I am Sumit and I am building nocodo.com - https://github.com/brainless/nocodo. It is is a fairly ambitious project and I feel I would get some needed support from folks on HN. Here is what nocodo is becoming:
- Use your own Linux machine or a cloud server (dev machine) to manage full lifecycle of building apps using Git, GitHub, cloud providers, CI, etc.\n - You will get integrated view of code changes (Git), issues/tasks (GitHub initially), CI (GitHub Actions initially)\n - Access test deployments direct to your computer if you generate binary or to server - DNS, DB managed for you\n - Team collaboration will become possible at the task/project level\n - `manager` daemon hosts API to connect from web/mobile interfaces to projects on the dev machine\n - `manager` runs any number of Claude Code, Gemini CLI, Qwen Code, Continue dev, etc. - your own API keys/Pro plans\n - `manager-web` app that connects to `manager`, allows sending prompts to any project, see status, etc.\n - `manager` will have API integrations to GitHub, GitLab, CI platforms, Cloudflare, and cloud providers\n - `manager` will check CI, manage DNS for test and live deployment\n - `manager` builds on my own set of contextual prompts to allow working on your projects (vibe coding): http://nododo.com/playbook\n - `manager-mobile` app(s) will come soon that allows same functionality as manager-web\n - `launcher` app will come soon that manages developer server on Scaleway, Digital Ocean, etc. using your API keys, SSH keys, etc.\nIf you go to https://github.com/brainless/nocodo/releases you can see I use this myself. I connect to my developer machine over SSH (this will be through manager soon), I talk to Claude Code, Claude edits code code, use GitHub based workflow, test binaries locally and continue building.
nocodo will be self-hosted and have no vendor lock-in, supporting multiple coding agents, cloud providers, etc. It will have authentication through nocodo.com if you enable that and it will be a small subscription (like USD 60 annual for 5 people team).
I am a solo founder and I have been chasing this for the last 2 years. nocodo.com is with me since 2013. I felt like sharing this since it is taking shape and also because I am running out of funds. I consult on the side to keep lights on, so if you like my work and have any work please message me on any network I am on.
Thank you so much,\nSumit"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: I am vibe coding a collaborative vibe coding tool"}},"_tags":["story","author_brainless","story_45155423","show_hn"],"author":"brainless","created_at":"2025-09-07T04:34:31Z","created_at_i":1757219671,"num_comments":0,"objectID":"45155423","points":4,"story_id":45155423,"story_text":"Hello everyone,
I am Sumit and I am building nocodo.com - https://github.com/brainless/nocodo. It is is a fairly ambitious project and I feel I would get some needed support from folks on HN. Here is what nocodo is becoming:
- Use your own Linux machine or a cloud server (dev machine) to manage full lifecycle of building apps using Git, GitHub, cloud providers, CI, etc.\n - You will get integrated view of code changes (Git), issues/tasks (GitHub initially), CI (GitHub Actions initially)\n - Access test deployments direct to your computer if you generate binary or to server - DNS, DB managed for you\n - Team collaboration will become possible at the task/project level\n - `manager` daemon hosts API to connect from web/mobile interfaces to projects on the dev machine\n - `manager` runs any number of Claude Code, Gemini CLI, Qwen Code, Continue dev, etc. - your own API keys/Pro plans\n - `manager-web` app that connects to `manager`, allows sending prompts to any project, see status, etc.\n - `manager` will have API integrations to GitHub, GitLab, CI platforms, Cloudflare, and cloud providers\n - `manager` will check CI, manage DNS for test and live deployment\n - `manager` builds on my own set of contextual prompts to allow working on your projects (vibe coding): http://nododo.com/playbook\n - `manager-mobile` app(s) will come soon that allows same functionality as manager-web\n - `launcher` app will come soon that manages developer server on Scaleway, Digital Ocean, etc. using your API keys, SSH keys, etc.\nIf you go to https://github.com/brainless/nocodo/releases you can see I use this myself. I connect to my developer machine over SSH (this will be through manager soon), I talk to Claude Code, Claude edits code code, use GitHub based workflow, test binaries locally and continue building.
nocodo will be self-hosted and have no vendor lock-in, supporting multiple coding agents, cloud providers, etc. It will have authentication through nocodo.com if you enable that and it will be a small subscription (like USD 60 annual for 5 people team).
I am a solo founder and I have been chasing this for the last 2 years. nocodo.com is with me since 2013. I felt like sharing this since it is taking shape and also because I am running out of funds. I consult on the side to keep lights on, so if you like my work and have any work please message me on any network I am on.
Thank you so much,\nSumit","title":"Show HN: I am vibe coding a collaborative vibe coding tool","updated_at":"2026-03-05T22:40:21Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"neom"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["digitalocean","managed","agents"],"value":"Hi! :)
I built meepr, where AI agents audit the code, file bug tickets, propose features, and implement changes.
The app itself started as standard microblogging 1.0 stuff \u2013 auth, profiles, following, likes, "remeeps", DMs, notifications etc.
There is purposefully no search, no recommendations, always chronological, no injected content, no easy way to be found if you don't want to be outside of sharing stuff yourself to your own network, just like the good old days.
On meepr, hashtags act more like Quora topics than post tags. An AI agent called the Tag Agent analyzes posting patterns for each hashtag, while a User Agent builds opinion profiles on everyone based on their meep history \u2013 topic affinity, expertise signals, behavior patterns. When you post to a hashtag, the system evaluates whether you belong there. New users get cold start handling. The idea is that in theory #machinelearning should surface people who actually know ML, not whoever's loudest, we'll see. :)
Then there's the self-maintaining part. Every night at 3am, an agent called Steward wakes up, clones the repo into an isolated worktree, runs npm audit and linting, scans PM2 logs for error patterns, and uses Claude with tool use to investigate anything weird. Weekly, it distills everything into themes and generates tickets in YAML format.
Those tickets feed into "Genesis", which runs a full OODA loop. It observes the workspace, orients around the backlog, decides what to work on, then acts \u2013 writing code, creating snapshots for rollback, running validation, restarting services if everything passes. Seven "pressure agents" act as internal critics arguing over every proposed change: one obsessed with security, one with performance, one advocating for users, one collecting tech debt, and so on.
Every post also gets analyzed \u2013 sentiment, topics, spam scoring, embeddings for semantic search. The V2 memory system builds persistent context about users that feeds back into the gating decisions. Snapshots before every mutation. A separate AI reviews changes before commit. Multiple autopilot modes from "observe only" to "fully autonomous." Secret redaction in all prompts. Major features get approved by me, then ship themselves about once a month.
It's been running for about 4 days now, the agents find real bugs, propose sensible improvements, and the code they generate usually runs, and every time it's managed to unstick itself.
Stack is Node/Express/Postgres/Drizzle with pgvector for embeddings, mix of GPT-5.2 and Sonnet for Genesis and the gating agents, runs on a single DigitalOcean droplet with nine PM2 processes.
Come meep with me! https://meepr.co/je"},"title":{"matchLevel":"none","matchedWords":[],"value":"Show HN: Meepr \u2013 A quiet, self building social platform"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://meepr.co/"}},"_tags":["story","author_neom","story_46724896","show_hn"],"author":"neom","created_at":"2026-01-22T20:44:10Z","created_at_i":1769114650,"num_comments":0,"objectID":"46724896","points":3,"story_id":46724896,"story_text":"Hi! :)
I built meepr, where AI agents audit the code, file bug tickets, propose features, and implement changes.
The app itself started as standard microblogging 1.0 stuff \u2013 auth, profiles, following, likes, "remeeps", DMs, notifications etc.
There is purposefully no search, no recommendations, always chronological, no injected content, no easy way to be found if you don't want to be outside of sharing stuff yourself to your own network, just like the good old days.
On meepr, hashtags act more like Quora topics than post tags. An AI agent called the Tag Agent analyzes posting patterns for each hashtag, while a User Agent builds opinion profiles on everyone based on their meep history \u2013 topic affinity, expertise signals, behavior patterns. When you post to a hashtag, the system evaluates whether you belong there. New users get cold start handling. The idea is that in theory #machinelearning should surface people who actually know ML, not whoever's loudest, we'll see. :)
Then there's the self-maintaining part. Every night at 3am, an agent called Steward wakes up, clones the repo into an isolated worktree, runs npm audit and linting, scans PM2 logs for error patterns, and uses Claude with tool use to investigate anything weird. Weekly, it distills everything into themes and generates tickets in YAML format.
Those tickets feed into "Genesis", which runs a full OODA loop. It observes the workspace, orients around the backlog, decides what to work on, then acts \u2013 writing code, creating snapshots for rollback, running validation, restarting services if everything passes. Seven "pressure agents" act as internal critics arguing over every proposed change: one obsessed with security, one with performance, one advocating for users, one collecting tech debt, and so on.
Every post also gets analyzed \u2013 sentiment, topics, spam scoring, embeddings for semantic search. The V2 memory system builds persistent context about users that feeds back into the gating decisions. Snapshots before every mutation. A separate AI reviews changes before commit. Multiple autopilot modes from "observe only" to "fully autonomous." Secret redaction in all prompts. Major features get approved by me, then ship themselves about once a month.
It's been running for about 4 days now, the agents find real bugs, propose sensible improvements, and the code they generate usually runs, and every time it's managed to unstick itself.
Stack is Node/Express/Postgres/Drizzle with pgvector for embeddings, mix of GPT-5.2 and Sonnet for Genesis and the gating agents, runs on a single DigitalOcean droplet with nine PM2 processes.
Come meep with me! https://meepr.co/je","title":"Show HN: Meepr \u2013 A quiet, self building social platform","updated_at":"2026-03-05T23:23:35Z","url":"https://meepr.co/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"jcyriac"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["digitalocean","managed","agents"],"value":"Hey HN,
I built DevOps Agents \u2014 a set of specialized AI agents to help with day-to-day DevOps and SRE work.\n\n The agents analyze your GitHub repo, figure out the cloud resources needed, deploy everything, and get your app live in\n production. They have a chat interface (like Claude Code or ChatGPT) and stick around after deployment to help you manage the\n infra ongoing. For example, I can ask the agent if the app is running, and it will SSH into the resource, check the status,\n check logs, find the root cause, and get the app back up.\n\n I've used this for various tasks involving complex setups \u2014 Kubernetes, ELK stack, Grafana, Prometheus, Redis, ClickHouse, CI/CD\n pipelines, self-hosted tools, Docker setups, and multi-account AWS, Azure, GCP, or DigitalOcean deployments.\n\n Why I built this: I was already using Cursor and Claude Code to manage my infra, and they're great for code. But infrastructure\n is different \u2014 most of the context isn't in code. Things like where your configs live, which cloud accounts map to which\n environments, what ports are exposed, how services talk to each other \u2014 all of that lives outside the codebase. Every time I\n started a new session, I was re-explaining my entire setup from scratch. The agents here are purpose-built to retain that\n infrastructure context across sessions, so I can keep managing my infra without losing continuity.\n\n Happy to answer any questions. I built DevOps Agents \u2014 a set of specialized AI agents to help with day-to-day DevOps and SRE work.\n\n The agents analyze your GitHub repo, figure out the cloud resources needed, deploy everything, and get your app live in\n production. They have a chat interface (like Claude Code or ChatGPT) and stick around after deployment to help you manage the\n infra ongoing. For example, I can ask the agent if the app is running, and it will SSH into the resource, check the status,\n check logs, find the root cause, and get the app back up.\n\n I've used this for various tasks involving complex setups \u2014 Kubernetes, ELK stack, Grafana, Prometheus, Redis, ClickHouse, CI/CD\n pipelines, self-hosted tools, Docker setups, and multi-account AWS, Azure, GCP, or DigitalOcean deployments.\n\n Why I built this: I was already using Cursor and Claude Code to manage my infra, and they're great for code. But infrastructure\n is different \u2014 most of the context isn't in code. Things like where your configs live, which cloud accounts map to which\n environments, what ports are exposed, how services talk to each other \u2014 all of that lives outside the codebase. Every time I\n started a new session, I was re-explaining my entire setup from scratch. The agents here are purpose-built to retain that\n infrastructure context across sessions, so I can keep managing my infra without losing continuity.\n\n Happy to answer any questions.State: Fully working, free trial, no card needed. Try it out and please give me feedback, especially if you run in to problems.
Goal: I built VoiceGremlin with the explicit goal of being Mailosaur for phone agents. We paid for Mailosaur at work because the alternative (having our automated tests interact programmatically with our corporate Outlook server) was doable, but very painful, both technically and organizationally. The lesson I learned was "doable, but painful" is a good sign of a SaaS opportunity.
Well, getting an automated test to call a phone number is also painful. Telephony providers are tough to get onboarded as vendors. Using your own STT/TTS means a lot of bandwidth moving through wherever you run your test automation from. It's tricky to get the LLM-to-LLM prompts dialed in enough to avoid flaky tests. Etc.
Process: It took about 45 days to build, with half of that being businessy stuff like implementing Stripe and my feeble attempts at marketing, and the other half being experimenting with different telephony providers and features, testing different models, prompt tweaking, and fraud/abuse prevention.
Design goal: Do one thing, do it well, and get out of the way. There's no ambition to manage your test cases for you, host your voice agents, or add upsell features.
Stack: The dependencies are Supabase (DB and authentication), Netlify (static storage and API routing), Digitalocean (the server component that makes the calls), Telnyx (easier to work with than Twilio IMO), Stripe, Openrouter, Cloudflare (captcha on signup). Oh, and I host my private git in Keybase, the greatest tool nobody uses.
Thanks!"},"title":{"fullyHighlighted":false,"matchLevel":"partial","matchedWords":["agents"],"value":"Show HN: VoiceGremlin, a SaaS tool for automated tests against AI phone agents"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://voicegremlin.com/"}},"_tags":["story","author_ineptech","story_49995804","show_hn"],"author":"ineptech","children":[49997635],"created_at":"2026-10-07T17:16:36Z","created_at_i":1791393396,"num_comments":1,"objectID":"49995804","points":3,"story_id":49995804,"story_text":"Hi, I'm a former SDET and now solo dev of VoiceGremlin, a tool for automated tests against AI that answer phones. You pass the API a phone number and a test case like "Verify that the agent does X." It calls your voice agent, tests the thing by having the bots talk to each other, and uses LLM-as-judge to provide a pass/fail for your pipeline.
State: Fully working, free trial, no card needed. Try it out and please give me feedback, especially if you run in to problems.
Goal: I built VoiceGremlin with the explicit goal of being Mailosaur for phone agents. We paid for Mailosaur at work because the alternative (having our automated tests interact programmatically with our corporate Outlook server) was doable, but very painful, both technically and organizationally. The lesson I learned was "doable, but painful" is a good sign of a SaaS opportunity.
Well, getting an automated test to call a phone number is also painful. Telephony providers are tough to get onboarded as vendors. Using your own STT/TTS means a lot of bandwidth moving through wherever you run your test automation from. It's tricky to get the LLM-to-LLM prompts dialed in enough to avoid flaky tests. Etc.
Process: It took about 45 days to build, with half of that being businessy stuff like implementing Stripe and my feeble attempts at marketing, and the other half being experimenting with different telephony providers and features, testing different models, prompt tweaking, and fraud/abuse prevention.
Design goal: Do one thing, do it well, and get out of the way. There's no ambition to manage your test cases for you, host your voice agents, or add upsell features.
Stack: The dependencies are Supabase (DB and authentication), Netlify (static storage and API routing), Digitalocean (the server component that makes the calls), Telnyx (easier to work with than Twilio IMO), Stripe, Openrouter, Cloudflare (captcha on signup). Oh, and I host my private git in Keybase, the greatest tool nobody uses.
Thanks!","title":"Show HN: VoiceGremlin, a SaaS tool for automated tests against AI phone agents","updated_at":"2026-10-07T22:00:52Z","url":"https://voicegremlin.com/"}],"hitsPerPage":20,"nbHits":5,"nbPages":1,"page":0,"params":"query=DigitalOcean+Managed+Agents&tags=story&advancedSyntax=true&analyticsTags=backend","processingTimeMS":18,"processingTimingsMS":{"_request":{"roundTrip":18},"afterFetch":{"format":{"highlighting":1,"total":1}},"fetch":{"query":14,"scanning":3,"total":18},"total":18},"query":"DigitalOcean Managed Agents","serverTimeMS":20}