Ideas Lab

Superlog (YC P26) – Observability that installs itself and fixes bugs

Hey HN, we’re Nico and Arseniy, co-founders of Superlog (https://superlog.sh). We're building a self-installing, self healing observability tool meant not to be opened. It has a wizard that daily sets up proper logging and an agent that investigates errors and opens PRs.Super short demo: https://www.youtube.com/watch?v=xFhU9Mk247M.In our earlier startups, we tried Sentry, Datadog, Grafana, Dash0, and nothing was good enough. Proper telemetry and alerting still requires a ton of manual setup. We struggled with adding good logs, so debugging was tough, especially as codebases grow at a faster pace. Meanwhile, the Datadog/Dash0 bill kept climbing, and we still spent engineering hours to learn, configure, and maintain our observability tooling.With Sentry, we found ourselves flooded by a stream of alerts into our Slack channel, most were duplicates or lacked context, so alert fatigue/constant interrupts were a real pain. The #ops notification is consistently the worst feeling on a Saturday morningWe’ve seen too many times servers run out of memory and disk, and three AWS metrics giving us three different values. Half of the graphs on dashboards are normally empty or outdated, and manually clicking through UIs, especially when the team is small, seems like a huge waste of time.At some point we realized that solving this problem would be more valuable than the things we had been working on, and we had the expertise to do it, since Arseniy had spent years at Datadog, getting paged during the night to debug production incidents. So we decided to build a platform that would just work: agent-first, MCP-native, zero-setup.Here’s how Superlog works: we have a wizard that scans your repo, and automatically instruments it with well-structured logs, traces and metrics via OpenTelemetry. We make sure to highlight main failure modes, endpoint performance, usage per tenant, and LLM/upstream cost (by callsite, tenant and model).Errors get

Hacker News5mo agoToolAI

Haystack – Review the PRs that need human attention

Hey HN! We're building Haystack (https://haystackeditor.com/) to help teams deal with the explosion in the number of pull requests that need to be reviewed due to the rise of coding agents.Haystack replaces the GitHub PR review system with a queue that triages each PR before a human has to read any diffs. It looks at the diffs, the codebase, and the coding-agent conversation that produced the PR. Haystack then routes it into one of three buckets:1. Safe to merge. This means the PR has enough evidence behind it that the team can merge it without another human's review.Some examples:-- A small UI copy change that includes a screenshot showing the final state-- A backend change where the author clearly tested the important paths and ran the changes in a real environment2. Needs fixes. This means that the PR has bugs or violates a rule in your codebase and therefore the PR needs to be fixed by the author.Some examples:-- The agent was asked to make loading a large table faster by adding pagination, but the PR still loads every result at once and "implements" pagination in the UI-- The PR silently catches an error instead of logging, surfacing, or handling it. This violates the team's "no silent error swallowing" rule3. Needs human review. This means that the PR could not be sufficiently verified by the author or is touching a sensitive part of the codebase (determined by user-input guidelines) and thus requires human review.Some examples:-- The PR changes a significant amount of logic in billing-- The PR changes an important user flow like onboarding, but the author only ran unit tests and never opened the app to check the flow end-to-end. That violates the team's rule that high-impact user-facing changes need manual verification.Instead of starting with line-by-line diffs, Haystack immediately tells the reviewer the goal behind the PR, what design decisions the author made (informed by their coding-agent conversati

Hacker News5mo agoToolAI

Semble – Code search for agents that uses 98% fewer tokens than grep

Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!

Hacker News5mo agoToolAI

85FL score

Ableton Live MCP

Ever wanted to control Ableton with just your voice? Me too! I made this MCP server so I could just ask Codex to do anything in Ableton Live for me, while I was nap-trapped by my baby.The chat messages I sent to Codex to make this:in ableton, make a self reflective song, with audio vocals (via macos say) and chip tunes and 80's drum machines. should be a real edm bangeri want midi for everything but vocals please, with ableton devices. not prerendered audio for instrumentsneeds some fillsand should hit way harder after "3-2-1 i become the sound"the vocals are squished too much (read too quickly), give them a little more lengthadd some dynamics, the song is basically one volume. and some pumping side chainimprove dynamics of the clap, seems a bit flat and indistinguished, want it harder after the 3-2-1 dropintroduce a new element on a new track after the 3-2-1 drop, that comes in but then recedes before the final exitdoesn't seem like the new thing has any notesthe element is a bit muddy/indistinct. perhaps it needs simplification and more space, different instrument choice, i dunno

Hacker News6mo agoToolAI

75FL score

Running the second public ODoH relay

Every privacy-focused DNS service requires an account: NextDNS, Cloudflare for Families, Apple's iCloud Private Relay (paid, iOS-only). The protocol that doesn’t require one - ODoH - had basically one well-known public relay operator (Frank Denis on Fastly Compute, default in dnscrypt-proxy). I built a second one and the client to talk to it.

Hacker News5mo agoToolAI

65FL score

GlycemicGPT – Open-source AI-powered diabetes management

I'm a Type 1 diabetic and software engineer. Last year I went months between endocrinologists with no clinician reviewing my data. I'm an engineer, so I built the tool I needed — and now I'm open sourcing it. GlycemicGPT is a self-hosted platform that connects continuous glucose monitors, insulin pumps, and existing Nightscout instances to an AI analysis layer running on your own infrastructure. Data sources:Dexcom G7 (cloud API) Tandem t:slim X2 and Mobi pumps (direct BLE) Nightscout (point it at your existing instance and you're running in minutes)What the AI layer does:Daily briefs summarizing overnight and 24-hour patterns Meal response analysis Conversational chat with RAG-backed clinical knowledge Predictive alerting with configurable thresholds and caregiver escalationImportant: this is monitoring and analysis only. GlycemicGPT does not deliver insulin, does not control your pump, and is not a closed-loop system. It reads your data and gives you insight on top of it. Your clinical decisions stay between you and your care team. Architecture:Self-hosted via Docker or K8S — the GlycemicGPT stack runs entirely on your hardware BYOAI — bring your own AI provider. Use Ollama for fully local operation (no data leaves your hardware), or point it at Claude, OpenAI, or any OpenAI-compatible endpoint if you prefer a hosted model. Data flows directly from your instance to the provider you choose; nothing is routed through any centralized service operated by the project. GPL-3.0, no subscriptions, no vendor lock-inStack:Backend API: FastAPI, Python 3.12, PostgreSQL 16, Redis 7 Web Dashboard: Next.js 15, React 19, Tailwind CSS, shadcn/ui AI Sidecar: TypeScript, Express, multi-provider proxy Android App: Kotlin, Jetpack Compose, BLE Wear OS: Kotlin, Wear Compose, Watch Face Push API Plugin SDK: Kotlin interfaces, capability-based, sandboxedLooking for contributors — especially folks with BLE/Android experience or anyone in the diabetes tech spa

Hacker News5mo agoToolAI

85FL score

Sx – an open-source package manager for AI skills, MCPs, and commands

Hacker News5mo agoToolAI

75FL score

Needle: We Distilled Gemini Tool Calling into a 26M Model

Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices.We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention is the right primitive for this, and FFN parameters are wasted at this scale.Simple Attention Networks: the entire model is just attention and gating, no MLPs anywhere. Needle is an experimental run for single-shot function calling for consumer devices (phones, watches, glasses...).Training: - Pretrained on 200B tokens across 16 TPU v6e (27 hours) - Post-trained on 2B tokens of synthesized function-calling data (45 minutes) - Dataset synthesized via Gemini with 15 tool categories (timers, messaging, navigation, smart home, etc.)You can test it right now and finetune on your Mac/PC: https://github.com/cactus-compute/needleThe full writeup on the architecture is here: https://github.com/cactus-compute/needle/blob/main/docs/simp...We found that the "no FFN" finding generalizes beyond function calling to any task where the model has access to external structured knowledge (RAG, tool use, retrieval-augmented generation). The model doesn't need to memorize facts in FFN weights if the facts are provided in the input. Experimental results to published.While it beats FunctionGemma-270M, Qwen-0.6B, Granite-350M, LFM2.5-350M on single-shot function calling, those models have more scope/capacity and excel in conversational settings. We encourage you to test on your own tools via the playground and finetune acc

Hacker News5mo agoToolAI

75FL score

Epiq – Distributed Git based issue tracker TUI

Issue trackers typically live outside of your workflow, with poor ergonomics. Epiq aims to solve that, bringing issue tracking into your terminal. Multi-user collaboration is achieved via git using user-scoped immutable event logs that converge in memory. Put my all into it. Let me know what you think.

Hacker News5mo agoToolAI

65FL score

AI-generated content sounds too robotic

Professionals and writers need a tool to make AI-generated responses and content sound more natural and less detectable as AI-drafted.

X5mo agoToolAI

SKIP

62FL score

AI verifier to check and fix other AIs' output

AI-generated work often has errors or 'shit work'; no dedicated AI exists solely to review, verify, and correct outputs from other AIs.

X5mo agoToolAI

62FL score

Cloud service for persistent AI agent runs without local machine

Developers running AI agents for UI changes or iterations have to keep their local computer half-shut/on all day; no simple cloud solution for continuous agent execution.

X5mo agoToolAI

Ardent (YC P26) – Postgres sandboxes in seconds with zero migration

Hey HN! We’re Vikram and Evan from Ardent (https://tryardent.com). We're building database sandboxes for you and your coding agents.In the last two years coding agents have gotten dramatically more capable at handling complex engineering tasks. But without access to a realistic sandbox at the DB layer for testing, they ship garbage that can take down production databases. I spent over a year building an AI Data Engineer that failed for this exact reason. Evan spent the last 12 years in data engineering and hit this wall building agents at his last company.Ardent was built to make it possible for coding agents to get near instant access to production-like sandboxes so they can test their work. To do this we write a replication stream out of the target DB, scaling with kafka onto a read replica with copy on write enabled and autoscaling compute (we currently prefer neon as a primary branching engine due to their implementation of these properties).Our replication stream uses logical replication + ddl triggers to enable usage on any hosted postgres DB since most platforms do not allow physical replication which is traditionally used for creating replicas.This provides a few primary benefits:1. Does not require a platform migration to a DB provider like neon, allowing strong separation of production and development concerns. 2. Minimal impact on the production database while allowing clones to spin up in <6s, even at TB scale with copy-on-writeSecurity matters a lot with cloning production so we run a proxy layer to generate custom postgres URLs and route all connections to allow more granular access control to clones, prevent credential leak, and follow a split plane architecture to allow full data residency on your cloud through BYOC.We also support anonymization through the ability to register SQL that runs on branches before they are returned. This has been used for PII redaction and branch modification.Our goal is to make every data infrastructure

Hacker News5mo agoToolAI

Statewright – Visual state machines that make AI agents reliable

Agentic problem solving in its current state is very brittle. I fell in love with it, but it creates as many problems as it solves.I'm Ben Cochran, I spent 20+ years in the trenches with full-stack Engineering, DevOps, high performance computing & ML with stints at NVIDIA, AMD and various other organizations most recently as a Distinguished Engineer.For agents to work reliably you either need massive parameter counts or massive context windows to keep the solution spaces workable. Most people are brute forcing reliability with bigger models and longer prompts.What if I made the problem smaller instead of making the model bigger?I took a different approach by using smaller models: models in the 13-20B parameter range and set them to task solving real SWE-bench problems. I constrained the tool and solution spaces using formal state machines. Each state in the machine defines which tools the model can access, how many iterations it gets and what transitions are valid. A planning state gets read-only tools. An implementation state gets edit tools (scoped to prevent mega edits) and write friendly bash tools. The testing state gets bash but only for testing commands. The model cannot physically skip steps or use the wrong tool at the wrong time. It is enforced via protocol, not via prompts.The results were more promising than I would have expected. Across multiple model families irrespective of age (qwen-coder, gpt-oss, gemma4) and the improvements were consistent above the 13B parameter inflection point. Below that, models can navigate the state machine but can't retain enough context to produce accurate edits. More on the research bit: https://statewright.ai/researchSurprisingly this yielded improvements in frontier models as well. Haiku and Sonnet start to punch above their weight and Opus solves more reliably with fewer tokens and death spirals. Fine tuning did not yield these kinds of functional improvements for me. The takeaway it se

Hacker News5mo agoToolAI

Voker (YC S24) – Analytics for AI Agents

Hey HN, we're Alex and Tyler, co-founders of Voker.ai (https://voker.ai/), an agent analytics platform for AI product teams. Voker gives full visibility into what users are asking of your agents, and whether your agents are delivering, without having to dig through logs. Our main product is a lightweight SDK that is LLM stack agnostic and purpose-built for agent products. (https://app.voker.ai/docs)Agent Engineers and AI product teams don’t have the right level of visibility into agent performance in production, which results in bad user experiences, churn, and hundreds of hours wasted with spot checks to find and debug issues with agent configurations.Demo: https://www.tella.tv/video/vid_cmoukcsk1000i07jgb4j65u67/vie...We recently conducted a survey of YC Founders and 90%+ of respondents said that the only way they know if their Agents are failing users in production is by hearing complaints from customers. They push a prompt change hoping that it fixes the problem and doesn’t break something somewhere else, and the cycle repeats.We saw tons of observability and evals products popping up to try to address these problems, but we still felt like something was missing in the agent monitoring stack. Obs is good for individual trace debugging but is only accessible to engineers. Evals are good for testing known issues, but don't give insights into trends that teams don’t expect, so engineers are always playing catch up. Traditional product analytics tools do a good job tracking clicks and pageviews across your product surface but weren’t built ground up for agent products. Knowing what users want out of agents, and whether the agent delivered requires specific conversational intelligence / unstructured data processing techniques.We came up with the agent analytics primitives of Intents, Corrections, and Resolutions to describe something pretty much all conversational agents had in common: a user will

Hacker News5mo agoToolAI

Agentic interface for mainframes and COBOL

Hi HN, we’re Sai and Aayush, and we’re building Hypercubic (https://www.hypercubic.ai/), bringing AI tools to the mainframe and COBOL world. (We did a Launch HN last year: https://news.ycombinator.com/item?id=45877517.) Today we’re launching Hopper, an agentic development environment for mainframes.You can download it here: https://www.hypercubic.ai/hopper, and you can also request access and immediately get a mainframe user account to play with.There's also a video runthrough at https://www.youtube.com/watch?v=q81L5DcfBvE.Mainframes still run a surprising amount of critical infrastructure: banking, payments, insurance, airlines, government programs, logistics, and core operations at large institutions. Many of these systems are decades old, but they continue to process enormous transaction volumes because they are reliable, secure, and deeply embedded into business operations.A lot of that software is written in COBOL and runs on IBM z/OS. The development environment looks very different from modern cloud or Unix-style development. Instead of GitHub, shell commands, package managers, and CI pipelines, developers often work through TN3270 terminal sessions, ISPF panels, partitioned datasets, JCL, JES queues, spool output, return codes, VSAM files, CICS transactions, and shop-specific conventions.TN3270 is the terminal interface used to interact with many IBM mainframe systems. ISPF is the menu and panel system developers use inside that terminal to browse datasets, edit source, submit jobs, and inspect output. It is powerful and reliable, but it was designed for expert humans navigating screens, function keys, and fixed-width workflows, not AI agents.A simple COBOL change might require finding the right source member, checking copybooks, locating compile JCL, submitting a job, reading JES/SYSPRINT output, interpreting condition codes, patching fixed-width source, and resubmitting.Much of this

Hacker News5mo agoToolAI

Gigacatalyst – Extend your SaaS with an embedded AI builder

Hi HN, I’m Namanyay from Gigacatalyst (link: https://gigacatalyst.com/). Gigacatalyst allows sales, CS, and users to build one-off features, so your SaaS can support long-tail customer workflows and engineers aren’t pulled away from the roadmap.When you sell software to large businesses, you realize that each customer needs their own workflow and features. Traditionally, this either means long engineering roadmaps or the customers end up using workarounds.But what if everyone could build their critical missing features just by talking to an AI? That’s what we do at Gigacatalyst. We provide an AI customization layer for your customers, CS team, and sales team to build these missing critical workflows without needing any engineers at all. Think Lovable, but built on top of YOUR platform.We connect to your product's APIs, learn your data model and design system, and let non-technical users build governed apps via natural language - inside your product, under your brand.Here’s what it looks like in action: https://www.youtube.com/watch?v=_taSpSphH6EOne of our customers, a Series B company, saw their users (not engineers - managers, ops people, facility directors) build critical workflows like:- Parts stockout prevention: A maintenance manager typed "show me which parts will run out in the next 2 weeks based on usage over the last 90 days, accounting for vendor lead times." The app tracks consumption velocity, forecasts stockouts, and alerts before it's too late. He says it's prevented ~$500K in emergency downtime.- Invoice OCR from phone photos: Technicians kept losing paper invoices. The prompt: "upload a photo of the invoice, extract vendor name, date, amount, and line items, then match it to the purchase order and flag discrepancies." Now techs snap a photo on-site to automatically add to the system of record.- Restaurant emergency triage: A pizza chain's facilities manager was drowning in maintena

Hacker News5mo agoToolAI

Users cannot generate AI images offline on iPhones due to reliance on cloud services

AI image generation typically requires internet and cloud processing, limiting offline use on mobile devices like iPhones; need local, offline capability.

X5mo agoToolAI

62FL score

Unknown reasons AI systems don't recommend products

Founders struggle to understand and diagnose why AI systems like search engines or agents hesitate to recommend or cite their websites and products, missing out on AI-driven traffic.

X5mo agoToolAI