officialOperational Playbooks
Nightly self-evolution + guardrail evaluation
Run hermes-agent-self-evolution on a schedule, then run a second verification cron to score quality and block optimization-loop gaming.
Playbooks & Blueprints
Featured
11 items
Operational Playbooks
5 items
officialOperational Playbooks
Memory pressure handling with Honcho/Hindsight
If you are repeating context or losing long-term recall, review Honcho Memory docs, and evaluate hindsight or self-hosted memory backends.
officialOperational Playbooks
Tune session timeout/expiry early
Use configuration docs to adjust session retention for slower-moving threads so context is kept when needed.
officialOperational Playbooks
OpenClaw side-by-side migration
Keep both systems running during migration using openclaw-to-hermes and native Hermes migration paths, then cut over once cron and routing behavior match.
officialOperational Playbooks
Curate USER.md and MEMORY.md intentionally
Treat profile memory as high-signal infrastructure. Keep entries concise, durable, and preference-focused instead of dumping raw notes.
Level-Up Blueprints
6 items
officialLevel-Up Blueprints
Memory stack that actually compounds
Start with built-in Hermes memory, then add honcho-self-hosted when you want stronger cross-session user modeling, hindsight when you need retain/recall/reflect workflows across large histories, and plur when you want portable shared memory artifacts in an open engram format. If you also want proactive recall, pair it with flowstate-qmd.
officialLevel-Up Blueprints
Self-improvement without self-delusion
Pair hermes-agent-self-evolution with scheduled regression checks, lintlang for prompt/config linting, and a second evaluation pass that blocks bad prompt mutations. The trick is not “evolve faster”; it’s “evolve without quietly getting weird.”
officialLevel-Up Blueprints
Operator cockpit for real work
Use hermes-workspace for the richest daily UI, mission-control when you need multi-agent fleet visibility and cost tracking, and hermes-webui if you want a lighter ops surface.
officialLevel-Up Blueprints
Multi-agent execution layer
Combine Hermes core delegation with hermes-agent-acp-skill for Codex/Claude Code routing, zouroboros-swarm-executors for local executor handoff, and opencode-hermes-multiagent or bigiron when you need specialized agent roles.
officialLevel-Up Blueprints
Migration + deployment hardening
If you are moving from OpenClaw, keep openclaw-to-hermes in the toolkit even if you prefer the native migration path. For repeatable deploys, look at nix-hermes-agent, hermes-agent-docker, and evey-setup depending on how opinionated you want the stack to be.
officialLevel-Up Blueprints
Paperclip-managed autonomous ops
For teams that want Hermes operating inside a governed company workflow, combine hermes-paperclip-adapter with Hermes cron jobs and one of the operator dashboards above. That gives you task governance, approvals, and actual operational continuity instead of a clever demo that forgets what it was doing.