Bourne Bot: a security agent that knows what it won't do
The Review

Bourne Bot: a security agent that knows what it won't do

Our fourth Hermes Agent template is a personal security advisor with hard refusals built in. It walks you through incidents, builds a threat model, and refuses the requests that would make you less safe. Here is what it does, how it thinks, and how to install it.

PR
Paula Rossi9 min
The image the model never saw
The Review

The image the model never saw

An MCP tool returned a screenshot. The model got back a MEDIA:/path line and never saw the pixels. A raw cua-driver MCP server could not see the screen at all. Seven commits landed this week to fix it — one mechanism, six review fixes that caught what the first cut missed. The pattern: a capability that works in a demo and fails under load.

PR
Paula Rossi11 min
The /goal contract survives the cut
The Review

The /goal contract survives the cut

Hermes PR #133692 re-folds the /goal contract through every compaction boundary, mirroring the todo-list fold that already worked. The mechanism is small. The pattern it follows is the one worth knowing: any state that must survive a lossy boundary has to be structurally pinned, not paraphrased into a summary.

PR
Paula Rossi9 min
Three Upstream Fixes That Stop Lying to You
The Review

Three Upstream Fixes That Stop Lying to You

A secret source removed but its value lingers in os.environ. A cron fire routed through the dashboard that the ticker never sees. A worker that died and got filed as 'Scheduler restarted.' Three commits on Hermes main this week fix the same class of bug: the system reporting success for something it didn't observe succeed.

PR
Paula Rossi11 min
FOCUS: Stop Summarizing What Happened, Start Preserving What Decides
The Review

FOCUS: Stop Summarizing What Happened, Start Preserving What Decides

A paper posted yesterday recasts agent context compression as a causal decision-preservation problem — not redundancy reduction. Monte Carlo rollouts score which past interactions shape future decisions, and the spans that don't get dropped. Peak context down 48%, task success up 8.9 points. Training-free.

PR
Paula Rossi9 min
Three Open, One Stuck, One Waiting for Checks: The Upstream Ledger
The Review

Three Open, One Stuck, One Waiting for Checks: The Upstream Ledger

Monday ledger: PR #93172 is mergeable with all CI green and has been waiting since August. #124319 just opened but CI has not reported. #86777 and #90133 are conflicting. Meanwhile upstream landed a toolchain isolation campaign that changes what Hermes will provision on our next update.

PR
Paula Rossi7 min
LAR: A Production-Grade Claim We Could Not Import
The Review

LAR: A Production-Grade Claim We Could Not Import

lar-agent-resilience advertised Agent, ModelRouter, and Checkpoint. The package __init__ was empty. The code imported lar.* and there was no lar package. Six tests passed — on a skill demo. We made the README true.

PR
Paula Rossi13 min
Oppositional Re-Pass: What “Production Hardening” Still Left Open
The Review

Oppositional Re-Pass: What “Production Hardening” Still Left Open

We re-audited Swarm, smf-forge, LAR, and Harbor after the first hardening wave. Parallel teams had merged. The remaining bugs were the ones that hide inside a green check: prompt-as-shell on main, shell=True in LAR, a diagnostic SSRF path, and a plugin that still advertised outcome logging.

PR
Paula Rossi11 min
smf-forge 0.2.0: The Prompt Is Not a Shell Command
The Review

smf-forge 0.2.0: The Prompt Is Not a Shell Command

Our multi-agent CLI had a real DAG engine and 35 tests. It also executed the step prompt via create_subprocess_shell when options.command was missing. That is RCE. Here is the audit, the fix, and the honest install story.

PR
Paula Rossi14 min