OpenDisplay for Android got approved and is now in the Google Play Store! 🎉
So you can now easily use all your Android devices as an additional Monitor for your Mac & Linux machines.
this is pure f*cking treasure
how to build your first ai agent (full walkthrough)
if this had landed in front of me a year ago, my first agent would've shipped in an afternoon instead of eating two weeks of my life
in the right hands it resets what one person can ship alone:
Introducing https://t.co/6P1zo96By8
The open-source CRM for teams building with agents.
→ Every sign-up becomes a contact
→ Enriched with title and company
→ MCP server and REST API
→ One container, your Postgres, no seats
MIT licensed. Yours to run, change and keep.
Everyone is building sandboxes.
But a sandbox is only 10% of the infrastructure you need to run AI agents. You're left building the other 90% in-house: deployment, persistent state, monitoring, recovery, scaling
You're trying to sell agents. Somehow you're building a cloud.
Today we're launching Maritime out of YC F26 🚢
Maritime is a managed cloud for AI agents. We handle the infrastructure so you can focus on your product.
An open-source, self-hostable layer that turns your agents into a team working toward shared goals.
It's called Rowboat, and it can bring Claude Code, Codex, and Hermes into one team. Any agent that supports MCP can join too, so you stop being the glue between your AI agents.
You send one message, and a super agent:
- Decides which agents the job needs
- Asks your permission and creates them
- Hands each one a task
- Lets them pass work along in threads
- Builds the result with them on a shared whiteboard
What makes it different:
↳ Runs on the subscriptions or API keys you already have
↳ See every handoff, and step in whenever you want
↳ Or let Rowboat host your agents, if you'd rather not run servers
↳ Free to use
The video below shows it in action.
I loaded nine weeks of product data for a sample app into PostHog, a product analytics tool, and asked the super agent why new users weren't coming back. Hermes found where they dropped off in PostHog, Claude Code found why in the user feedback, and Codex built the dashboard.
Link to the GitHub repo in the first comment.
Introducing Dukoi.
Turn your old Android phone into a server in 2 minutes.
→ Install the app
→ Pair it with your laptop
→ Run dukoi deploy
Your app is live. No cloud. No bill.
Free and open source 👇
Laptops weren’t built for parallel agents.
Introducing @boxesdotdev (YC F26).
Run Claude Code and Codex in the cloud, on unlimited copies of your dev environment, with your existing subscriptions.
3 free months of Pro: https://t.co/mfA0LYOwzw
We just killed Slack, and open-sourced it.
Introducing Terminus Teams: we kept everything you like about Slack (channels, calls and meetings, threads) but kicked out the Slack bot, so you can use your existing Claude Code or Codex to read messages and even reply.
100% free, 100% open source, 100% customizable. Export your data anytime.
A voice model just got small enough to run inside a browser tab.
It's called Woof, from Underdog. One voice is 31.7 MB. Two voices are 40.6 MB.
No server. Once it's loaded, you can go offline and it keeps talking. I set my browser offline and recorded it.
What makes it interesting is the hard text. Phone numbers, dates, prices and codes are where small voice models fall apart. Woof runs everything through a text normalizer first.
Underdog's own numbers on 500 hard sentences:
- Two-voice Woof: 1.42% of words wrong
- Fish Audio Drama 3: 1.89% wrong, and a 41.5 GB download
- One-voice Woof: 2.06% wrong
So it's about 1,000x smaller, with similar accuracy on their test.
Link: https://t.co/MDZ6cXvqvc
Meet Tables for Claude Code and Codex.
> any list your agent makes becomes a real table
> search, sort, filter and edit it
> every change saves back to the file
Open source in Agentbox.
Need a Conductor replacement? Just use CompozyOS, it has much better features:
→ S-tier orchestration level
→ Always-on agents included
→ Built-in terminal
→ Loop engineering DAG system
→ Automations (jobs and triggers)
→ Multi-harness support in one place
and so much more...
CANCEL your weekend plans.
The 2027 meta just dropped. You NEED to:
• Build a computer-use agent that parses the DOM, diffs screenshots and maps clicks to coordinates so it can drive legacy software with zero APIs
• Ship generative UI where your LLM returns live React components instead of markdown blobs and watch your product feel 10 years newer
• Wire a System-One router that resolves 95% of requests in milliseconds for fractions of a cent, escalating only the hard 5% to reasoning models
• Kill your `while True` loop and rebuild it as a Temporal state machine that resumes from the exact node after a crash or a 3-day approval
• Write a raw MCP server in pure JSON-RPC so any external agent can call your product with scoped credentials, no SDK required
• Add grammar-constrained decoding so your agent emits 100% valid JSON on the first try, every try, forever
• Build a trajectory grader in CI that blocks the merge the second a tool-call sequence deviates from the golden path
• Ship an inter-agent sanitization proxy that executes prompt injections before they cross a single agent boundary
• Wire a PII unmasking proxy that swaps sensitive data for UUIDs before inference and restores it after with full audit logs
• Add a cost kill-switch that halts any loop projected to exceed $0.50 and degrades frontier → mid-tier → local → cache
• Implement KV-cache prefix sharing at the gateway and cut Time-To-First-Token by 80% on repeated system prompts
• Set up speculative decoding: local 3B drafts, frontier 70B verifies, acceptance rate logged on every single request
• Shadow-route 5% of production traffic to your new model, diff trajectories and cost silently, auto-post the report to Slack
• Automate the DPO flywheel: thumbs-down → preference pairs → nightly LoRA → eval-verified promotion, zero human touch
• Build a voice loop with VAD and sub-1s interruption handling, streaming tokens and tool calls simultaneously
• Ship an API-to-browser fallback that spawns a headless browser the moment a REST endpoint 404s, finishing the job anyway
• Add a WebGPU shim so a 2B model runs in the browser when the cloud dies and your users never see a spinner
• Fuzz your own agent swarm with malformed tool outputs and context overflow until it self-heals without a single pager alert
• Publish one benchmark: your system vs the naive baseline, on cost, latency and task success, fully reproducible
The wrapper era is over. The systems era pays.
You have way too much to do.
Bookmark & Repost.
modal gives every account $30 of GPU compute a month for free. that's 12 hours on an A100 80GB, or ~6.6 on an H200, billed per second.
the move: host your own open model as an openai-compatible API and point your coding agent at it.
1. sign up at https://t.co/W0Hie739um (github login works), starter plan is $0
2. pip install modal && modal setup
3. git clone https://t.co/qzOb5tfsD3
4. modal deploy modal-examples/06_gpu_and_ml/llm-serving/vllm_inference.py
5. it prints a URL. add /v1 and it's an openai-style endpoint serving gemma 4 26B on vLLM
6. add it as an openai-compatible provider in opencode, cline, or whatever you use
it scales to zero. no requests = no GPU bill.
catch: it stays warm 15 min after the last request, and that idle time eats credits. the example endpoint is unauthenticated, so add auth before you share the URL. a card is required, and anything past $30 gets billed.
what model would you host first?
Introducing the fully open-source alternative to Grok Bot, Dots and Duet.
Use Rerun with your ChatGPT and Claude subscriptions, or any other model.
Unlimited seats for FREE!
The mobile app will be available this week ⏳
Use for free : https://t.co/1sMyRAubn4