https://blog.lynxflow.co/en/tags/hermes/Recent content in Hermes on Lynx Tech BlogHugo -- gohugo.ioenSun, 13 Sep 2026 16:15:00 +0800https://blog.lynxflow.co/en/posts/hermes-claude-code-control-routes-2026/Sun, 13 Sep 2026 16:15:00 +0800https://blog.lynxflow.co/en/posts/hermes-claude-code-control-routes-2026/<img src="https://blog.lynxflow.co/images/hermes-cc-control-routes-cover.png" alt="Featured image of post The Complete Technical Routes for Hermes to Control Claude Code: From Terminal Invocation to Agent Interoperability Protocols" />One-Sentence Summary Hermes (a Telegram bot gateway) controlling Claude Code (Anthropic&rsquo;s CLI coding agent) has 7 technical routes: direct terminal invocation, SDK programmatic API, MCP bidirectional communication, A2A Agent-to-Agent protocol, ACP Agent Communication protocol, Hooks system, and Cloud sessions. Hermes already has codex_app_server and copilot_acp subprocess runtime templates — adding a Claude Code runtime is essentially copying an existing pattern. For Telegram bot scenarioshttps://blog.lynxflow.co/en/posts/2026-08-23-workflow-control-plane-selection/Sun, 23 Aug 2026 00:00:00 +0800https://blog.lynxflow.co/en/posts/2026-08-23-workflow-control-plane-selection/<img src="https://blog.lynxflow.co/images/2026-08-23-control-plane-architecture-cover.png" alt="Featured image of post Installing a Control Plane for 'Script + Cron + Agent' Black-Box Automation: A Survey of 12 Platforms" /> TL;DR: What I need isn&rsquo;t another orchestration tool, but a Control Plane—a coordination layer that answers in one place: which workflow, which version, which run, which step failed, how many retries, when&rsquo;s the next run. cron only knows how to &ldquo;knock on time&rdquo; and then walks away. After surveying 11 platforms, my pick: Windmill first choice, Kestra co-selected; n8n/Temporal/Argo explicitly rejected; Hermes demoted to &ldquo;scheduled agent&rdquo; instead of scheduler.https://blog.lynxflow.co/en/posts/hermes-openclaw-setup-guide/Sat, 08 Aug 2026 00:00:00 +0800https://blog.lynxflow.co/en/posts/hermes-openclaw-setup-guide/<img src="https://blog.lynxflow.co/images/hermes-vs-openclaw.png?v=090818" alt="Featured image of post Hermes + OpenClaw Beginner Deployment and Configuration Guide (2026)" /> This guide ties together five hands-on Hermes / OpenClaw articles on this site into one complete path: which one to choose → how to install it → how to configure models → how to use skills. Every command was verified against real running instances on 2026-07-31—not padded out by copying official docs. Both projects move fast, so you should re-check the official documentation before you start. 0. What are these two for? Hermes and OpenClaw are both open-source, self-hostable AI agent frameworks.https://blog.lynxflow.co/en/posts/changelog-digest-2026-8/Sat, 01 Aug 2026 00:00:00 +0800https://blog.lynxflow.co/en/posts/changelog-digest-2026-8/<img src="https://blog.lynxflow.co/images/changelog-digest-2026-8.png" alt="Featured image of post Hermes & OpenClaw: Release Digest, 2026-08" />This digest tracks 2026-08 releases of the two self-hosted agent harnesses — OpenClaw (2) and Hermes (0). Listed in reverse chronological order; full notes at each release link. OpenClaw v2026.7.2-beta.7 — 2026-08-02 2026.7.2 Highlights State safety and recovery: protect persisted data with a quarantine store that survives primary-database damage, crash-recoverable SQLite snapshots, crash-durable filesystem publication, schema-upgrade data-loss rejection, and rollback-writer snapshot recovery. (https://blog.lynxflow.co/en/posts/changelog-digest-july-2026/Fri, 31 Jul 2026 00:00:00 +0800https://blog.lynxflow.co/en/posts/changelog-digest-july-2026/<img src="https://blog.lynxflow.co/images/changelog-digest-july-2026.png" alt="Featured image of post Hermes & OpenClaw: changelog digest, July 2026" />This digest rounds up recent changes in the two open-source self-hosted agent harnesses AgentHub tracks — OpenClaw and Hermes — as of late July 2026. It&rsquo;s distilled from each project&rsquo;s own changelog and commit history (see sources); every entry below is traceable to a real release note or commit. OpenClaw — 2026.6.8 The installed CLI reports OpenClaw 2026.6.8 (844f405). The 2026.6.8 release is broad; the highlights: Channels. Telegram delivery got structured rich text — tables, listshttps://blog.lynxflow.co/en/posts/skills-portability-hermes-openclaw/Fri, 31 Jul 2026 00:00:00 +0800https://blog.lynxflow.co/en/posts/skills-portability-hermes-openclaw/<img src="https://blog.lynxflow.co/images/skills-portability-hermes-openclaw.png" alt="Featured image of post Hermes Skills vs OpenClaw Skills: Do They Port?" />The short answer: yes, they port A skill you install on Hermes will install — byte-identical — on OpenClaw, and vice versa. Both harnesses speak the standard agent-skill format (SKILL.md with YAML frontmatter + supporting examples/, references/, scripts/, templates/ dirs), and both pull from the same registries. Verified 2026-07-31: the skill agent-self-evaluation (among many others) is installed identically on both — same SKILL.md (7625 bytes, identical content), same directory layout — on thishttps://blog.lynxflow.co/en/posts/hermes-vs-openclaw/Fri, 31 Jul 2026 00:00:00 +0800https://blog.lynxflow.co/en/posts/hermes-vs-openclaw/<img src="https://blog.lynxflow.co/images/hermes-vs-openclaw.png?v=090818" alt="Featured image of post Hermes vs OpenClaw: Which Self-Hosted AI Agent Harness in 2026" />The two rising self-hosted agent harnesses Hermes and OpenClaw are two open-source, self-hostable AI agent harnesses attracting growing attention in 2026. Both let you run an agent that talks to humans across messaging channels, calls tools, and maintains state — but they differ in language, philosophy, and ecosystem. Dimension Hermes OpenClaw Repo NousResearch/hermes-agent openclaw/openclaw Version (2026-07-31) 0.16.0 2026.7.1-2 Language Python Node.js / TypeScript License MIT MIT One-liner Thehttps://blog.lynxflow.co/en/posts/install-hermes-wsl2/Fri, 31 Jul 2026 00:00:00 +0800https://blog.lynxflow.co/en/posts/install-hermes-wsl2/<img src="https://blog.lynxflow.co/images/install-hermes-wsl2.png?v=090500" alt="Featured image of post How to Install Hermes Agent on WSL2 (2026)" />Hermes is a self-hosted, self-improving AI agent (Python, MIT). On WSL2 it installs the same way as on Linux — the official installer lands under ~/.hermes. This guide was verified against a live WSL2 instance running Hermes v0.16.0. 1. Install (official one-liner) 1 curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash The installer handles its own dependencies: uv, Python 3.11, Node.js, ripgrep, and ffmpeg. On WSL2 it detects your existing Git and uses it (no bundled Git needed).https://blog.lynxflow.co/en/posts/model-provider-setup/Fri, 31 Jul 2026 00:00:00 +0800https://blog.lynxflow.co/en/posts/model-provider-setup/<img src="https://blog.lynxflow.co/images/model-provider-setup.png" alt="Featured image of post Model Provider Setup: Hermes + OpenClaw (2026)" />A self-hosted agent is useless until it can reach a model. Both Hermes and OpenClaw let you pick an inference provider interactively and store it in a local config file — with secrets in environment variables, never in the file. This guide covers the official commands and config structure (verified 2026-07-31); no live keys are shown. Hermes — hermes model Hermes ships an interactive provider picker: 1 hermes model It lists providers, fetches each one&rsquo;s live /v1/models list, and lets you chttps://blog.lynxflow.co/en/posts/self-hosted-agent-landscape-2026/Fri, 31 Jul 2026 00:00:00 +0800https://blog.lynxflow.co/en/posts/self-hosted-agent-landscape-2026/<img src="https://blog.lynxflow.co/images/self-hosted-agent-landscape-2026.png" alt="Featured image of post Self-Hosted AI Agent Landscape 2026" />Two categories that get conflated &ldquo;AI agent&rdquo; in 2026 covers two very different things, and mixing them up causes most bad choices: Build-your-own frameworks — libraries you code against to assemble an agent (LangGraph, CrewAI, AutoGPT-style). You own the plumbing: tool-calling loops, memory, channels. High control, high effort. Ready-to-run harnesses — a packaged agent you install, configure, and deploy as a service. It already has the reasoning loop, the channels, the skills system.