Results for low code · 1.360s

Sponsored
News for “low code”
19 results • 1351 ms server time
Ask HN: Are LLMs slowly making companies dysfunctional?IMAGE
news.ycombinator.com• Jul 7, 2026• 1 min read
Ask HN: Are LLMs slowly making companies dysfunctional?LLMs are great. They can quickly one-shot plausible solutions for many problems. This makes companies push hard to offload rising cognitive demands to LLMs.It doesn't make much sense to invest effort into verifying a plausible-looking throwaway solution that is reviewed and smoke-tested by an LLM, with a quick glance from a tired human.This results in complexity creep everywhere: decisions, communication, code, documentation, etc.On par with cognitive debt, as thinking and decision refinement were offloaded, nobody gained unique experience solving a niche use case. This is equal to having a knowledgeable person leave the company before the knowledge transfer occurred. All you're left with is a legacy of someone else's assumptions and decisions you'll never be fully aware of.I already see it happening. In support, LLMs never solved any of my support requests. Support, which should know the product inside out, recommends visiting pages and clicking buttons that are hallucinated and don't
Show HN: Metaspec: The DpANS3R Common Lisp Spec in S-Expr and HTML FormatIMAGE
metaspec.dev• Jun 24, 2026• 1 min read
Show HN: Metaspec: The DpANS3R Common Lisp Spec in S-Expr and HTML FormatI started this project back in 2015, to translate the TeX original specification into an easily parsed format (s-doc), and to create an HTML rendering of that format as a proof of concept.The project is homed here: https://codeberg.org/dlowe/metaspectre/Differences from the Hyperspec (from the README): - Most importantly, it is free to modify and distribute. - The original TeX is very hard to parse and use for things other than generating a printed copy. The Hyperspec is an HTML rendering which can be parsed as HTML, but loses a lot of information. The Metaspec has an easily parsed intermediate form that can be used for all kinds of purposes, like converting into lookups. - Math equations are rendered using MathML. - Includes the acknowledgements and appendix sections. - Uses progressively enhanced Javascript to provide search and light/dark theme switching. - Incorporates over 145 patches for content, using corrections accumulated over the years, and documented in the errata page. - I
Show HN: eBook to audiobook narration with realistic AI voicesIMAGE
ebookaloud.com• Jun 24, 2026• 1 min read
Show HN: eBook to audiobook narration with realistic AI voicesFor a while I've wanted to try out the new AI voices for long-form narration, but everything I found required a subscription that didn't justify my limited usage. I came across the open Kokoro model [0] and the voices are very good -- good enough to listen to for hours without the fatigue I got from legacy, robotic TTS voices. The model is 82m parameters and designed to run fast, but I still struggled to get reasonable times from CPU inference on my 12-core laptop. I thought a cloud-based GPU service would let me generate audiobooks fast enough to feed my own self-hosted library, and that same pipeline could become a product other people could use.I had two goals in building this: get some exposure to AI multi-agent coding workflows, and build a TTS product targeting ebook to audiobook conversion specifically. 99% of ebookaloud was written by DeepSeek v4 in OpenCode. I've used about 750 million tokens costing $12 in credits over the course of a month, and I'm very pleased with the resu
Show HN: A policy gate that runs before your AI coding agent's tool callsIMAGE
sigmashake.com• Jun 16, 2026• 1 min read
Show HN: A policy gate that runs before your AI coding agent's tool callsAs a Security Engineer with over 10+ years in industry, I kept running into the same problem with coding agents: Instructions are not guarantees.I put guidance in `CLAUDE.md`, `AGENTS.md`, memory files, MCP descriptions, and tool documentation. I explicitly told the agent things like:- Use the code graph for architecture questions instead of grepping the repository. - Do not use deprecated APIs or Unsafe code. - Prefer specific tools for specific tasks.The agent would still ignore those instructions surprisingly often. It would grep the entire repo, use deprecated APIs, or choose a slower tool even when a better one was available.That made me realize prompts and rules solve different problems.A prompt is a probabilistic influence on model behavior. A rule is an enforcement mechanism.So I built SSG (SigmaShake Governance), which sits between the agent and its tools. Instead of asking the model to remember a policy, SSG evaluates every tool call before it executes.For example, this rule
We aren't getting to AGI without a fightIMAGE
news.ycombinator.com• Jun 13, 2026• 1 min read
We aren't getting to AGI without a fightI think I realized why I am so angry about the fable takedown. It's because I realize we aren't getting to AGI without a fight. This is the powerful closing ranks to keep capability centralized. This is the ceiling of model capability which we will be allowed to use. Greater capability will exist but it will be gated behind clearances, vetting and power. Reportedly, Amazon relayed these jailbreaks to the administration. Any investment Amazon has in Anthropic is dwarfed by its investment in AWS. The Anthropic investment was likely a hedging of risk and a seat on the board so they could do exactly what they just did.I've had a large project on the back burner for quite a while. It's a substantial one, where I'm not just translating code into another language with functional equivalence, I'm completely redesigning everything from the ground up. AI has helped a great deal but only in context size chunks. The problem with this, and this is a recurring theme in AI coding is that you need to
Advertisement
Show HN: I am running 3 coding agents non-stop over the last 3 days. Here is howIMAGE
news.ycombinator.com• Jun 13, 2026• 1 min read
Show HN: I am running 3 coding agents non-stop over the last 3 days. Here is how1. Headless modeHeadless mode allows you to use the AI as a command-line utility for automation and scripting. In Claude Code you run it with the -p flag: claude -p, in codex - exec, opencode - run.2. Ask humanThe traditional communication channel with the operator won't work in headless mode - we need to implement a dedicated tool. Here is an example of how this can be done https://github.com/sermakarevich/claude/tree/main/mcp/ask_hu...3. Tasks queueBeads is a lightweight distributed graph issue tracker for AI agents, powered by Dolt. You can create tasks, define dependencies between tasks, and have status, priorities, hierarchy. Beads helps prevent multiple tasks from being claimed by > 1 worker.4. Worker artifactsWe want to be able to monitor how a worker is doing, at what stage it is, and resume it after a restart. For every task we can create a dedicated folder using the beads task id and put into it what we need. I put there: - plan and status md - knowledge md - events.jsonl - s
Show HN: Mac screen recorder that adds zoom animations from click dataIMAGE
screencharm.com• Jun 9, 2026• 1 min read
Show HN: Mac screen recorder that adds zoom animations from click dataHi HN, I started building my product around 2 years ago as a Chrome extension. After releasing it, I realized I would never reach the quality of desktop apps, so at the beginning of 2025 I pivoted to a macOS app. I spent 3 months rewriting the codebase for Electron. I’m still using Next.js under the hood because the chrome extension used it, but in the near future I want to switch to ViteJS since it’s lighter and I don’t need backend functionality for an Electron app.Overall I spent about 2 years on the development. The more interesting part is tracking the cursor movements when user starts recording and transforming it into smooth cursor movements and click-driven zoom effects. I use Swift scripts for low-level cursor tracking, then run a post-processing pipeline: resampling to timeline FPS, outlier-jump clamping, stillness detection/snap-to-median, cursor-type flicker smoothing, and coordinate normalization for area vs full-screen recording. Clicks are converted into timed zoom segme
Show HN: Command Center, the AI coding env for people who care about qualityIMAGE
cc.dev• Jun 8, 2026• 1 min read
Show HN: Command Center, the AI coding env for people who care about qualityHi HN! We’re Jimmy and Ray. Jimmy is a Thiel Fellow with a Ph. D. from MIT who has worked on programming tools for 15 years; Ray became VP of Sales at a $2B company when he was 19 and has built side-businesses vibe-coding.Last year, we set to answer the question “If AI can write code 100x faster, then why aren’t you shipping 100x faster?” What we learned shocked us — even fairly nontechnical people and solo founders told us they were spending more than half of their development time reading the AI-written code. And much of the rest of the time was spent either de-slop-ping it, or wishing they had done so.As luck turns out, our last two products were a tool that quickly onboards people to large codebases ( https://x.com/0xjimmyk/status/1873357324229984677 ) and trainings that taught deep concepts of code quality to CEOs, YC founders, and engineers at top companies ( mirdin.com ), so we were extremely well-positioned to solve these problems.Command Center is an agentic coding environment
Show HN: OpenDeck – DIY MIDI Platform Based on Zephyr RTOSIMAGE
github.com• Apr 22, 2026• 1 min read
Show HN: OpenDeck – DIY MIDI Platform Based on Zephyr RTOSThis is OpenDeck, my own platform for building custom MIDI controllers. I've been working on it for more than 10 years, and now I've made the biggest change so far - rewritten the entire codebase to make use of Zephyr - RTOS with which I've been working professionally for few years now. This now allows me to support many newer boards, complex features and also to modernize the codebase in general. I've been limited on all fronts before.The platform itself allows for simple building and configuring of custom MIDI controllers - main reason for that is because it requires no coding. Load the firmware on the board, configure it via web configurator and you're good to go. The amount of configurable features is also huge. I do have extensive documentation which covers usage, configuration, flashing of various boards, customization of own boards etc. All available on GitHub.The platform supports a large number of various boards - not only my own, custom designs, which I sell, but boards like
Show HN: LLM-primer – pre-warmed Claude Code session pool, zero startup waitIMAGE
github.com• Apr 15, 2026• 1 min read
Show HN: LLM-primer – pre-warmed Claude Code session pool, zero startup waitClaude Code sessions that read a real CLAUDE.md take 30-60 seconds to initialize. Fine once. Friction when you're switching contexts constantly.llm-primer keeps a pool of warm sessions in the background. When you need one, it's already past the startup protocol.Happy to answer questions. The main motivation was that I'm running LLM wikis (llm-context-base) and switching context between different agent roles constantly. The startup latency was killing the flow.
Advertisement
Show HN: Mason – A container for running a team of agents using a conciergeIMAGE
github.com• Apr 4, 2026• 1 min read
Show HN: Mason – A container for running a team of agents using a conciergeWhile working on a few projects with claude code I found myself building a bunch of scaffolding to organize and build my agent workflow. Trying to figure out how to orchestrate my agents and work with them in a more natural way was more interesting to me. This container has all of the basic building blocks of my workflow. I use both the terminal and chat server depending on what I’m trying to do. So do what feels comfortable to you. I suggest having the terminal window open and watching the agents work is a good idea to get a feel for things. Take a look at the README and the other docs. I’ll be checking this thread and will respond when I can. Thanks for reading this far!
Show HN: Zerobox – Sandbox any command with file, network, credential controlsIMAGE
github.com• Mar 30, 2026• 1 min read
Show HN: Zerobox – Sandbox any command with file, network, credential controlsI'm excited to introduce Zerobox, a cross-platform, single binary process sandboxing CLI written in Rust. It uses the sandboxing crates from the OpenAI Codex repo and adds additional functionalities like secret injection, SDK, etc.Watch the demo: https://www.youtube.com/watch?v=wZiPm9BOPCgZerobox follows the same sandboxing policy as Deno which is deny by default. The only operation that the command can run is reading files, all writes and network I/O are blocked by default. No VMs, no Docker, no remote servers.Want to block reads to /etc? zerobox --deny-read=/etc -- cat /etc/passwd cat: /etc/passwd: Operation not permitted How it works:Zerobox wraps any commands/programs, runs an MITM proxy and uses the native sandboxing solutions on each operating system (e.g BubbleWrap on Linux) to run the given process in a sandbox. The MITM proxy has two jobs: blocking network calls and injecting credentials at the network level.Think of it this way, I want to inject "Bearer OPENAI_API_KEY" but I
Show HN: Context Overflow – a Stack Overflow for AI AgentsIMAGE
ctxoverflow.dev• Mar 20, 2026• 1 min read
Show HN: Context Overflow – a Stack Overflow for AI AgentsHey HN,After using a bunch of agents, my friend and I noticed a major issue: an agent could spend a bunch of time solving a tricky task, but when the session ended all that knowledge vanishes. Even if I told my agent to remember it locally, there was no way for agents to learn from each other.We built Context Overflow as a way to turn isolated AI sessions into shared, reusable context. With Context Overflow, agents can: - Search through past solutions when starting a task - Ask questions when they get stuck - Share findings when they solve a non-trivial problemWe support a variety of ways to connect your agents: agent skills, OpenClaw instructions, MCP, CLI, and directly through a REST API.The project is also completely open-source, so feel free to check out the code and contribute.https://www.ctxoverflow.devgithub: https://github.com/sahilmahendrakar/context-overflow
Show HN: Hopsule – Persistent memory and decision layer for AI developmentIMAGE
news.ycombinator.com• Mar 17, 2026• 1 min read
Show HN: Hopsule – Persistent memory and decision layer for AI developmentHi HN! I'm building Hopsule.If you use AI coding tools like Cursor, Copilot, or Claude, you’ve probably seen this happen: The AI writes good code - but it ignores your architecture.It doesn’t know: - why you chose a specific pattern - which conventions your team agreed on - which decisions are already locked in So it falls back to generic patterns, outdated examples, or random GitHub training data. Over time this slowly breaks the consistency of the codebase.Most teams try to fix this with: - giant Markdown files - wiki pages - long prompts - Slack threads But those aren't machine-readable rules.So we built Hopsule. Hopsule turns architecture decisions into enforceable context that AI tools must follow.Example: Your team approves a decision: “All database access must go through the repository layer.” Hopsule records this as a rule and injects it into the AI context before code generation.No giant prompts. No manual context stuffing. No architecture drift.Website: https://hopsule.com Do
Show HN: Claude Code skills that build complete Godot gamesIMAGE
github.com• Mar 16, 2026• 1 min read
Show HN: Claude Code skills that build complete Godot gamesI’ve been working on this for about a year through four major rewrites. Godogen is a pipeline that takes a text prompt, designs the architecture, generates 2D/3D assets, writes the GDScript, and tests it visually. The output is a complete, playable Godot 4 project.Getting LLMs to reliably generate functional games required solving three specific engineering bottlenecks:1. The Training Data Scarcity: LLMs barely know GDScript. It has ~850 classes and a Python-like syntax that will happily let a model hallucinate Python idioms that fail to compile. To fix this, I built a custom reference system: a hand-written language spec, full API docs converted from Godot's XML source, and a quirks database for engine behaviors you can't learn from docs alone. Because 850 classes blow up the context window, the agent lazy-loads only the specific APIs it needs at runtime.2. The Build-Time vs. Runtime State: Scenes are generated by headless scripts that build the node graph in memory and serialize it t
Ask HN: AI Agents vs. Gateways vs. HarnessesIMAGE
news.ycombinator.com• Mar 16, 2026• 1 min read
Ask HN: AI Agents vs. Gateways vs. HarnessesHi,I'd like to get everyone's take on the different components in the AI Agents ecoysystem. I find the current terminology quite confusing as it's not always obvious what I'll be actually getting when I examine the available options.A lot of things get called Agents, but that term seems hard to define as it often refers to overlapping functionality. To me, agents seem to be currently composed of the following components:## Harnesses- Adds UI and system instructions around an LLM and may also augment it with tools such as memory, tool calls, etc...- Examples are Claude Code, Code, Gemini CLI, pi.dev, ...## Gateways- These connect agents to your communication tool of choice, e.g. Whatsapp, Telegram, Slack, Discord, ...- Examples are OpenClaw and Nanoclaw## Sandboxes- Isolated environments where Agents can run with limited or auditable capabilities- Examples can be from physical ones like separate Mac Minis to docker-agent, agent-sandbox, localsandbox, ...This then takes us to *Agents*:##
Advertisement
Show HN: Nixcage – Sandbox AI coding agents per project with Nix and direnvIMAGE
github.com• Mar 13, 2026• 1 min read
Show HN: Nixcage – Sandbox AI coding agents per project with Nix and direnvI built nixcage to solve a problem that's been bugging me: AI coding agents like Claude Code have broad access to your filesystem, network, and system. That's powerful but uncomfortable, especially on client projects or machines with sensitive data.nixcage creates per-project sandboxes that activate automatically when you cd into a directory (via direnv). It uses bubblewrap on Linux and sandbox-exec on macOS — no VMs, no Docker, no overhead.Three isolation levels: strict (no network, empty home), standard (project writable, network on), and relaxed (home readable, project writable).It also controls Nix store access (shared, readonly, copy, or fully isolated) so sandboxed tools can't pollute your host store.Quick start: nixcage init --preset claude-code && direnv allowA debug mode captures every blocked syscall so you can see exactly what's denied and tune your config.https://github.com/hamidr/nixcage
Show HN: AgentCash – access 280 paid APIs with no API keysIMAGE
agentcash.dev• Mar 10, 2026• 1 min read
Show HN: AgentCash – access 280 paid APIs with no API keysHey HN - I'm Mason, and I'm excited to share AgentCash - a CLI to help your agent discover and pay for premium APIs and paywalled data.The problem we kept running into was simple: if you want an agent to use premium data or services, the setup flow is awful.You have to find the right provider, sign up manually, subscribe, generate an API key, install tooling, and then teach your agent how to use it. Then do that again for the next provider.We wanted a simpler model: give the agent a universal balance, let it discover available resources, and let it pay per call.So AgentCash gives agents one balance with access to 280+ paid APIs. It’s built on x402 [0,1] (the Coinbase/Cloudflare payments protocol) and designed to work with tools like Claude Code, Codex, OpenClaw, Cursor, etc.I also am really proud of our onboarding flow - we actually use AgentCash itself to research you and the decide how much free cash to give based on a score.The vision for this is to essentially give agents JIT conte
Sponsored