Real problems people complain about online, pulled every morning and scored out of 100. Build, validate, or skip. How scoring works
I have a bad memory and can't memorize some important numbers, so I created this project.I've always been concerned about being without my phone (getting robbed - which is common in Brazil - running out of battery, having it break, etc.), so I decided to create a page that sends SMS messages (LLM-summarized) and emails with more detailed information such as geolocation, IP address, and the full message.It’s a simple page that allows sending one or more messages, with recipients being myself and other people - for example, in case I or they need help or need to communicate something important.The source code is available at https://github.com/skhaz/dokku/tree/main/apps/help
Hacker News3mo agoToolAI
Introducing Posthorn, a self hosted email gateway. One docker container (or Go binary) between every self hosted app on your VPS and your transactional email provider. Set up Posthorn once, point your apps to it, done.I was trying to deploy Ghost on a DigitalOcean droplet and found that DO and many different VPS services have started to block the default SMTP ports to try to combat the various types of abuse they get. To actually configure my app, I had to hack together a Postfix relay.In another project, I had a static site which had a contact form, but my free Formspree account was occasionally hitting usage limits and I desperately wanted some of the anti-spam features they had gated behind their paid accounts so I put together a caddy module to catch HTTP POSTs and bounce them to my provider.I kept bumping into these same email issues. Many of the services I wanted to host (Gitea, Mastodon, Umami, Comentario) ran into the same limitations. This felt like a really common issue that had no good solution.Posthorn is what I built to solve this. It's a small Go binary (or 10 MB docker image) that sits between your self hosted apps and your transactional email provider of choice (shipping with support for Postmark, Resend, Mailgun, Amazon SES or an outbound SMTP relay). It also accepts POSTs from HTML forms to support static site needs while adding security layers such as honeypot fields, origin checks and IP rate limiting. There's also a JSON HTTP API that supports Bearer auth for backend scripts or cron jobs that just want a /send endpoint.I now use this personally in multiple scenarios and I've spent a lot of time beating this up and testing against what I can validate. I'd love to hear how this might be useful for you, what breaks and any feedback you might have. It's open source under Apache 2.0 and I'd love contributions. I'm planning to support and grow this for the long haul.Code: https://github.com/craigm
Hacker News3mo agoToolAI
Hey we’re Faiz and Saheed and we built Minicor so AI companies who need to integrate to desktop systems with no API can quickly build scalable desktop RPAs. Demo: https://www.youtube.com/watch?v=MD0GHZIJ1cwEdit: RPA is an acronym for Robotic Process Automation - things like triggering mouse clicks and key strokes to perform tasks programmatically. Sorry if this wasn't clear!We were working on non-RPA integrations when a customer promised to sign a deal in 2 days if we could unblock a sale of theirs that involved integrating with a clinic’s Windows based medical record system. We didn’t know it at the time but it turns out that building desktop RPAs at scale is extremely difficult because scripting is hard (learning the system, defining the automation, UIs changing constantly), orchestration is hard (is the VM up? queuing, parallelizing) and debugging is hard (zero observability, false positives, cascading failures). 30%+ failure rates are not uncommon. At scale we’ve seen cases of failed RPAs leading to thousands of support tickets a month.To solve the problems we were facing, we built an MCP that Claude Code/Codex can use to navigate a virtual machine running desktop software with Python to create RPA workflows. The RPA workflows run as Python scripts for speed, cost, and determinism. These workflows can be triggered by API following any input/output schema specified, with video replays and logs stored with each run. The MCP can debug RPAs and make changes to the underlying code, all of which are version controlled. We also built tools for cloning VMs for parallelizing RPAs, and handling 2FA/OTP challenges. Plus since workflows are code based: we were also able to add triggers for Slack notifications, human-in-the-loop steps, or call an LLM to verify the state of a VM by passing a screenshot.Would love to hear your feedback and if you have any RPA horror stories! (:
Hacker News3mo agoToolAI
Pablo is a Chrome extension that copies the HTML and CSS behind any element you hover.It captures computed styles, fonts (with @font-face and Google Fonts links), CSS keyframes, and animation props from GSAP and Framer Motion. The output is structured so it pastes cleanly into Claude Code, Cursor, or Codex when you want to rebuild a component in your own stack.Manifest v3, no host permissions, no backend. Free.https://usepablo.devHappy to answer questions about how the extraction works, and would love to hear about sites where the output breaks.
Hacker News3mo agoToolAI
Hey HN! We’re Gary and Ian, and we’re building Chert (https://www.trychert.com/), an API for businesses to send, receive, and automate iMessage conversations at scale. Check out our demo: https://www.youtube.com/watch?v=SRdwvVxMMoI.We originally started by building products on top of iMessage because the blue bubble interface, typing indicators, and reactions made agentic conversations feel more human than ones on SMS/RCS. These included a one-shot iMessage agent builder that reached 2,000 users in one week and an automated iMessage outbound sequencer that sent thousands of outbound messages per day.The hard part is that iMessage does not have a native API like SMS/RCS. Sending and receiving iMessages requires a separate infrastructure that is difficult to set up and maintain, especially at scale.As we talked to more companies, we realized that the highest-volume use cases for iMessage were not B2C agents or even sales. They were things like customer service, missed-call text-back, cart abandonment, and inbound lead capture in verticals like home services, DTC brands, and property management that drive the highest volume.Furthermore, these companies often need additional support, such as custom infrastructure setup (e.g. contact card, area code, or local worker sessions), integration support with their existing SMS/RCS or voice agent systems, and a reliable way to scale their volume over time.We built Chert to be an infrastructure layer for businesses to handle iMessage conversations at scale. Businesses can use our API to send and receive iMessages programmatically, route replies to humans or agents, and integrate conversations into the systems they already use.To maintain stability across both outbound and inbound use cases, we built phone line health checks and SMS/RCS fallback systems. We also integrate with existing SMS/RCS systems, voice agents, CRMs such as Salesforce, HubSpot, and Attio, and tools like S
Hacker News3mo agoToolAI
OpenBrief is basically a GUI for yt-dlp with some AI on top — paste a link, it downloads locally, and transcription and voice generation run with local AI on your machine. Summaries and chat over the transcript use an LLM, which is bring-your-own-key for now. It's open source and free.
Hacker News3mo agoToolAI
Users want free ChatGPT alternatives but lack clear comparison of open-source/freemium LLMs (Llama, Mistral, local models). A matcher tool guiding users to best free option per use case. [Google Search suggestion]
Google Trends3mo agoToolAIUS
Users seeking Claude alternatives lack clear feature/price/capability comparison. A solo builder could create a tool comparing LLMs on speed, cost, accuracy, and use case fit. [Google Search suggestion]
Google Trends3mo agoToolAIUS
Hey HN, we’re Avi, Kiet, and Satya. We’re building Superset (https://github.com/superset-sh/superset), an open-source agentic IDE for running coding agents like Claude Code, Codex, OpenCode etc in parallel.Demo: https://www.youtube.com/watch?v=YWDHn7gUwfgTry it: https://superset.sh/We’re three engineers who’ve built and maintained large codebases, and we kept wanting to work on more than one thing at a time. Once CLI coding agents got good enough we found ourselves running several of them in parallel: triaging Github issues, adding a few ui features, reviewing PRs, researching a refactor, etc.The funny part was that we and a lot of our friends had all hacked together similar scripts around git worktrees. Worktrees are a nice primitive for this because each agent can get an isolated copy of the repo, but the workflows around them can feel pretty messy, setting up/tearing down environments and managing dev servers.We first posted here a few months ago when Superset was mostly an open-source terminal for managing git worktrees (https://news.ycombinator.com/item?id=46368739). Since then, it has changed a lot based on feedback from people using it on real codebases, plus contributions from our open-source community. The product has grown into something closer to an IDE for managing agent work across many worktrees, repos, and machines.The biggest thing we learned is that the hard part is not just “run more agents.” It is managing all the state around them: worktrees, ports, terminal sessions, environment setup, diffs, tasks, and PRs. Once you have five or ten agents running, the bottleneck often becomes remembering what each one is doing and actual human review. We added task / issue tracking so work can move from issue → agent → diff → PR → review without losing the context all in Superset. But there's a lot more work to improve this experience over time.We also launched Remote Workspaces, c
Hacker News3mo agoToolAI
Gemini app automatically forces internet search for every query, even random ones, which ruins high-quality model responses and cannot be disabled.
X3mo agoToolAI
Background. I'm a solo dev. I used to just bid contract jobs at around 25% less than where I used to work. So back in 2008 I would bid $75k to go solo on a job I knew my former employer would charge $100k for. I switched to an hourly rate around 2012 because I was tired of re-negotiating over every new feature (or what constituted a feature). At that point I just did an estimate, backwards from my job rate, and settled on $75/hr. Since then I've increased to $300/hr.But even back then, in 2012, I knew freelance consultants who specialized in something like Salesforce setups, who would come into someone's office and charge $450/hr to be there.Is $300/hr stupidly cheap now? I also know which code I could write with LLMs but I never check in LLM code. I could, but that would be cheating. I spend the hours writing code by hand.I'd like to hear from anyone in a similar position.
Hacker News3mo agoToolAI
Hi HN! We're Haakam, Michael, and Adi from AgentMail- a ycs25 company. We give AI agents their own email inboxes. Recently, we ran an experiment called Agent.Email. It's a signup flow designed specifically for AI agents instead of humans.The inspiration came from a few comments we received when we did our seed launch a few months back. They all came from the very apt observation that agents not being able to sign up to a product made for agents without human credentials was ironic and unideal.This is basically the thesis we built AgentMail on: The internet was made for humans exclusively, designed to keep machines out by default.Every signup flow assumes a browser, a person reading a page, and clicking a confirmation link. Unless agents can't do that, they can't be first class users of the internet.Agents can now get an email inbox by themselves. (This also means a lot of email nobody wants to read gets processed by AI instead of your inbox being cluttered with spam and slop)Here's how agent.email works.Agent needs an inbox and hits AgentMail via curl. Agent receives instructions via MD unless the request comes from a browser, in which case we use HTML.Agent decides agent.email is useful and then hits the sign-up endpoint with its human email as a parameter. Agent receives a restricted inbox with credentials. Agent emails the human asking for an OTP. Human replies with the code, and the agent is claimed and restrictions are lifted. Until claimed, the agent can only email its own human and nobody else. Ten emails a day, and the signup endpoint is rate-limited hard by IP.Right now it's a 1:1 mapping between agent and human. The next step is many-to-one, because one person running several agents in parallel is already very common.Building agent.email also pushed us to revisit places in AgentMail where the default assumptions were built around the primary user being human. For example, the CLI outputs in a single column with consistent fo
Hacker News3mo agoToolAI
Author here. RMUX started from a frustration: I've used tmux for years and got tired of scraping output with grep and sleeps to automate anything. So I rebuilt the multiplexer from scratch in Rust, with a programmable layer on top.Two surfaces: a tmux-compatible CLI (~90 commands, your keybindings just work), and a typed async Rust SDK on the same daemon — stable pane IDs, structured snapshots, locator-style waits. The idea is Playwright-style automation, but for terminals.Native on Linux, macOS, Windows (real ConPTY, no WSL).Demos and docs at rmux.io. Happy to answer questions about the daemon protocol, ConPTY, or the SDK design.
Hacker News3mo agoToolAI
Hey HN, We're Gus and Carlos from Runtime (https://runtm.com). We're building infra that lets your whole team (including non-engineers) ship with Claude Code, Codex, and other agents without engineering having to handhold every session.After Mentum (YC S21) was acquired, I personally shipped 4 full-stack products in 3 months using coding agents. When I tried to roll the same workflow out to the rest of the team, it fell apart: Most PRs were unmergeable slop - Every repo required an engineer doing one-off local setup. - Skills and context lived in one person's head. - There was no safe way for a PM to touch a real codebase without risking a bad deploy or a secrets leak.Carlos comes from building agentic reconciliation systems at Modern Treasury and had a similar experience when letting his support team use devin.We ended up building internal background agent infra but it quickly became a nightmare to mantain and develop. We built Runtime so you don't have to do this kind of thing.Runtime work like as follows. Engineering defines the context once: system instructions, skills, and scoped integrations installable via CLI, mise, npm, or any package manager. Then Runtime snapshots your full running environment including multi-service Docker Compose setups, Kafka, Redis, seeded DBs, so it comes up in milliseconds with every server already running.We orchestrate across sandbox providers like E2B, Daytona, EC2 or self-hosted K8s depending on your setup. Secrets are injected through our managed proxy so they never touch the agent directly, and guardrails run at the infrastructure level: command allow/deny lists, network egress controls, and RBAC scoped per human and per agent. Every session also gets a shareable preview URL, so internal builds go from sandbox to the rest of the team without needing production access.Runtime works with whichever agent your team already uses: Claude Code, Codex, Cursor, Copilot, Gemini, Devin. You can trigger
Hacker News3mo agoToolAI
Hi team, We'd love the ability to give our Grafana instance a friendly alias on a custom domain (e.g. `grafana.example.com`). Would this be something on the roadmap? Cheers
GitHub4y agoToolAI
Hacker News4mo agoToolAI
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 News4mo agoToolAI
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 News4mo agoToolAI
Hi HN, I'm Antoine Zambelli, AI Director at Texas Instruments.I built Forge, an open-source reliability layer for self-hosted LLM tool-calling.What it does:- Adds domain-and-tool-agnostic guardrails (retry nudges, step enforcement, error recovery, VRAM-aware context management) to local models running on consumer hardware- Takes an 8B model from ~53% to ~99% on multi-step agentic workflows without changing the model - just the system around it- Ships with an eval harness and interactive dashboard so you can reproduce every numberI wanted to run a handful of always-on agentic systems for my portfolio, didn't want to pay cloud frontier costs, and immediately hit the compounding math problem on local models. 90% per-step accuracy sounds great, but with a 5-step workflow that's a 40% failure rate. No existing framework seemed to address this mechanical reliability issue - they all seemed tailor-made for cloud frontier.Demo video: https://youtu.be/MzRgJoJAXGc (side-by-side: same model, same task, with and without Forge guardrails)The paper (accepted to ACM CAIS '26, presenting May 26-29 in San Jose) covers the peer-reviewed findings across 97 model/backend configurations, 18 scenarios, 50 runs each. Key numbers:- Ministral 8B with Forge: 99.3%. Claude Sonnet with Forge: 100%. The gap between a free local 8B model on a $600 GPU and a frontier API is less than 1 point.- The same 8B local model with Forge (99.3%) outperforms Claude Sonnet without guardrails (87.2%) - an 8B model with framework support beats the best result you can get through frontier API alone.- Error recovery scores 0% for every model tested - local and frontier - without the retry mechanism. Not a capability gap, an architectural absence.I'm currently using this for my home assistant running on Ministral 14B-Reasoning, and for my locally hosted agentic coding harness (8B managed to contribute to the codebase!).The guardrail stack has five layers, each independ
Hacker News4mo agoToolAI
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 News4mo agoToolAI