LIVE TAPE
OpenClaw 88,412 stars·CVE-2026-25898 disclosed (HIGH, Hermes)·Hermes Agent v2026.4.7 published·Hermes Agent +182 stars (last hour)·OpenClaw v2026.4.6 — credential vault hardening·CVE-2026-26133 patched (NanoClaw)·Pi 5 16GB rumoured for Q3 — recheck guidance·Nanobot +47 stars (last hour)·ZeroClaw v0.4.2 — Apple container fixes·Mac Mini M4 wins quarterly hardware survey·OpenClaw 88,412 stars·CVE-2026-25898 disclosed (HIGH, Hermes)·Hermes Agent v2026.4.7 published·Hermes Agent +182 stars (last hour)·OpenClaw v2026.4.6 — credential vault hardening·CVE-2026-26133 patched (NanoClaw)·Pi 5 16GB rumoured for Q3 — recheck guidance·Nanobot +47 stars (last hour)·ZeroClaw v0.4.2 — Apple container fixes·Mac Mini M4 wins quarterly hardware survey·
PocketClawvol. 1 · 2026

Inbox triage

Self-hosted agent reads incoming email, classifies, drafts replies, flags actions. Saves 30-60 minutes a day.

The problem

Email volume past ~50 messages/day exceeds what most people can triage well. Hosted services like Superhuman or HEY work but ship your inbox to a third party. Self-hosted lets you keep the data while still gaining the leverage.

Recommended setup

AgentHermes Agent
HardwareRaspberry Pi 5 (8 GB) or Hetzner CX22 (€5/month)
LLMClaude 4.5 Sonnet via Anthropic API (or OpenRouter)

How it works

Hermes Agent connects to your IMAP/JMAP inbox via a custom MCP tool. The tool fetches headers + first 500 characters of new mail, the agent classifies (action / reply / archive / spam) and either replies (drafts saved to drafts folder, never auto-sent) or files. Approval flow on every send.

Reality check

After three months of running this on my own inbox: 80% classification accuracy on routine mail, ~30 false positives per month I had to correct. Time saved: 4-5 hours per week. Anthropic API cost: ~€18 per month for ~3,000 messages classified. Cheaper than Superhuman, less polished UI, but the data stays on my hardware.

What breaks

  • Long, threaded conversations (agent loses context past ~10 turns)
  • Highly contextual replies that need knowledge from outside the email itself
  • Anything legal, financial or relationship-sensitive (always reply yourself)

Alternative setups

Nanobot + custom IMAP tool if you want to read every line of code that touches your inbox. ZeroClaw + local Mistral 7B if you can tolerate ~62% classification accuracy in exchange for cloud-free operation.

Other use cases
€0 if you already have the hardware. €5-30/month LLM if calling cloud.
Pre-PR code review
Agent reviews your PRs locally before you push, catches obvious bugs, flags security issues, suggest…
€0 if local-only. €0-10/month embedding API if you go cloud.
Document RAG over personal notes
Agent searches your notes, documents, codebases via vector embeddings. Answers questions with refere…
€38/month VPS + €30-100/month LLM (varies with volume)
First-line customer support
Self-hosted agent answers tier-1 customer questions from your docs/knowledge base. Hands off to huma…
€5/month Pi 5 power + €5-15/month LLM (light usage)
Security monitoring & alert triage
Agent watches your security feeds (CVE alerts, GitHub advisories, log anomalies), summarises and pri…