864 commits. 588 merged PRs. 295 contributors. Durable multi-agent Kanban. Persistent /goal tracking. 8 P0 security fixes. Hermes just shipped the features OpenClaw users have been requesting for months.
AlphaSignal published their analysis three days ago: "Install Hermes v0.13 this weekend as the runtime layer next to Claude Code or Codex, not as a replacement."
That's not a casual recommendation. AlphaSignal has 280,000+ developer subscribers. They're telling developers to install Hermes right now.
One week after v0.12 shipped the Curator (self-maintaining skills). Seven days later, v0.13 shipped Kanban (multi-agent task completion). Two releases in seven days that fundamentally changed what Hermes is.
Here's what actually shipped in v0.13, what it means for the OpenClaw ecosystem, and the honest assessment of where Hermes is strong, where it's weak, and where BetterClaw fits in.
What "The Tenacity Release" Actually Ships
The tagline says it all: "Hermes Agent now finishes what it starts."
Before v0.13, Hermes (like OpenClaw) had a completion problem. You'd ask the agent to do a multi-step task. It would start, hit a snag, and either loop, hallucinate a result, or silently abandon the work. The agent was smart. It just wasn't persistent.
v0.13 attacks this with three features that work together:
Durable multi-agent Kanban. Spin up a board. Drop tasks on it. Multiple Hermes workers pick them up, hand off, and close them out. Heartbeats, reclaim on timeout, zombie detection (catches workers that died mid-task), auto-block on incomplete exit, per-task retry budgets, and a hallucination recovery gate. This is genuine multi-agent orchestration with durability, not a demo.
/goal (the Ralph loop). Tell the agent what you want accomplished. It stays locked on that target across turns. If it gets sidetracked, it comes back. If a tool fails, it finds another way. The agent doesn't forget what you asked it to do. OpenClaw's TaskFlows (v2026.4.7) tackle a similar problem but with a different architecture: webhook-triggered flows versus persistent goal tracking.
Checkpoints v2. State persistence rewritten with real pruning, disk guardrails, and no orphan shadow repos. The agent can roll back to a known good state. Combined with gateway auto-resume (interrupted sessions automatically recover after restart), the agent survives crashes.
The shift: v0.12 taught Hermes to maintain itself (Curator). v0.13 taught it to finish what it starts (Kanban + /goal + Checkpoints). Together, they make Hermes the first open-source agent framework with built-in completion guarantees. OpenClaw doesn't have an equivalent yet.
The Security Wave (8 P0 Closures in One Release)
Here's what nobody tells you about Hermes security.
v0.13 closed 8 P0 security issues in a single release. For context, OpenClaw's CVE-2026-25253 (CVSS 8.8, one-click RCE) was one P0 that dominated headlines for weeks. Hermes closed eight at once.
Redaction ON by default. Agent output now redacts sensitive content automatically. You don't enable it. It's on. OpenClaw doesn't have equivalent output redaction.
Discord role-allowlists are now guild-scoped. Previously, a CVSS 8.1 cross-guild DM bypass let users from one Discord server interact with agents in another. Closed.
WhatsApp rejects strangers by default. New WhatsApp connections are blocked unless explicitly allowlisted. Compare to OpenClaw where 30,000+ instances were found exposed without authentication.
TOCTOU windows closed across auth.json and MCP OAuth. Time-of-check-to-time-of-use vulnerabilities in the authentication flow are patched.
For the OpenClaw security risks analysis, our security risks deep dive covers the broader attack surface that both frameworks share.
The Platform Count (20 and Growing)
Hermes v0.13 added Google Chat as its 20th messaging platform. The full list: Telegram, Discord, Slack, WhatsApp, Signal, DingTalk, SMS (Twilio), Mattermost, Matrix, Webhook, Email (IMAP/SMTP), Home Assistant, Feishu/Lark, WeCom, Weixin, BlueBubbles (iMessage), QQBot, Yuanbao, Microsoft Teams, and Google Chat. LINE support is on main.
OpenClaw claims 50+ channels but many are community-contributed and inconsistently maintained. Hermes's 20 are all run from one gateway process with unified session management.
The Honest Comparison (Where Hermes Beats OpenClaw, Where It Doesn't)
Stay with me here. We're a company in the OpenClaw ecosystem. Being honest about a competitor's strengths is the right call because you'll figure it out anyway.
Where Hermes v0.13 is stronger:
- Task completion (
/goal+ Kanban). Hermes has native goal persistence and multi-agent task boards. OpenClaw has TaskFlows but they're webhook-triggered, not goal-tracked. - Security defaults. Redaction on by default. Stranger rejection by default. Guild-scoped allowlists. OpenClaw's defaults are more permissive.
- Self-maintenance (Curator from v0.12). The agent maintains its own skill library on a 7-day cycle. OpenClaw relies on ClawHub, which had 1,400+ malicious skills.
- Stability. AlphaSignal notes: "fewer 'install another skill' moments, more persistent runtime machinery." The community reports less breaking-change churn than OpenClaw's 18-releases-in-18-days pace.
Where OpenClaw is stronger:
- Ecosystem size. 230K+ stars versus Hermes's growing but smaller community. More tutorials, more integrations, more community support.
- Channel count. 50+ versus 20. If you need a niche platform, OpenClaw probably has a community plugin for it.
- MCP adoption. 1,000+ MCP servers work with OpenClaw natively. Hermes exposes itself as an MCP server but the ecosystem is smaller.
- Feature velocity. OpenClaw ships faster (sometimes too fast, as the update fatigue problem shows). New features land sooner, regressions included.
If you want the features of both ecosystems without managing either framework's setup, security, and infrastructure, BetterClaw supports both OpenClaw workflows and is model-agnostic. The platform handles deployment, security, monitoring, and updates. You focus on the agent workflows. Free tier with 1 agent and BYOK. $19/month per agent for Pro.
What This Means for the AI Agent Space
Here's the honest take.
Hermes v0.13 is the first time an OpenClaw competitor shipped features that OpenClaw users actively want and don't have. Goal persistence, multi-agent Kanban with durability, default-on security redaction, and self-maintaining skills. These aren't marketing features. They're architectural decisions that address real complaints from the OpenClaw community.
AlphaSignal's recommendation was specific: "Install Hermes v0.13 this weekend as the runtime layer next to Claude Code or Codex." Not instead of OpenClaw. Next to it. The community is starting to run both frameworks for different purposes.
The caveat from AlphaSignal: "Wait if production controls, mature audit trails, or zero setup friction matter more than the runtime upside." Hermes v0.13 is "Tenacity, not Production." macOS users with Python 3.13 hit installer conflicts. Docker users hit Node version mismatches. Native Windows isn't supported (WSL required). /goal uses a judge model that can mark goals complete prematurely or keep them open too long.
The AI agent framework market is splitting. OpenClaw owns the ecosystem (stars, plugins, community). Hermes owns the runtime machinery (completion, self-maintenance, security defaults). Both are self-hosted. Both require infrastructure management.
For the side-by-side comparison of Hermes against BetterClaw, our BetterClaw vs Hermes post covers how the managed platform compares to the self-hosted framework.
If you want the agent without managing either framework, give BetterClaw a try. Free tier with 1 agent and BYOK. $19/month per agent for Pro. We track both ecosystems so you don't have to. The agent runs. The framework choice is ours. The conversations are yours.
Frequently Asked Questions
What is Hermes Agent v0.13?
Hermes Agent v0.13, called "The Tenacity Release," shipped May 7, 2026 from Nous Research. It adds durable multi-agent Kanban (task boards with heartbeats, zombie detection, retry budgets), persistent /goal tracking (the agent stays locked on a target across turns), Checkpoints v2 (state persistence with real pruning and rollback), and 8 P0 security fixes. 864 commits, 588 merged PRs, 295 contributors.
How does Hermes v0.13 compare to OpenClaw?
Hermes v0.13 is stronger on task completion (/goal, Kanban), security defaults (redaction on, strangers rejected, guild-scoped allowlists), and self-maintenance (Curator). OpenClaw is stronger on ecosystem size (230K+ stars), channel count (50+ vs 20), MCP adoption (1,000+ servers), and feature velocity. Many users are starting to run both for different purposes.
Should I switch from OpenClaw to Hermes?
Not necessarily. AlphaSignal recommends installing Hermes "next to Claude Code or Codex, not as a replacement." The frameworks have different strengths. If task completion and security defaults matter most, Hermes v0.13 is compelling. If ecosystem breadth, channel support, and community resources matter most, OpenClaw is still ahead. BetterClaw lets you avoid the framework choice entirely with managed deployment.
Is Hermes v0.13 production-ready?
AlphaSignal's assessment: "Tenacity, not Production." Known issues: macOS Python 3.13 installer conflicts, Docker Node version mismatches, no native Windows support (WSL required), /goal judge model can prematurely complete or keep goals open. Treat it as a serious test, not a production deployment. The security improvements are real. The stability improvements are real. The rough edges are also real.
Does BetterClaw support Hermes Agent?
BetterClaw is built on the OpenClaw framework with platform-level optimizations (smart context management, verified skills, secrets auto-purge). While BetterClaw doesn't run Hermes directly, it provides the managed deployment, security, and monitoring that both OpenClaw and Hermes users need. Free tier with 1 agent and BYOK. $19/month per agent for Pro.
