Run a 24/7 local agent that curates news digests
Web page · https://agentusecases.ai/use-case/run-a-24-7-local-agent-that-curates-news-digests
Done with Hermes Agent. The author runs Hermes Agent on a Proxmox VM with a local Qwen model, monitoring RSS feeds, curating news digests, and reporting via Telegram.
First seen by Oriel on .
AI summary
This use case describes Hermes Agent running continuously on local infrastructure to curate RSS news digests and deliver trend-aware briefings through Telegram.
- Hermes Agent runs on a 4-vCPU, 8 GB RAM Proxmox VM without a GPU, calling a Qwen 3.6 MoE llama-server on an RTX 5060 Ti.
- A single Telegram request created a daily 8 AM cron job that combines RSS and MCP data, checks memory, and posts briefings to Telegram topics.
- The system also produces a 9 AM startup and VC digest without API costs, while its memory accumulates into trend-aware reports over weeks.
- The author reports no formal quality measurements, and found the fast MoE model about three times faster than the dense 27B model.
- The recommended prompt specifies feeds, schedule, topic relevance, duplicate and clickbait filtering, digest format, delivery channel, and an immediate test.
#hermes agent #rss #local ai #telegram
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| Agent Use Cases | https://agentusecases.ai/use-case/run-a-24-7-local-agent-that-curates-news-digests | https://agentusecases.ai/use-case/run-a-24-7-local-agent-that-curates-news-digests Read discussion |