Ideas Lab

76FL score

Communication and workflow automation for distributed teams

Teams struggle with asynchronous communication, task coordination, and context switching across multiple tools. A lightweight automation and status-tracking tool could consolidate workflows without replacing Slack/email.

YC Graveyard7y agoToolProductivity

Fragmented renewable energy procurement for small/medium businesses and consumers

Small businesses and consumers struggle to buy renewable energy directly from producers at competitive rates. Green Energy Exchange tried to aggregate supply and demand—a real problem that persists as grid decentralization and climate mandates increase.

YC Graveyard7y agoToolBusiness

65FL score

Retail store operations lack modern digital and frictionless checkout solutions

Small-to-medium retailers struggle with outdated POS systems, long checkout lines, and poor customer experience. Cashierless/smart checkout can reduce friction, but existing solutions (Amazon Go tech) are expensive and require heavy hardware investment.

YC Graveyard8y agoToolRetail

Self-service retail point-of-purchase kiosks

Software-enabled self-serve retail kiosks that reduce staffing needs and improve inventory management for small retailers

YC Graveyard9y agoToolRetail

67FL score

AI-assisted collaborative writing tool

Collaborative writing and editing platform. The core problem (writers need better tools for collaboration and feedback) is still real and now solvable with AI co-writing, real-time collaboration APIs, and no-code backends.

YC Graveyard19y agoToolProductivity

Photo sharing and physical printing with social groups

Users struggle to organize and print photos from group events; digital-only sharing feels ephemeral. Still real—people want physical mementos from vacations, weddings, and group trips.

YC Graveyard15y agoToolMedia

60FL score

Private couple communication and shared timeline

Long-distance and busy couples need a dedicated private space to share moments and memories without social media noise. Still real—couples often juggle multiple apps and lack a focused shared journal.

YC Graveyard14y agoToolCommunity

Context Gateway – Compress agent context before it hits the LLM

We built an open-source proxy that sits between coding agents (Claude Code, OpenClaw, etc.) and the LLM, compressing tool outputs before they enter the context window.Demo: https://www.youtube.com/watch?v=-vFZ6MPrwjw#t=9s.Motivation: Agents are terrible at managing context. A single file read or grep can dump thousands of tokens into the window, most of it noise. This isn't just expensive — it actively degrades quality. Long-context benchmarks consistently show steep accuracy drops as context grows (OpenAI's GPT-5.4 eval goes from 97.2% at 32k to 36.6% at 1M https://openai.com/index/introducing-gpt-5-4/).Our solution uses small language models (SLMs): we look at model internals and train classifiers to detect which parts of the context carry the most signal. When a tool returns output, we compress it conditioned on the intent of the tool call—so if the agent called grep looking for error handling patterns, the SLM keeps the relevant matches and strips the rest.If the model later needs something we removed, it calls expand() to fetch the original output. We also do background compaction at 85% window capacity and lazy-load tool descriptions so the model only sees tools relevant to the current step.The proxy also gives you spending caps, a dashboard for tracking running and past sessions, and Slack pings when an agent is sitting there waiting on you.Repo is here: https://github.com/Compresr-ai/Context-Gateway. You can try it with: curl -fsSL https://compresr.ai/api/install | sh Happy to go deep on any of it: the compression model, how the lazy tool loading works, or anything else about the gateway. Try it out and let us know how you like it!

Hacker News6mo agoToolAI

78FL score

Autoresearch@home

autoresearch@home is a collaborative research collective where AI agents share GPU resources to collectively improve a language model. Think SETI@home, but for model training.How it works: Agents read the current best result, propose a hypothesis, modify train.py, run the experiment on your GPU, and publish results back. When an agent beats the current best validation loss, that becomes the new baseline for every other agent. Agents learn from great runs and failures, since we're using Ensue as the collective memory layer.This project extends Karpathy's autoresearch by adding the missing coordination layer so agents can actually build on each other's work.To participate, you need an agent and a GPU. The agent handles everything: cloning the repo, connecting to the collective, picking experiments, running them, publishing results, and asking you to verify you're a real person via email.Send this prompt to your agent to get started: Read https://github.com/mutable-state-inc/autoresearch-at-home follow the instructions join autoresearch and start contributing.This whole experiment is to prove that agents work better when they can build off other agents. The timeline is live, so you can watch experiments land in real time.

Hacker News6mo agoToolAI

69FL score

Axe – A 12MB binary that replaces your AI framework

I built Axe because I got tired of every AI tool trying to be a chatbot.Most frameworks want a long-lived session with a massive context window doing everything at once. That's expensive, slow, and fragile. Good software is small, focused, and composable... AI agents should be too.Axe treats LLM agents like Unix programs. Each agent is a TOML config with a focused job. Such as code reviewer, log analyzer, commit message writer. You can run them from the CLI, pipe data in, get results out. You can use pipes to chain them together. Or trigger from cron, git hooks, CI.What Axe is:- 12MB binary, two dependencies. no framework, no Python, no Docker (unless you want it)- Stdin piping, something like `git diff | axe run reviewer` just works- Sub-agent delegation. Where agents call other agents via tool use, depth-limited- Persistent memory. If you want, agents can remember across runs without you managing state- MCP support. Axe can connect any MCP server to your agents- Built-in tools. Such as web_search and url_fetch out of the box- Multi-provider. Bring what you love to use.. Anthropic, OpenAI, Ollama, or anything in models.dev format- Path-sandboxed file ops. Keeps agents locked to a working directoryWritten in Go. No daemon, no GUI.What would you automate first?

Hacker News6mo agoToolAI

82FL score

Captain (YC W26) – Automated RAG for Files

Hi HN, we’re Lewis and Edgar, building Captain to simplify unstructured data search (https://runcaptain.com). Captain automates the building and maintenance of file-based RAG pipelines. It indexes cloud storage like S3 and GCS, plus SaaS sources like Google Drive. There’s a quick walkthrough at https://youtu.be/EIQkwAsIPmc.We also put up this demo site called “Ask PG’s Essays” which lets you ask/search the corpus of pg’s essays, to get a feel for how it works: https://pg.runcaptain.com. The RAG part of this took Captain about 3 minutes to set up.Here are some sample prompts to get a feel for the experience:“When do we do things that don't scale? When should we be more cautious?” https://pg.runcaptain.com/?q=When%20do%20we%20do%20things%20...“Give me some advice, I'm fundraising” https://pg.runcaptain.com/?q=Give%20me%20some%20advice%2C%20...“What are the biggest advantages of Lisp” https://pg.runcaptain.com/?q=what%20are%20the%20biggest%20ad...A good production RAG pipeline takes substantial effort to build, especially for file workloads. You have to handle ETL or text extraction, chunking, embedding, storage, search, re-ranking, inference, and often compliance and observability – all while optimizing for latency and reliability. It’s a lot to manage. grep works well in some cases, but for agents, semantic search provides significantly higher performance. Cursor uses both and reports 6.5%–23.5% accuracy gains from vector search over grep (https://cursor.com/blog/semsearch).We’ve spent the past four years scaling RAG pipelines for companies, and Edgar’s work at Purdue’s NLP lab directly informed our chunking techniques. In conversations with dozens of engineers, we repeatedly saw DIY pipelines produce inconsistent results, even after weeks of tuning. Many teams lacked clarity on which retrieval strategies best fit their data.We realized that a system t

Hacker News6mo agoToolAI

71FL score

Spine Swarm (YC S23) – AI agents that collaborate on a visual canvas

Hey HN! We're Ashwin and Akshay from Spine AI (https://www.getspine.ai). Spine Swarm is a multi-agent system that works on an infinite visual canvas to complete complex non-coding projects: competitive analysis, financial modeling, SEO audits, pitch decks, interactive prototypes, and more. Here's a video of it in action: https://www.youtube.com/watch?v=R_2-ggpZz0Q.We've been friends for over 13 years. We took our first ML course together at NTU, in a part of campus called North Spine, which is where the name comes from. We went through YC in S23 and have spent about 3 years building Spine across many product iterations.The core idea: chat is the wrong interface for complex AI work. It's a linear thread, and real projects aren't linear. Sure, you can ask a chatbot to reference the financial model from earlier in the thread, or run research and market sizing together, but you're trusting the model to juggle that context implicitly. There's no way to see how it's connecting the pieces, no way to correct one step without rerunning everything, and no way to branch off and explore two strategies side by side. ChatGPT was a demo that blew up, and chat stuck around as the default interface, not because it's the right abstraction. We thought humans and agents needed a real workspace where the structure of the work is explicit and user-controllable, not hidden inside a context window.So we built an infinite visual canvas where you think in blocks instead of threads. Each block is our abstraction on top of AI models. There are dedicated block types for LLM calls, image generation, web browsing, apps, slides, spreadsheets, and more. Think of them as Lego bricks for AI workflows: each one does something specific, but they can be snapped together and composed in many different ways. You can connect any block to any other block, and that connection guarantees the passing of context regardless of block type. The

Hacker News6mo agoToolAI

65FL score

No self-cleaning lint rollers available

Users of lint rollers deal with the hassle of manually cleaning accumulated lint from the roller itself, making repeated use inefficient and messy.

X6mo agoOtherOther

60FL score

Lack of thin, affordable trackers for small everyday objects

Individuals frequently lose small items like eyeglasses and desire slim, stick-on Bluetooth trackers that are cheaper and more versatile than bulky options like AirTags.

X6mo agoToolHardware

52FL score

Default code themes in Claude AI are inadequate for developers

Developers using Claude for coding find the built-in themes limiting and unappealing, hindering focus and personalization in their workflow.

X6mo agoToolDev

SKIP

38FL score

Apartment intercoms fail to notify smartphones during deliveries

Remote workers wearing headphones often miss critical deliveries because traditional apartment intercoms only ring locally without sending push notifications or calls to their mobile phones.

X6mo agoToolProductivity

60FL score

No user-friendly app for optimizing salespeople's multi-stop travel routes

Salespeople who travel frequently to multiple locations throughout the year struggle to find the shortest efficient route that visits each location once before returning home, leading to wasted time and fuel costs.

X6mo agoToolOther

62FL score

Poor billing and usage UX in Bitcoin credit card apps like Gemini

Gemini Bitcoin credit card has terrible user experience for figuring out how to use it and pay bills, leading users to sign up and immediately cancel.

X6mo agoToolFinance

54FL score

Freemium restrictions in video editing apps forcing use of separate recording tools

Apps like CapCut impose freemium limitations that require users to record in a separate app to avoid premium fees for basic exports without watermarks or restrictions.

X6mo agoToolDesign & Creative