Find good eBay deals on a schedule
TL;DR. Task: TL;DR Hermes is a local-first agent framework from Nous Research that creates and refines skills as it works. It uses persistent memory to remember user preferences and past conversations between sessions, getting sharper with use. Firecrawl is the default web provider, giving the agent search and crawl tools out of the box. A June 2026 update made web reading up to 60x faster and 49x cheaper by dropping a redundant summarization step and passing clean backend markdown straight to the agent. The new /learn command turns a directory, doc URL, past conversation, or pasted notes into a reusable skill without hand-writing a SKILL.md file. The Hermes agent from Nous Research addresses the biggest limitation of most AI agent frameworks: they're stateless. Every session starts from a blank slate, so you repeat context and the agent never learns anything about you or the tasks you assign it. Hermes takes the opposite approach. It runs on your own machine, remembers what worked in past sessions, and turns finished tasks into reusable skills it can pull up again later. What is Hermes agent? Hermes agent is an open-source framework from Nous Research, the lab behind the Hermes and Nomos model families. The piece that sets it apart from other agent runtimes is the learning loop. When Hermes finishes a complex task, it writes a new "skill" to disk and reuses that skill the next time a similar task comes up. This learning cycle is built on a flexible architecture. The agent itself can live anywhere you can run a script. It supports six terminal backends including local execution, Docker, SSH, and serverless platforms like Daytona and Modal. That means you can chat with an agent from a messaging app like Telegram while it works on a remote cloud VM you never log into directly. The framework is also model-agnostic. You can switch between providers like Nous Portal, OpenRouter, OpenAI, and Anthropic, or connect to a local model through Ollama, by running the hermes model command. Pick the model that fits your budget and task, and swap it out later with one command. For web access, Hermes uses a pluggable backend system. Firecrawl is the default, and the framework auto-detects which provider to use from your API keys. Tavily, Exa, and Parallel are also supported. Firecrawl is the only one of the four that covers search, scraping, and multi-page crawling in a single backend. What makes Hermes agent different? The core of the agent's persistence is a pair of markdown files. Hermes stores its own notes and summaries in MEMORY.md, a 2,200-character file, and builds a profile of your preferences in USER.md, a 1,375-character file. Both are injected into the system prompt at the start of every session. For longer-term recall, the agent uses FTS5 full-text search to query all past conversations and can connect to eight external memory providers like Honcho or Mem0. When the agent finishes a task that used five or more tool calls, it writes a new "skill" on its own. A skill is a portable knowledge document, compatible with the agentskills.io open standard, that the agent can pull up again the next time a similar task lands. For a full breakdown of how agent skills work — including SKILL.md structure, cross-platform compatibility, and how to build or install your own — see the dedicated guide. You don't have to wait for the agent to write skills on its own, either. A June 2026 update added the /learn command, which authors a skill from source material you point it at: a local directory, a documentation URL, a past conversation, or pasted notes. The agent gathers the material with its own tools, reading local files with read_file and search_files or fetching online docs through its web backend, then writes a standards-compliant SKILL.md for you with no hand-authoring. When you point /learn at a doc URL, Firecrawl is what fetches and cleans the page before the agent distills it into a skill. Because there's no separate ingestion engine, /learn behaves the same across the CLI, TUI, messaging gateway, and dashboard, and every skill it saves becomes a slash command you can call later. Skills can also be shared or installed from hubs like ClawHub and the official Skills Hub. Out of the box, Hermes agent ships with 47 built-in tools. The built-in set covers web search, terminal execution, file editing, and memory management. For bigger jobs, it can delegate work by spawning up to three isolated subagents in parallel.; tools: Hermes Agent. Human role: The original post does not say how a person stayed involved.; limitations: Prerequisites include a local Hermes installation, Firecrawl API key (or free tier), and eBay access. Operating costs depend on model API usage and Firecrawl credits. The agent's stateless nature is addressed by persistent memory, but skill creation requires sufficient tool calls or manual /learn triggers. Human approval is mandatory for financial transactions..
Tools
Published on Agent Work Atlas:
Overview
TL;DR
Workflow
TL;DR Hermes is a local-first agent framework from Nous Research that creates and refines skills as it works. It uses persistent memory to remember user preferences and past conversations between sessions, getting sharper with use. Firecrawl is the default web provider, giving the agent search and crawl tools out of the box. A June 2026 update made web reading up to 60x faster and 49x cheaper by dropping a redundant summarization step and passing clean backend markdown straight to the agent. The new /learn command turns a directory, doc URL, past conversation, or pasted notes into a reusable skill without hand-writing a SKILL.md file. The Hermes agent from Nous Research addresses the biggest limitation of most AI agent frameworks: they're stateless. Every session starts from a blank slate, so you repeat context and the agent never learns anything about you or the tasks you assign it. Hermes takes the opposite approach. It runs on your own machine, remembers what worked in past sessions, and turns finished tasks into reusable skills it can pull up again later. What is Hermes agent? Hermes agent is an open-source framework from Nous Research, the lab behind the Hermes and Nomos model families. The piece that sets it apart from other agent runtimes is the learning loop. When Hermes finishes a complex task, it writes a new "skill" to disk and reuses that skill the next time a similar task comes up. This learning cycle is built on a flexible architecture. The agent itself can live anywhere you can run a script. It supports six terminal backends including local execution, Docker, SSH, and serverless platforms like Daytona and Modal. That means you can chat with an agent from a messaging app like Telegram while it works on a remote cloud VM you never log into directly. The framework is also model-agnostic. You can switch between providers like Nous Portal, OpenRouter, OpenAI, and Anthropic, or connect to a local model through Ollama, by running the hermes model command. Pick the model that fits your budget and task, and swap it out later with one command. For web access, Hermes uses a pluggable backend system. Firecrawl is the default, and the framework auto-detects which provider to use from your API keys. Tavily, Exa, and Parallel are also supported. Firecrawl is the only one of the four that covers search, scraping, and multi-page crawling in a single backend. What makes Hermes agent different? The core of the agent's persistence is a pair of markdown files. Hermes stores its own notes and summaries in MEMORY.md, a 2,200-character file, and builds a profile of your preferences in USER.md, a 1,375-character file. Both are injected into the system prompt at the start of every session. For longer-term recall, the agent uses FTS5 full-text search to query all past conversations and can connect to eight external memory providers like Honcho or Mem0. When the agent finishes a task that used five or more tool calls, it writes a new "skill" on its own. A skill is a portable knowledge document, compatible with the agentskills.io open standard, that the agent can pull up again the next time a similar task lands. For a full breakdown of how agent skills work — including SKILL.md structure, cross-platform compatibility, and how to build or install your own — see the dedicated guide. You don't have to wait for the agent to write skills on its own, either. A June 2026 update added the /learn command, which authors a skill from source material you point it at: a local directory, a documentation URL, a past conversation, or pasted notes. The agent gathers the material with its own tools, reading local files with read_file and search_files or fetching online docs through its web backend, then writes a standards-compliant SKILL.md for you with no hand-authoring. When you point /learn at a doc URL, Firecrawl is what fetches and cleans the page before the agent distills it into a skill. Because there's no separate ingestion engine, /learn behaves the same across the CLI, TUI, messaging gateway, and dashboard, and every skill it saves becomes a slash command you can call later. Skills can also be shared or installed from hubs like ClawHub and the official Skills Hub. Out of the box, Hermes agent ships with 47 built-in tools. The built-in set covers web search, terminal execution, file editing, and memory management. For bigger jobs, it can delegate work by spawning up to three isolated subagents in parallel.
Reported result
The source reports a 60x speedup and 49x cost reduction in web extraction for documentation pages, but provides no specific metrics for eBay deal finding. Actual business impact on deal acquisition rates is unknown. Proposed acceptance check: Measure the time saved per week on manual searching and the accuracy of deal alerts against a baseline of 100 manually verified listings.
Human role
The original post does not say how a person stayed involved.
Limitations
Prerequisites include a local Hermes installation, Firecrawl API key (or free tier), and eBay access. Operating costs depend on model API usage and Firecrawl credits. The agent's stateless nature is addressed by persistent memory, but skill creation requires sufficient tool calls or manual /learn triggers. Human approval is mandatory for financial transactions.
Try it
I want to set up a scheduled eBay deal finder using Hermes Agent and Firecrawl. First, install Hermes and configure Firecrawl as the web backend. Use the /learn command to create a skill from my saved eBay search criteria and past successful purchases. Set up a cron job to run the search every 6 hours. The agent should scrape listings, compare prices against my criteria, and save potential deals to a local file. Do not make any purchases. After the first run, show me the top 5 deals found and ask for my confirmation before adjusting the search parameters or sending alerts. If Firecrawl fails, fallback to manual search instructions. Ensure all outputs are saved in ~/.hermes/deals/ for my review.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.