Ami – A local, open-source agent that does your busywork across apps
Hey everybody, sharing Ami on HN today. Ami is an open source, local-first agent harness that acts as your shadow worker and copilot chat. It ships with a graph memory. Here's what Ami does on its own - - connects to apps, data, repositories, tools with your personal tokens - Learns how you do tasks (execution style, decisions, anti-patterns) - Learns how you communicate (external and internal) - maintains a universal to-do list Here's how you use Ami - 1. You can execute busywork. It fetches and executes tasks autonomously in your style, asks approval before risky actions, gives…
What it does
In the maker’s words, at launch
Hey everybody, sharing Ami on HN today. Ami is an open source, local-first agent harness that acts as your shadow worker and copilot chat. It ships with a graph memory. Here's what Ami does on its own - - connects to apps, data, repositories, tools with your personal tokens - Learns how you do tasks (execution style, decisions, anti-patterns) - Learns how you communicate (external and internal) - maintains a universal to-do list Here's how you use Ami - 1. You can execute busywork. It fetches and executes tasks autonomously in your style, asks approval before risky actions, gives deliverables, drafts replies / emails / ticket updates. 2. You can execute copilot chats. Use it to ask questions, fire off ad-hoc tasks, create to-dos, update memory. Ami was built for internal use. My team found it useful, so we wanted to share it here. It's still in development stage, and we might push a more stable release soon. It constructs a context graph memory of you, with entities, relationships, feedbacks, decisions, writing styles maintained in memory so it can get more autonomous the more you use it. Few examples where Ami helped me this week - 1. fetched a bug report from slack, created fix PR autonomously which I merged, verified fix is working. 2. debugged a traffic spike on our new blog. 3. turned a sales POC into an order form draft using recently signed forms. 4. nailed down metrics definitions from notion and created a dashboard. 5. closed out my day by auto-updating Linear tickets based on slack activity. Any feedback is most welcome.
Does the same job
all alternatives →
- NONous – Open-Source Agent Framework with Autonomous, SWE Agents, WebUI2024 · github.com · ▲155
Hello HN! The day has finally come to stop adding features and start sharing what I've been building the last 5-6 months. It's a bit of CrewAI, OpenDevon, LangFuse/Cloud all in one, providing devs who prefer TypeScript an integrated framework thats provides a lot out of the box to start experimenting and building agents with. It started after peeking at the LangChain docs a few times and never liking the example code. I began experimenting with automating a simple Jira request from the engineering team to add an index to one of our Google Spanner databases (for context I'm the…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
