Ideas Lab
Real problems people complain about online, pulled every morning and scored out of 100. Build, validate, or skip. How scoring works
- Ideas
- 4,163
- BUILD
- 689
- Sources
- 8
- Last sync
- 7h ago
Twill.ai (YC S25) – Delegate to cloud agents, get back PRs
Hey HN, we're Willy and Dan, co-founders of Twill.ai (https://twill.ai/). Twill runs coding CLIs like Claude Code and Codex in isolated cloud sandboxes. You hand it work through Slack, GitHub, Linear, our web app or CLI, and it comes back with a PR, a review, a diagnosis, or a follow-up question. It loops you in when it needs your input, so you stay in control.Demo: https://www.youtube.com/watch?v=oyfTMXVECbsBefore Twill, building with Claude Code locally, we kept hitting three walls1. Parallelization: two tasks that both touch your Docker config or the same infra files are painful to run locally at once, and manual port rebinding and separate build contexts don't scale past a couple of tasks.2. Persistence: close your laptop and the agent stops. We wanted to kick off a batch of tasks before bed and wake up to PRs.3. Trust: giving an autonomous agent full access to your local filesystem and processes is a leap, and a sandbox per task felt safer to run unattended.All three pointed to the same answer: move the agents to the cloud, give each task its own isolated environment.So we built what we wanted. The first version was pure delegation: describe a task, get back a PR. Then multiplayer, so the whole team can talk to the same agent, each in their own thread. Then memory, so "use the existing logger in lib/log.ts, never console.log" becomes a standing instruction on every future task. Then automation: crons for recurring work, event triggers for things like broken CI.This space is crowded. AI labs ship their own coding products (Claude Code, Codex), local IDEs wrap models in your editor, and a wave of startups build custom cloud agents on bespoke harnesses. We take the following path: reuse the lab-native CLIs in cloud sandboxes. Labs will keep pouring RL into their own harnesses, so they only get better over time. That way, no vendor lock-in, and you can pick a different CLI per task or combine them.When you giv
Hacker News5mo agoToolAI
Druids – Build your own software factory
Hi HN!Druids (https://github.com/fulcrumresearch/druids) is an open-source library for structuring and running multi-agent coding workflows. Druids makes it easy to do this by abstracting away all the VM infrastructure, agent provisioning, and communication. You can watch our demo video here (https://www.youtube.com/watch?v=EVJqW-tvSy4) to see what it looks like.At a high level:- Users can write Python programs that define what roles the agents take on and how they interact with each other.- A program is made of events - clear state transitions that the agents or clients can call to modify state. Each event gets exposed as an agent tool.- Druids provisions full VMs so that the agents can run continuously and communicate effectively.We made Druids because we were making lots of internal coding tools using agents and found it annoying to have to rearrange the wiring every time.As we were building Druids, we realized a lot of our internal tools were easier to express as an event-driven architecture – separating deterministic control flow from agent behavior – and this design also made it possible to have many agents work reliably.We had issues with scaling the number of concurrent agents within a run, so we decided to have each program run in an isolated sandbox program runtime, kind of the same way you run a Modal function. Each agent then calls the runtime with an agent token, which checks who can talk to who or send files across VMs, and then applies the tool call.Our early users have found the library useful for:- running many agents to do performance optimization- building custom automated software pipelines for eg code review, pentesting, large-scale migrations, etc...We've heard that the frontier labs have the infrastructure to quickly spin up 100 agents and have them coordinate with each other smoothly in various ways. We're hoping that Druids can be a starting point to make that infrastructure more accessible.
Hacker News5mo agoToolDev
Hiring in the age of AI-assisted coding: what works?
I saw the HackerRank (YC S11) hiring post (https://news.ycombinator.com/item?id=47667011) and it made me realize I no longer understand how to evaluate candidates effectively.Specifically, we are changing hiring across 3 dimensions: > Tasks: Real-world tasks on code repositories vs standard algorithmic-style puzzles > Evaluation: AI fluency, orchestration skills vs functional correctness > Candidate experience: Agentic IDE vs a simple code editorIn the “old world,” you could ask multiple questions and triangulate skill from answers. Now it seems like evaluation depends heavily on tools and models that keep changing month to month.So I’m curious: > What signals actually correlate with strong engineers today? > How do you design interviews that don’t become obsolete with the next model release? > Are algorithmic interviews still useful at all?Would love to hear from people who have recently changed their hiring process or have been interviewed using this new approach.
Hacker News5mo agoToolAI
Marimo pair – Reactive Python notebooks as environments for agents
Hi HN! We're excited to share marimo pair [1] [2], a toolkit that drops AI agents into a running marimo notebook [3] session. This lets agents use marimo as working memory and a reactive Python runtime, while also making it easy for humans and agents to collaborate on computational research and data work.GitHub repo: https://github.com/marimo-team/marimo-pairDemo: https://www.youtube.com/watch?v=6uaqtchDnocmarimo pair is implemented as an agent skill. Connect your agent of choice to a running notebook with:/marimo-pair pair with me on my_notebook.pyThe agent can do anything a human can do with marimo and more. For example, it can obtain feedback by running code in an ephemeral scratchpad (inspect variables, run code against the program state, read outputs). If it wants to persist state, the agent can add cells, delete them, and install packages (marimo records these actions in the associated notebook, which is just a Python file). The agent can even manipulate marimo's user interface — for fun, try asking your agent to greet you from within a pair session.The agent effects all actions by running Python code in the marimo kernel. Under the hood, the marimo pair skill explains how to discover and create marimo sessions, and how to control them using a semi-private interface we call code mode.Code mode lets models treat marimo as a REPL that extends their context windows, similar to recursive language models (RLMs). But unlike traditional REPLs, the marimo "REPL" incrementally builds a reproducible Python program, because marimo notebooks are dataflow graphs with well-defined execution semantics. As it uses code mode, the agent is kept on track by marimo's guardrails, which include the elimination of hidden state: run a cell and dependent cells are run automatically, delete a cell and its variables are scrubbed from memory.By giving models full control over a stateful reactive programming environment, rat
Hacker News5mo agoToolAI
FluidCAD – Parametric CAD with JavaScript
Hello HN users,This is a CAD by code project I have been working on on my free time for more than year now.I built it with 3 goals in mind:- It should be familiar to CAD designers who have used other programs. Same workflow, same terminology.- Reduce the mental effort required to create models as much as possible. This is achieved by: - Provide live rendering and visual guidance as you type. - Allow the user to reference existing edges/faces on the scene instead of having to calculate everything. - Provide interactive mouse helpers for features that are hard to write by code: Only 3 interactive modes for now: Edge trimming, Sketch region extrude, Bezier curve drawing. - Implicit coding whenever possible: e.g: There are sensible defaults for most parameters. The program will automatically fuse intersecting objects together so you do not have to worry about what object needs to be fused with what. - It should be reasonably fast: The scene objects are cached and only the updated objects are re-computed.I think I have achieved these goals to a good extent. The program is still in early stages and there are many features I want to add, rewrite but I think it is already usable for simple models.Update to add more details: This is based on Opencascade.js WASM binding. So you get all the good things that come with any brep kernel. Fillets, chamfers, step import and export...The scene is webview but the editing is in your local file. You use your own editor and the environment you are familiar with.One important feature that I think make this stand out among other code based cad software is the ability to transform features not just shapes. More here: https://fluidcad.io/docs/guides/patterns You can see it in action in the lantern example: https://fluidcad.io/docs/tutorials/lantern
Hacker News5mo agoToolAI
CSS Studio. Design by hand, code by agent
Hi HN! I've just released CSS Studio, a design tool that lives on your site, runs on your browser, sends updates to your existing AI agent, which edits any codebase. You can actually play around with the latest version directly on the site.Technically, the way this works is you view your site in dev mode and start editing it. In your agent, you can run /studio which then polls (or uses Claude Channels) an MCP server. Changes are streamed as JSON via the MCP, along with some viewport and URL information, and the skill has some instructions on how best to implement them.It contains a lot of the tools you'd expect from a visual editing tool, like text editing, styles and an animation timeline editor.
Hacker News5mo agoToolAI
Keeper – embedded secret store for Go (help me break it)
Keeper is an embeddable secret store (Argon2id, XChaCha20-Poly1305 by default). Four security levels, audit chains, crash-safe rotation. Vault is overkill for most use cases. This is for when you ge paranoid about env and need encrypted local storage that doesn't suck. No security through obscurity, hence, It's still early, so now's the best time to find weird edge cases, race conditions, memory leaks, crypto misuse, anything that breaks. The README has a full security model breakdown if you want to get adversarial.
Hacker News5mo agoToolAI
Eve – Managed OpenClaw for work
Eve is an AI agent harness that runs in an isolated Linux sandbox (2 vCPUs, 4GB RAM, 10GB disk) with a real filesystem, headless Chromium, code execution, and connectors to 1000+ services.You give it a task and it works in the background until it's done.I built this because I wanted OpenClaw without the self-hosting, pointed at actual day-to-day work. I’m thinking less personal assistant and more helpful colleague.Here’s a short demo video: https://www.loom.com/share/00d11bdbe804478e8817710f5f53ac61The main interface is a web app where you can watch work happen in real time (agents spawning, files being written, use of the CLI). There's also an iMessage integration so you can fire a task asynchronously, put your phone down, and get a reply when it's finished.Under the hood, there's an orchestrator (Claude Opus 4.6) that routes to the right domain-specific model for each subtask: browsing, coding, research, and media generation.For complex tasks it spins up parallel sub-agents that coordinate through the shared filesystem. They have persistent memory across sessions so context compounds over time.I’ve packaged it with a bunch of pre-installed skills so it can execute in a variety of job roles (sales, marketing, finance) at runtime.Here are a few things Eve has helped me with in the last couple days:- Edit this demo video with a voice over of Garry: https://www.youtube.com/watch?v=S4oD7H3cAQ0- Do my tax returns- To build HN as if it was the year 2030: https://api.eve.new/api/sites/hackernews-2030/#/AMA on the architecture and lmk your thoughts :)P.S. I've given every new user $100 worth of credits to try it.
Hacker News5mo agoToolAI
Local businesses invisible in AI search recommendations
Small local businesses aren't recommended by AI search engines due to lack of organic mentions in online conversations.
X6mo agoOtherSEO & Geo
No detailed real-time tracker for all public transport trains
Riders can't check status of specific trains across all metro and train lines in real-time.
X6mo agoToolTransportation
Cumbersome mobile apps prevent quick expense logging
Finance organizers using Notion struggle to log quick street expenses as mobile app is too slow and hassle-filled.
X5mo agoToolFinance
Individuals sign complex documents without understanding them
Small businesses and individuals sign contracts, insurance, leases without comprehension due to lack of time, legal skills, or budget for experts.
X7mo agoToolLegal
Non-technical owners can't maintain custom AI-prompted business software
Businesses using vibecoded (AI-built) custom tools face ongoing issues with feature requests, bugs, and API changes, leading to frustration without developer support.
X8mo agoOtherAI
No way to loan unused AI compute tokens temporarily
AI users with surplus token quotas at certain times can't lend or borrow them to others facing shortages, leading to wasted capacity.
X5mo agoToolAI
Mobile banking apps have unreliable logins when roaming
Telco apps like Safaricom OneApp require re-login every time, specific SIM as primary with mobile data (not WiFi initially), and fail to detect number on secondary carrier data like Airtel.
X5mo agoToolFinance
AI video tools fail at character consistency
AI platforms like Pixverse are frustrating for creators as they alter custom characters (e.g., changing user's elf design) in generated videos, ruining workflows.
X5mo agoToolAI
Food delivery apps show unusable coupons
Delivery apps like Ifood display 'you have 13 coupons' but apply restrictive rules and bugs preventing any use, leading to constant frustration and poor ratings. (Translated from Portuguese)
X5mo agoToolLogistics & Delivery
Document scanning apps force cloud storage by default
Adobe scanning app defaults to storing scanned documents in their cloud, making it frustrating to simply scan and email locally without unwanted cloud involvement.
X5mo agoToolProductivity