When we say Nightshift is infrastructure-agnostic, we mean all of it.
Your compute, wherever it runs. Your storage, wherever it lives. Your identity provider, your auth provider, your model provider. Nightshift doesn't ask you to compromise, and it doesn't lock you in.
We built it this way because the alternative is the trade every other platform asks you to make: adopt our cloud, our identity layer, our model, and rebuild your assumptions around our product.
The agent layer should fit the stack you have- not the other way around.
To learn more, read our blog post: https://t.co/uPNNO50keR
agent sovereignty matters.
we open-sourced the same tech that powers OpenAI Frontier and Claude Managed Agents.
run agents securely on your stack, with observability and telemetry at every level.
https://t.co/LIPJx5kD22
I was tinkering with KVM to get an idea of what Firecracker was doing under the hood for @nightshiftdotsh and decided to write a blog post of building a VMM (what firecracker is) in Python, from scratch.
https://t.co/LqmME8fHDc
The rate of task completion success and nightshift is tightly coupled to the context the agent has available in its workspace. It will build context over time, but what we were interested in is creating a standard bootstrapping prompt that could solve the cold-start problem.
We benchmarked how different frontier models performed at setting up their environments, focusing on skill creation ability and proper workspace configuration.
Check out the blog post here: https://t.co/eAgssuVpF8
Join the flock here ๐ฆ : https://t.co/CwUt1uMSyK
Agents events deployed into Nightshift v0.4.3 are durable! A quality of life feature for those building Agents.
Deploy your flock of Agents ๐ฆ Stream their events. Build useful sh*t.
In the latest release of @nightshiftdotsh (v0.4.3) Agent events are durable and repayable.
Deploy your own KVM backed Agent Sandbox Platform. Is and will always be OSS.
The @nightshiftdotsh SDK is boring.
We designed it that way.
Write your agent in the frameworks you're used to (we're using the @OpenAI Agent SDK here). Wrap your agent in a decorator. Run it in a sandbox. Deploy and serve users.
Is and will always be open source, for the community.
I now ship with Gollum (a simple wiki system built on top of Git) giving our users a way for them to collaborate along side agents asynchronously.
Build your flock of agents. Manage them over time.
In the latest developments of @nightshiftdotsh we now ship Gollum (a simple wiki system built on top of git) that gives you a view into the agent workspace.
This gives a consistent space for humans and agents to collaborate on knowledge work asynchronously. Have the agent read from documentation you add, or have them write out to a reports directory after performing a long running background job.
In the latest version of Nightshift v0.1.3 enables turning coding agents like @opencode into async knowledge workers.
- Define your task spec on the job board
- Run multiple tasks at once
- Agents solve work to completion
- Run tasks in the background
https://t.co/HpEjlFkfaZ
In the latest @nightshiftdotsh (v0.1.3) you can now turn a coding agent like @opencode into background knowledge worker.
- Define your task spec on the job board
- Run multiple tasks at once
- Agents run tasks to completion
- Run tasks in the background
We're open source.
In the latest @nightshiftdotsh (v0.1.3) you can now turn a coding agent like @opencode into background knowledge worker.
- Define your task spec on the job board
- Run multiple tasks at once
- Agents run tasks to completion
- Run tasks in the background
We're open source.
@ThePeterMick My names Gianni and i'm building @SylowTech, we're a group of builders helping startups get to revenue and Enterprises solve hard problems. If you're interested in AI Trust Protocols check out one of our OSS projects https://t.co/QfOeBasufr
Our September NYC meetup is right around the corner.
Come join us for an evening of AI-powered commerce and sales:
โข Sylow Technologies Ethan Henley & Gianni Crivello will demo how agents can research merchants, build carts, and complete checkout with Lightning AIโs LitServe.
โข Jyoti Shah will share frameworks for GenAI-powered sales conversations that convert.
โข Lightning Fellow Jon Krohn will be emceeing the evening.
๐ September 30 | Lightning AI NYC HQ | 6:00 โ 8:30 PM
Food, drinks, and space are limited โ RSVP soon โ https://t.co/6ZQAy976NO
The next big UX unlock for agents is giving them the ability to safely transact across merchants. Iโm excited to share what @henl_ey and I have been working on for the past 5 months with the @LightningAI community. If youโre around in NYC on the 30th, come by!
Most infra wasnโt built for AI agents that need to handle payments.
Sylow is showing how to close that gap with Lightning AIโs LitServe โ agents that can interpret instructions, research merchants, assemble carts, and complete checkout.
See it live in NYC on Sept 30 โ https://t.co/6ZQAy976NO