OpenHands

OpenHands is the leading open source agent for software development, usable through a CLI, GUI, SDK, or IDE

[OpenHands @OpenHandsDev]

For coding agents, "skills" are a great way to automate repetitive workflows, but how can we tell if they're working at scale?

We did a deep dive on how you can log, monitor, and improve agent skills, with a real example of building a customized PR review skill.

[Rajiv Shah @rajistics]

I couldn't help myself and had to dig into dynamic workflows.
Check out my repo which explains it: https://t.co/kPJh4btQ1a
Or a video if you want to hear me talk through it:
https://t.co/UknWcPaXC9

[Graham Neubig @gneubig]

Claude dynamic workflows seemed pretty cool and I wanted an open-source version, so I made one. This one improves the test coverage of your entire repo, but you should be able to swap out the prompt and do anything else: https://t.co/zqT4BP8K7W

[OpenHands @OpenHandsDev]

We have also partnered with @MiniMax_AI to provide

*free access to agents with MiniMax-M2.7*

for a limited time!

This is a great opportunity to test out how to mix in cost-effective models into your coding workflows.

Try it out here: https://t.co/FQw0hqxzLX

[OpenHands @OpenHandsDev]

Our latest release has *in-conversation fast language model choice*!

This lets you switch LLMs by:

1. A dropdown or /model slash command
2. Telling the model "switch to this LLM now", it will call a tool for you!

You can say things like "use opus for planning, minimax for implementation, and gpt for final review".

[OpenHands @OpenHandsDev]

Check it out!

On the cloud: https://t.co/UpXEKKmeH5
Locally through our agent canvas: https://t.co/mFkDazOZKH

And read more in our blog here: https://t.co/tzUuDp7urG

[OpenHands @OpenHandsDev]

Our latest release has *in-conversation fast language model choice*!

This lets you switch LLMs by:

1. A dropdown or /model slash command
2. Telling the model "switch to this LLM now", it will call a tool for you!

You can say things like "use opus for planning, minimax for implementation, and gpt for final review".

[OpenHands @OpenHandsDev]

Come say hi to us at the @CAISconf in San Jose this week if you're around!

[Graham Neubig @gneubig]

I'm at @CAISconf in San Jose this week! Giving three talks, joining a panel, and otherwise being around the bay area. Come say hi if you're around!

Talks slides 👇

[OpenHands @OpenHandsDev]

@Teknium Amazing! We'll have to work on a Hermes orchestration skill so our agents can orchestrate each other

[Teknium 🪽 @Teknium]

Hermes Agent now can orchestrate the @OpenHandsDev agents with a new optional skill!

`hermes update` then do `hermes skills install official/autonomous-ai-agents/openhands`

Reminder: You can already do this for claude code, codex, opencode, and hermes itself, you can force load the skill with `/<agent-name> <prompt>` or just ask hermes to use them, and it should find them.

These ones are all built-in skills :)

[OpenHands @OpenHandsDev]

@scriptology_eu @levelsio @TermiusHQ If you had any issues with setup that we could make easier we'd be happy to hear about them so we can try to make it easier next time!

[Jamie Chicago @jamiechicago312]

In FOUR days, leaders from @OpenHandsDev @vercel @AMD @nvidia are going to be featured in a panel hosted by @alumniventures

We've had over 100+ sign ups in a week, spots are limited so head over to @LumaHQ to reserve your spot.

RSVP link below

[OpenHands @OpenHandsDev]

Today · 12:00–1:00 PM ET / 4:00–5:00 PM UTC
RSVP: https://t.co/jx0httuBw2

[OpenHands @OpenHandsDev]

Today: OpenHands Community Call.

We’re sharing project updates, demos of what’s new, contributor shout-outs, and open Q&amp;A with the community.

Come join us live.

[jevpen @me_darealjev]

building a disciplined local coding agent setup...

- Main surface: OpenHands
- Local models via Ollama (7B-class on M3 Pro 18GB)
- Codex will be the "strong external model as senior reviewer/verifier"
- Will use strict modes + mandatory structured handoff packets + gates

Anyone else running something similar with OpenHands + local LLMs? What am I missing or what commonly goes wrong?

#LocalLLM #OpenHands #AgenticCoding

[Graham Neubig @gneubig]

Scaling Enterprise AI Agents event in NYC on May 26th!

Speakers from @OpenHandsDev, @NVIDIAAI, @AIatAMD, and @vercel! If you're in the city then we'd love to have a good turnout.

[OpenHands @OpenHandsDev]

Thursday, May 21 · 12:00–1:00 PM ET / 4:00–5:00 PM UTC
RSVP: https://t.co/jx0httuBw2

[OpenHands @OpenHandsDev]

Tomorrow: OpenHands Community Call.

We’re live with project updates, demos of what’s new, contributor shout-outs, and open Q&amp;A.

If you want to hear what’s been shipping — and where OpenHands is headed next — join us live.

[Xingyao Wang @xingyaow_]

I’ll be at MLSys 2026 in Seattle this week!

We’re presenting our OpenHands Software Agent SDK work — lessons from OpenHands V0, where we ran into the hard parts of scaling software agents to production.

If you’re around, come say hi! Happy to chat about agent infrastructure, evaluation, training, verification, or anything software agents.

Oral: Thu May 21, 9:30–9:45 AM PDT
Poster: Thu May 21, 6–8 PM PDT, Poster Session 3
https://t.co/JybXZHpgB4

[Rajiv Shah @rajistics]

Context is a huge challenge for enterprises.
How do you get all your systems and data to work together?
Go spend some time at the @AtScale summit, they have some terrific speakers and sessions to deepen your understanding.
https://t.co/m849GDgWnM

[Graham Neubig @gneubig]

A serious compromise at github, again due to a supply chain vulnerability...

It demonstrates that basically everyone needs to start securing their software supply chain through every means possible, deterministic scanning being the first step, AI where necessary.

[OpenHands @OpenHandsDev]

Thursday, May 21 · 12:00–1:00 PM ET / 4:00–5:00 PM UTC
RSVP: https://t.co/jx0httuBw2