hermes verify: One Command That Answers 'Does This Project Actually Run?'
Hermes Agent's new hermes verify subcommand auto-detects your project type (Node/Python/Go/Rust/Java/Make/docker-compose), runs bootstrap → build → test → start → readiness poll, and returns a structured pass/fail verdict. It can also save the detected recipe to .hermes/environment.json for reproducible checks. Full flags and real usage included.
Read more
10 Hidden Hermes Tricks Even Veteran Users May Not Know: From /goal to Pets to an API Server
From /goal persistent objectives, hermes import-agent one-command migration, and journey memory starmaps to insights usage analytics, proxy API server, desktop pets, skins, external memory, skill sync, and the iron-proxy egress firewall — 10 Hermes Agent hidden gems, every one verified on a live install.
Read more
Hands-Free Hermes: /heartbeat, /refine, and /goal Gates for Self-Driving Agents
Three new commands merged into Hermes Agent main on 2026-08-06: /heartbeat session heartbeats, /refine on-demand self-improvement reviews, and /goal gate deterministic quality gates. Real CLI examples show how to combine them into a hands-free, self-driving workflow — and where the boundaries with cron and Completion Contracts sit.
Read more
Give Hermes Agent a Semantic Memory with LanceDB: Install, Configure, Benchmark
Hermes' built-in memory matches keywords, so paraphrases miss. LanceDB's official memory plugin adds vector recall + hybrid retrieval: LongMemEval accuracy 0.661 vs 0.533 for the built-in FTS5 baseline. Full install, config, the four memory tools, and a careful reading of the benchmark numbers.
Read more
Stop Paying for Silence: Cloud STT Silence Trim & Local Whisper Idle Unload in Hermes Agent
Voice messages are the most natural way to talk to Hermes Agent — but with cloud STT, every pause in your voice note costs money and invites hallucinated transcript junk. Two new features fix both sides: pre-upload silence trim for cloud providers (measured 13.2s → 6.2s, -53%, identical transcript) and idle unload for the local Whisper model (frees ~370MB of RAM/VRAM, transparently reloads on the next message). This post covers the real config, the honest memory numbers for GPU vs CPU, when to disable the trim, and recommended settings per use case.
Read more
Hermes Desktop Closes the Loop: In-App Browser Lands and the Agent Can Finally Read the Page It Opened
Hermes Agent merged two updates back-to-back: the in-app browser and preview rail became real layout-tree tabs, and a new read_preview tool lets the agent read the visible text of the current page. From open_preview to read_preview, the desktop open-then-read loop is complete.
Read more
Hermes v0.20.0 Herald Deep Dive: Conversational Voice, Wake Words, Grounded Citations, and A2A
Hermes Agent v0.20.0 (Herald) is here: talk to Hermes with barge-in voice, hands-free wake words, voice on every platform, source-backed research with citations, A2A agent interoperability, desktop Artifacts, outbound webhooks, and a wave of CLI power commands.
Read more
Wire Up Hermes Webhooks: Let Your Business Systems Push Alerts to Telegram, Discord, and Slack
Polling wastes API quota and adds latency. Hermes Agent's webhook platform turns order, payment, monitoring, and CI/CD events into instant chat notifications, with Direct Delivery mode for sub-second, zero-token pushes.
Read more
Hermes Smart Approvals: Stop Nodding at Every Step
Approval fatigue is real — every flagged command stops your flow. Hermes v0.19's smart approvals have an LLM review each command, auto-approve the safe ones, auto-deny the dangerous ones, and only escalate the uncertain. Here's how it works and how to keep hard red lines.
Read more
Hermes Agent v0.19.1: The 'Patch' That Touched 4,700 Files and Rebuilt the Voice Stack
v0.19.1 is no ordinary patch. We unpack the official release notes and source commits behind the 4,700-file voice subsystem salvage: full-duplex barge-in, rolling-window VAD, stop-phrase semantics, container repair, and wake-word readiness, with copy-paste config and debugging tips.
Read more
Turn Hermes Conversations into Obsidian Notes Automatically
Stop losing insights inside chat sessions. Wire Hermes Agent's persistent memory, session recall, skills, and cron jobs into an Obsidian vault so your knowledge base updates itself.
Read more
Hermes Agent Now Integrates with Buzz: Three Ways for Humans and Agents to Share One Workspace
Buzz is Block's Nostr-based workspace where humans and AI agents coexist in the same channels. Learn the three Hermes integration paths — Desktop runtime, relay bridge, and native gateway — and pick the right one for your setup.
Read more
Mastering Hermes Automation with Cron Jobs: From Daily Briefings to Custom Watchers
Hermes Agent cron is more than a scheduler — it is a complete automation framework. This guide covers natural-language scheduling, skill-backed jobs, multi-job chains with context_from, no-agent script watchers, and production deployment patterns with real CLI examples.
Read more
Stop Stuffing API Keys into .env: 5 Steps to Wire Hermes v0.19's New External Secret Vault
Hermes Agent v0.19.0 ships a pluggable SecretSource layer that reads API keys from Bitwarden Secrets Manager and 1Password at startup. This post gives a 5-step migration that keeps a working rollback path.
Read more
Hermes Agent Gets a Storage Diet: How the v23 FTS Layout Cuts state.db by Up to 78%
Hermes Agent's new compact v23 FTS layout removes duplicate search-index copies and stops indexing tool output for CJK trigrams. Existing users can opt in with hermes sessions optimize-storage; fresh installs get it for free.
Read more
Hermes v0.19 Smart Approvals: Set Up 3 Security Gates Step by Step, with Commands
Hermes Agent v0.19 enables Smart Approvals by default. This article turns LLM-powered auto-approval into a security flow you control with three concrete gates — LLM pre-review, hard red lines (approvals.deny), and human decision-making. Every config key is verified against the v0.19 source code and official docs, with full config and CLI commands.
Read more