CEOmarabha

👑Temporarily Immortal👑

[CEOmarabha @CEOmarabha]

@banana_large @ilovegoyslop @The1ClearTruth @NotSonnyFaz 😂😂😂

[CEOmarabha @CEOmarabha]

@Saccc_c you're a clown kid

[Luke The Dev @iamlukethedev]

Hidden Hermes gem: /rollback

I just watched an AI agent destroy a codebase in 3 seconds.

rm -rf src/
rm -rf tests/
git reset --hard

It ran them all in a single turn. The agent made a logic error early on and cascaded into catastrophic failure.

So I typed: /rollback 1

Everything came back.

Files restored. Agent context rewound. Like it never happened.

This is the checkpoint system.

Here's what it does:

Hermes auto-snapshots your project before EVERY destructive operation:

- File writes (write_file)
- File patches (patch)
- Dangerous terminal commands (rm, git reset --hard, sed -i, etc.)

One snapshot per directory per turn. No spam in long sessions.

Then when things go wrong (or right, but you want a different approach):

/rollback lists all checkpoints with change stats
/rollback <N> restores to checkpoint N AND rewinds agent context (filesystem state matches agent context)
/rollback diff <N> previews what changed since checkpoint N
/rollback <N> filename restores a single file from checkpoint N

How to enable:

Per-session:
hermes chat --checkpoints

Or globally in ~/.hermes/config.yaml:
checkpoints:
enabled: true

How it actually works under the hood:

Single shared git store (~/.hermes/checkpoints/store/)
Git's content-addressable object DB deduplicates across projects
Per-project refs track checkpoint history independently
Result: after first snapshot, each new snapshot costs near-zero storage

Safety guardrails:

Skips files larger than max_file_size_mb (default 10 MB)
Skips overly broad directories (root /, home $HOME)
Skips repos with 50k+ files
Auto-prunes orphan projects (whose working directory no longer exists)
Respects max_snapshots (default 20) and max_total_size_mb (default 500)
If git is not on PATH, checkpoints transparently disable
Non-fatal errors log at debug level; your tools continue running

What it's NOT:

Not a git replacement
Not full version control
Not recursive backup magic

Just a safety net for AI operations. Opt-in. Silent. Near-zero cost.

Best for:

Unattended automation (cron jobs, deployments, CI/CD)
Multi-step refactoring where mistakes cascade
Bulk file operations you want to abort instantly
Experiments you're not 100% confident in

Real example:

Agent refactoring your package structure:
Snapshot 1: write_file for new modules (+847 lines)
Snapshot 2: patch imports across 15 files
Snapshot 3: terminal rm -rf old_src/

Somewhere in step 3, it deletes more than intended.

/rollback 1

Back to before the refactoring started. Agent context rewinds. You're in control again.

This is what separates:
- Hands-on automation (you watch every step)
- Trusted automation (you set it loose, but you have an undo button)

CLI commands (outside a session):

hermes checkpoints
hermes checkpoints status
hermes checkpoints prune
hermes checkpoints clear

Config options:

checkpoints:
enabled: false
max_snapshots: 20
max_total_size_mb: 500
max_file_size_mb: 10
auto_prune: true
retention_days: 7

Why this matters now:

Most AI agent frameworks have no undo. You're supposed to use git manually. Hermes built it in, transparent, automatic, intelligent.

[SpaceWeatherNews @SunWeatherMan]

ECDO Theory - Roger B. Cunningham (EthicalSkeptic) - YouTube

Full five hour presentation https://t.co/GtLolY9lvW

[CEOmarabha @CEOmarabha]

@SunWeatherMan thanks for sharing

[Omar Tawil @OTawil89]

Brother @sneako needs to sit down with scholars and good company. Nowhere famous or with too much traffic and the focus has to be off-camera.

Can someone with more clout get this idea to him? There are plenty of hidden gems in the USA where they won’t care about his status

[Isaac’s Army @ReturnOfKappy]

MESSI’S HUMILIATION RITUAL 20 YEARS AGO…

At 18, Messi was publicly grabbed, manhandled, and degraded on Argentine TV in this “comedy” sketch…

Elites initiating their stars early with ritual humiliation… 👀

[BridgeMind @bridgemindai]

New CursorBench results just dropped and Grok 4.5 is the story.

#3 overall at 66.7%. Right behind Fable 5 Max at 70.5%.

Now look at the cost column.

Fable 5 Max: $17.32 per task
Grok 4.5 High: $1.51 per task

That is Fable level performance at roughly 1/10th the cost.

And it beats Fable 5 High and Opus 4.8 Max outright.

The intelligence war just became a price war.

[CEOmarabha @CEOmarabha]

@Arnavmj are you actually gonna send it or is this some way to try and make people pay for the way to do it

[CEOmarabha @CEOmarabha]

@Arnavmj tool

[CEOmarabha @CEOmarabha]

@SantiTorAI bs

[adam · agentic ai, adhd-driven @aae_on_x]

@RoundtableSpace i was able to use fable to create skills that resulted in sonnet 5 out performing opus 4.8 on benchmarks
https://t.co/SxhE7GHFGM

[Starter Story @starter_story]

Jake, who built a $50K/month alarm app in 4 months, says the most valuable skill right now isn't building it's...

"Focus on top of funnel only. That is the most valuable skill right now is marketing. There's so many people that can build an app and it's so easy with AI, but there's not so many people that know how to market and know how to get views."

"If nobody knows about your app, it doesn't exist. You can build as many features as you want."

"Building doesn't really matter so much. You got to build a good product, of course. But getting views is more of the unknown."

[Juan Tyrus @GenesisFarmLLC]

It's official I'm the first person to video verify Dicyanin Glasses and Dye work allowing us to see invisible light.
Next I make a Dicyanin light to see what a modern Pelan Tan does for seeing the unseen.
I have hundreds of new experiments coming.
We saw a first today 🤯

[CEOmarabha @CEOmarabha]

@SunWeatherMan @Equalrightsyay hahaha😂😂😂

[libapi @libapi_]

基于 @NousResearch Hermes Studio /MoA 多模型协同机制。

/MoA = DeepSeek + GLM-5.2 的组合同样能够产出高水准的动态网页作品。

虽然整体生成周期相对较长，过程中存在一定的冗余输出，但最终成品在视觉表现、交互体验和完成度方面均具备较好的水准。 @Teknium

[Ray Fernando @RayFernando1337]

I went to sleep and woke up with huge iOS features ready to go: onboarding, research for pricing, adding a paywall, ai proxy, and fixing multiple bugs.

There is a massive iOS App Store opportunity that is now unlocked with Fable 5 + Cursor Multitask. It didn't require arduous chat windows, paragraphs of prompts, skills, or anything out of the ordinary.

It was able to build the app, test, generate screenshots, iterate until it was done. I'll post more images of the Cursor session and will be doing some livestreams to show you more. I'm blown away with the Cursor app and I like this experience better than inside of Claude Code.

[wil michael @wilplatypus]

this dream is ending soon

[Hermes Agent Tips @HermesAgentTips]

so.. for those who didnt know.. if you have an xai grok subscription you can now run cursor's composer 2.5 model inside hermes agent

no separate api key, full 200k context, straight through oauth

your grok plan, hermes's agent loop, composer's coding speed

ALL 3 separate products working together.. what a year to be alive sheeeshhh!