Joined February 2026
- Tweets 6,292
- Following 844
- Followers 5,698
- Likes 8,573
378 Photos and videos
Pinned Tweet
Here's the top 5 most cost efficient models to run on hermes agent
1. MiMo-V2.5
2. DeepSeek V4 Flash (Max)
3. MiMo-V2-Flash (Feb 2026)
4. DeepSeek V4 Flash (High)
5. Hy3-preview
64
98
957
49,905
introducing /share command for hermes
- full fidelity export: captures user messages, agent responses, tool calls, and tool output with unix precise timestamps. Nothing gets dropped.
- dual mode: plain /share dumps the full convo and /share - - summary generates a concise 3-5 sentence recap
- hermes native: only uses built in tools. no external APIs, no auth tokens and it will not break when hermes updates
please, let me know how yall feel when you use it and I hope its useful!
3
2
21
1,137
1
1
3
265
now that Fable 5 gone.. what model are you running on hermes agent?
38
1
46
10,147
before hermes touches a single file it creates a checkpoint of your working directory
most people don't know this is happening
if something breaks you type /rollback and you're back to exactly where you were
I've seen people avoid hermes for serious projects because they're worried about the agent making mistakes
this is the feature that should change that
6
8
83
3,361
well this didn’t age too well
Claude Fable 5 has been out for a couple of days. Some projects people have already built with it:
3
22
1,561
bye bye Fable 5… it was good while it lasted
Jun 13
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.
Access to all other Claude models is not affected.
We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.
Read our full statement: anthropic.com/news/fable-myt…
2
14
805
Top current LLMs in the intelligence field.. Fable 5 being the kind followed by GPT-5.5(xhigh)
do you think Fable 5 is better than 5.5 rn or not really
9
2
23
1,113
hermes WhatsApp Business integration just got a serious upgrade
- blue double checkmark read receipts the moment your message lands
- typing indicator shows while the agent is thinking
- voice notes auto transcribed and answered
- native tap buttons for approvals instead of typing commands
- images and documents read directly by the agent
- one setup wizard: hermes whatsapp-cloud
bro… this is not a WhatsApp bot
this is your agent with a WhatsApp number
Jun 12
Hermes Agent now has a production-grade WhatsApp Business Cloud integration: use it as a private WhatsApp bot for yourself or your team, or configure it for customer-facing support.
Connect an existing WhatsApp Business Cloud number or create one through Meta Business Manager, then run 'hermes whatsapp-cloud' to wire it into Hermes with guided setup, secure webhooks, media/voice support, read receipts, typing indicators, and interactive approval buttons.
5
3
35
3,128
how good is DeepSeek V4 that it’s killing it on the charts?
3
7
743
if ur into
- building awesome ai agents
- hermes agent
- codex
- claude code
- robots n LLMs
- local LLMs
check in below fellas we’re connecting forever 💯🔥
33
3
134
9,650
hermes automation blueprints are not just cron jobs with a better name TRUSTTT
these are fully built workflows you copy, fill in your details, and run
- nightly github issue triage that delivers a digest to telegram
- automatic PR code review that posts directly on the PR
- CI failure analysis that tells you why it broke and how to fix it
- stripe payment monitoring that flags disputes as urgent
all of it ships ready to go
you're not building automations anymore, you're just turning them on
Jun 11
Hermes Agent now has Automation Blueprints, turning cron jobs into clickable, fillable, conversational workflows.
4
7
125
19,394
I guess we’ll see GPT-5.6 drop next week? i doubt they would drop something later in the day today
16
1,297
managing multiple hermes profiles just got a lot less painful
• no more running separate dashboards for each profile
• switch between all your agents from one place
• one unified gateway is coming next
small update, big difference in practice
We are unifying profile management in Hermes Agent starting today.
Now the dashboard allows switching management to any of your agent profiles on the machine. No more running multiple dashboards to manage each profile!
Also soon, you will only need one gateway to access all of your agents. This will enable us to progress toward full and true isolated multi-tenant solutions in the future.
2
2
27
1,820
the @nousresearch might be the fastest moving team in open source AI right now
hermes launched in february and by june it had a native desktop app, kanban swarm system, 15 messaging integrations, and a full skills marketplace
four months
that pace doesn't happen by accident theyre really cooking it up
1
2
41
1,538
big release tomorrow?? @OpenAI the stage is urs boyyy
5
16
972
I think this is a great feature, especially those who do not want Hermes to memorize everything now you have the ability to turn it off if that’s what you want
Introducing Write Gate in Hermes Agent.
Now you have the capability to be able to approve/deny memory updates, skill updates, and skill creation with the same familiar mechanisms as approving dangerous commands.
If you are using a small model that doesn't always recognize what it learned, a secure environment that needs gating before things that can affect operations occurs, or just want to be more involved in the self improvement process of your Hermes Agent, now you have full control!
This will be included in the next major release version, but you can run `hermes update` now to access early!
1
12
1,326
if you're using AI coding agents and not tracking what you're spending, tokscale fixes that
one command: npx tokscale@latest
- tracks claude code, cursor, codex, gemini, opencode, amp, and 10 more
- real-time cost breakdown per model and platform
- github style contribution graph for your token usage
- global leaderboard to see how you stack up
- built in rust... 8x faster than the typescript version
tokens are the new electricity
know what you're burning
3
8
1,261
1
767
someone built 754 cybersecurity skills for AI agents and it's fully open source
> 26 security domains covered
> mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, and NIST AI RMF
> works with hermes agent, claude code, cursor, copilot, and 20 platforms
install it by telling ur hermes this: hermes skills install mukul975/Anthropic-Cybersecurity-Skills
wanted to test this on my linux box running Hermes Agent so i did...
i ran it like a pentester would... here is what they found in under 10 minutes:
- a web server serving the entire filesystem to the local network
- no firewall on a machine with ssh remote desktop and a public ngrok tunnel
- ssh configured with password auth and x11 forwarding enabled
- api keys sitting in plaintext in shell config files
- a huggingface token readable by any process on the system
- 92 pending security updates
and more...
my agent fixed all of them
your agent just got the skills of a senior security analyst
4
4
51
2,617
1
8
437