carbonato](<https://devfeed.tech/tags/carbonato.md>), [computer-help](<https://devfeed.tech/tags/computer-help.md>), [computer-security](<https://devfeed.tech/tags/computer-security.md>), [computers](<https://devfeed.tech/tags/computers.md>), [cyber](<https://devfeed.tech/tags/cyber.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [docker](<https://devfeed.tech/tags/docker.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [hermes-agent](<https://devfeed.tech/tags/hermes-agent.md>), [infosec](<https://devfeed.tech/tags/infosec.md>), [infosec-computer-security](<https://devfeed.tech/tags/infosec-computer-security.md>), [linux](<https://devfeed.tech/tags/linux.md>), [mac](<https://devfeed.tech/tags/mac.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-removal](<https://devfeed.tech/tags/malware-removal.md>), [security](<https://devfeed.tech/tags/security.md>), [spyware](<https://devfeed.tech/tags/spyware.md>), [support](<https://devfeed.tech/tags/support.md>), [tech-support](<https://devfeed.tech/tags/tech-support.md>), [technical-support](<https://devfeed.tech/tags/technical-support.md>), [virus](<https://devfeed.tech/tags/virus.md>), [virus-removal](<https://devfeed.tech/tags/virus-removal.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

BleepingComputer reports that the Carbonato botnet is compromising Docker hosts with unauthenticated APIs. It launches privileged containers, installs Hermes Agent for operator-directed commands, establishes persistence, collects credentials and API keys, and scans for additional exposed Docker daemons.

### Source excerpt

A new botnet malware called Carbonato is targeting insecure hosts running Docker daemons to install the Hermes Agent AI framework and take control. [...]

## Sending SMS with an Agentic AI using Twilio and Hermes Agent

DevFeed: [Sending SMS with an Agentic AI using Twilio and Hermes Agent](<https://devfeed.tech/articles/sending-sms-with-an-agentic-ai-using-twilio-and-hermes-agent-57767.md>)

Original publisher: [Read original article](<https://www.twilio.com/en-us/blog/developers/tutorials/integrations/sending-sms-agentic-ai-using-twilio-hermes-agent>)

Author: Amanda Lange

Published: 2026-09-21T00:00:00Z

Content type: tutorial

Language: en

Sources: [Twilio](<https://devfeed.tech/sources/twilio-blog.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [command-line](<https://devfeed.tech/tags/command-line.md>), [developer-insights](<https://devfeed.tech/tags/developer-insights.md>), [hermes-agent](<https://devfeed.tech/tags/hermes-agent.md>), [homebrew](<https://devfeed.tech/tags/homebrew.md>), [mac-mini](<https://devfeed.tech/tags/mac-mini.md>), [python](<https://devfeed.tech/tags/python.md>), [sms](<https://devfeed.tech/tags/sms.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>), [twilio](<https://devfeed.tech/tags/twilio.md>)

### AI overview

This tutorial and process review describes building an AI agent that can be contacted through Twilio SMS. It uses Hermes Agent on a dedicated Mac Mini, with Homebrew and ngrok installed through the command line, and discusses the setup prerequisites and installation steps.

### Source excerpt

Sending SMS with an Agentic AI using Twilio and Hermes Agent - a tutorial and review of process

## A sandbox doesn't constrain an API Key: What Polsia learned running autonomous companies on Render

DevFeed: [A sandbox doesn't constrain an API Key: What Polsia learned running autonomous companies on Render](<https://devfeed.tech/articles/a-sandbox-doesn-t-constrain-an-api-key-what-polsia-learned-running-autonomous-companies-on-render-81848.md>)

Original publisher: [Read original article](<https://render.com/blog/a-sandbox-doesn-t-constrain-an-api-key-what-polsia-learned-running-autonomous-companies-on>)

Author: The email key had more authority than the agent needed

Published: 2026-07-23T13:00:00Z

Content type: article

Language: en

Sources: [Render](<https://devfeed.tech/sources/render.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [agent-sdk](<https://devfeed.tech/tags/agent-sdk.md>), [agents](<https://devfeed.tech/tags/agents.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [github](<https://devfeed.tech/tags/github.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>)

### AI overview

Polsia founder Ben Broca describes production lessons from running autonomous AI agents that build and operate businesses. The article covers provisioning sandboxes, limiting API credentials, turning deployment and other workflow steps into explicit checkpoints, choosing models based on task cost, and maintaining standardized infrastructure.

### Source excerpt

Learn how Polsia runs autonomous AI companies on Render, why sandboxes don't limit API key permissions, and the guardrails production agents need.

## How to Use Hermes Agent with OpenRouter: Setup, Models & Routing

DevFeed: [How to Use Hermes Agent with OpenRouter: Setup, Models & Routing](<https://devfeed.tech/articles/how-to-use-hermes-agent-with-openrouter-setup-models-routing-78645.md>)

Original publisher: [Read original article](<https://openrouter.ai/blog/tutorials/hermes-agent/>)

Author: OpenRouter

Published: 2026-06-12T16:00:00Z

Content type: tutorial

Language: en

Sources: [OpenRouter](<https://devfeed.tech/sources/openrouter.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [litellm](<https://devfeed.tech/topics/litellm.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-pricing](<https://devfeed.tech/tags/ai-pricing.md>), [api](<https://devfeed.tech/tags/api.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [automation](<https://devfeed.tech/tags/automation.md>), [catalog](<https://devfeed.tech/tags/catalog.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [model](<https://devfeed.tech/tags/model.md>), [openrouter](<https://devfeed.tech/tags/openrouter.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [routing](<https://devfeed.tech/tags/routing.md>), [setup](<https://devfeed.tech/tags/setup.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

### AI overview

This tutorial explains how to connect the Hermes Agent terminal application to OpenRouter, choose models that meet its stated 64K context requirement, and configure provider routing, fallbacks, and auxiliary models. It also describes cost controls for coding tasks and how to monitor usage and troubleshoot setup problems.

### Source excerpt

Hermes Agent has pushed over 17 trillion tokens through OpenRouter. Here's how to set it up, pick a model that clears the 64K context bar, and tune routing for cost and reliability.

## Using Hermes Profiles for Family Home Automation via WhatsApp

DevFeed: [Using Hermes Profiles for Family Home Automation via WhatsApp](<https://devfeed.tech/articles/hermes-profiles-are-perfect-for-family-home-automation-38376.md>)

Original publisher: [Read original article](<https://meedamian.com/post/hermes-profiles-family-home-automation/>)

Author: hi@meedamian.com (Damian Mee)

Published: 2026-05-26T00:00:00Z

Content type: tutorial

Language: en

Sources: [Damian Mee | Blog | Portfolio | About](<https://devfeed.tech/sources/damian-mee-blog-portfolio-about.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [hermes-agent](<https://devfeed.tech/tags/hermes-agent.md>), [home-automation](<https://devfeed.tech/tags/home-automation.md>), [whatsapp](<https://devfeed.tech/tags/whatsapp.md>)

### AI overview

A tutorial on setting up a restricted Hermes profile that lets a family member control home devices through WhatsApp. It covers isolating the profile from higher-risk tools, avoiding WhatsApp bridge conflicts, and providing model credentials.

### Source excerpt

Disclosure: GPT-5.5 wrote the original long version. Grok 4.3 rewrote it into the current shorter form. Both models were running inside Hermes Agent -- the harness, profile system, tool layer, gateway, and memory that actually does the work. The setup is real. The mistakes were real. The OAuth tokens were dramatic. The profile name was changed to protect the guilty. I wanted my mom to have a tiny AI that could control the house from WhatsApp.