Comments URL: https://news.ycombinator.com/item?id=49563851

Points: 248

# Comments: 279

Comments URL: https://news.ycombinator.com/item?id=49546398

Points: 2

# Comments: 1

But based on this I thought I could make something similar for cad files, and they turned out to be an entirely different monster. the cad spec is like 1000x bigger than ppts, cad files themselves were hard to gather for test targets. 70-80% of their spec is public and remaining is driven by private vendors. the format itself is in binary. The LLM has been chasing that goal since about 2 months now and its nowhere close.

Comments URL: https://news.ycombinator.com/item?id=49543337

Points: 1

# Comments: 0

https://github.com/artpar/puppt

it allows your llms to see the ppt files structurally apart from just rendering it

almost any project which matures to requiring a user authn/authz (and there are always assets owned by users) i default to using daptin

I have hardened it a lot over the last 10 years, especially in terms of transaction/concurrency/security. happy to help you setting it up in your project. you can dm me ( x.com/phparth ) or leave an issue on the github repo

1. oauth/account management -> daptin can serve itself as a oauth provider as well as allow "login via oauth" on 3rdparty oauth servers. you get a full managed account including forget/reset password

2. permissions -> this involves more than rate limits, like who's the owner of what and you can manage permissions at user/guest/group level

3. handling payments -> fraud monitoring is usually part of the payment processor and you are not supposed to do much about it

and these days you can point your llm agent to the wiki to get most of the stuff done without needing to read the docs yourself. you just need a cheap vps (the $5 ones on digital ocean will be more than fine).

https://github.com/daptin/daptin/wiki

https://github.com/daptin/daptin/wiki/Permissions

Comments URL: https://news.ycombinator.com/item?id=48729506

Points: 1

# Comments: 0

I made ATM, short for Agent Task Manager. It is a small CLI/TUI that shows which local coding agents are running on your machine, which repo they are in, and whether they look active, idle, stale, or just present as a process.

It currently recognizes common agent CLI processes like Codex, Claude, Gemini, Aider, OpenCode, Goose, Amp, and Cursor Agent. Codex has the deepest support right now: ATM can read local session metadata to show the project, session path, last activity, and a compact "what just happened" summary.

I built it because I kept ending up with several agents running across different repos and wanted something friendlier than ps for answering: "what is still alive, where is it working, and has it gone quiet?"

Install:

curl -fsSL https://github.com/artpar/atm/releases/latest/download/insta... | sh

Repo: https://github.com/artpar/atm

It is early, tiny, and CLI-first. I’d love feedback from people running multiple local agents at once because right now its a very basic.

Comments URL: https://news.ycombinator.com/item?id=48223680

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48075356

Points: 6

# Comments: 2

canopy renders jsonl files as functional and interactive native GUI

Here is a hello world example

```example.jsonl

{"type":"createSurface","surfaceId":"main","title":"Tasks"}

{"type":"updateDataModel","surfaceId":"main","ops":[ {"op":"replace","path":"/tasks","value":[{"title":"Ship demo","done":false}]}]}

{"type":"updateComponents","surfaceId":"main","components":[ {"componentId":"root","type":"Column","children":["title"]}, {"componentId":"title","type":"Text","props":{"content":{"path":"/tasks/0/title"}}} ]}

```

jsonl to gui renderer is one part, canopy can connect with your llm provider directly and let the llm build the app thru these incremental jsonl.

canopy supports --claude or --codex at run in "reverse controlled mode", starts claude/codex with canopy as an MCP server and appropriate prompt.

the mcp also exposes a "screenshot" tool for itself so the LLM can actually "see" whats its build. and it can obviously interact with the app itself to test it.

the images in the readme are real examples.

apart from the basic native components like input field, scroll, layouts etc, canopy can do - ffi function calls - take its own screenshot - audio/video capture - api calls

for "demo" apps it works okay, i notice different kind of "behavioral issues" in the generated apps though, mostly in terms of state management for more complex apps, the issue gets multiplied. i tried a "pixel editor to ico export", the editor part worked fine (0 ergonomics for the user though), the export did not work at all. i coulnt get to a usable "sqlite browser" at this point.

but i am sure these are prompt problems/tooling that can be fixed with better abstractions (packages, reusable components)

https://github.com/artpar/canopy

go build -o canopy

Comments URL: https://news.ycombinator.com/item?id=47873874

Points: 2

# Comments: 1

https://github.com/artpar/terminal-tunnel

P2P with webrtc (pion ftw) with e2ee

client side is webui so you can use on any device

ps: the default Cloudflare Worker from my account is already maxed out so you will need your own exchange (self host on your account)

except '- the directness and simplicity of JavaScript'

https://github.com/artpar/guage

But somehow the language feels so foreign. it can obviously do hello world, but I don't have a real use case

PS: the "Pure symbols only" is no longer true, most symbols have been converted to English names

and, the "days" you see there in the markdowns are "claude code sessions", not actual days

https://news.ycombinator.com/item?id=46514587

tt start -p mypassword → get a URL (qrcode) → open in browser → enter password → connected.

Direct webrtc datachannel between your machine and browser.

Signaling server is a cloudflare worker, exchanges ~2KB of sdp/ice metadata then gets out of the way. Password never transmitted - argon2id derives 256-bit key locally on both ends. All terminal i/o gets nacl secretbox encryption before hitting the datachannel. double encrypted with dtls underneath but I wanted the relay to see nothing useful even during signaling.

go + pion/webrtc, about 14k loc. browser is xterm.js + webcrypto for argon2id. stun default, turn for symmetric nat.

my use case: checking on claude code runs from my phone when im not at my desk. hotel wifi, spotty mobile data. spent time on turn fallback, keepalive with reconnection, buffered writes during disconnects. pwa so it works from home screen and survives app switching. holds up ok on 3g.

Trade-offs: ice gathering takes 2-5s on connect. browser cant initiate, need cli on host. codes expire 24h.

Single binary, no deps. daemon mode for multiple sessions. tests with race detector, chaos tests for disconnects, network condition simulation. crypto and webrtc at ~72% coverage.

https://github.com/artpar/terminal-tunnel

ps: default relay runs on my cloudflare free tier so no guarantees. you can self-host the worker or run tt relay locally.

Comments URL: https://news.ycombinator.com/item?id=46514587

Points: 13

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=46424433

Points: 3

# Comments: 0