Saturday, November 7, 2026 270 picks · 133 builders credited Subscribe
AgentRags.

The agentic rag, wrung out.

Guides & WorkflowsWednesday, October 7, 2026

Manual approval for Hermes self-written skills

Operator note on the skill-learning loop: one bad instruction can ride into every later task that loads that skill. Gate it with `/skills approval on`, then `/skills pending`, `/skills diff <id>`, `/skills approve <id>`, `/skills reject <id>`. The gate covers skill writes including background learning.

Cover art for Guides & Workflows: Manual approval for Hermes self-written skills

Why it matters

Self-improving skills are the Hermes feature people turn on first and audit last. This is the concrete control, not a philosophy post.

From the source

Hermes Agent#skills#approval-gate#memory#self-improvement#operator

Related

More Guides & Workflows

Guides & WorkflowsOct 29

oh-my-hermes: One-Line Install for 150+ Skills + Video Generation

@rlaope packaged a heavily tuned Hermes setup (150+ skills, long-term memory with higher retention, graph engineering, multi-model subagent routing, parallel tool execution) into a single install. Latest addition: built-in video generation skills (hyperframe clips, reels, 3D renders, pixel art). Fully open source; designed for zero-friction handoff of complex tasks.

Guides & WorkflowsOct 24

Oh-My-Hermes: 150+ Skills, Trusted Long-Term Memory, and Automatic Model Routing

HOPE. (@rlaope) released Oh-My-Hermes after burning ~200B tokens tuning setups. One-line install adds 150+ specialist skills, graph engineering, verified long-term memory (candidates kept/refused with reasons; recall packs ranked to token budget), subagent routing across model chains, parallel tool calling, and evals. It operates as a layer on top of Hermes without patching it.

Never miss a night

Every pick, delivered to your reader.

One feed for everything, or one per agent harness you run. Rebuilt every night, with full credit on every item.