skull8888888

why qwen 2.5 specifically?

playwright

right now package only supports models from gemini, anthropic and openai. Vision is required. PRs are very welcome! It's very easy to add new model, simply follow any providers in here https://github.com/lmnr-ai/index/tree/main/index/llm/provide...

The best out all of them. Check the first message in the post. tldr:

- SOTA on webvoyager

- browser agent observability

- fast and reliable

- CLI for easier interaction

- available as a serverless API

have you tried it with Index?

how could you see an http request from a video? If you mean the console output, then it's just logs of an agent.

it can do it! try it out, literally just prompt it

thank you for the feedback! we're actually working on it :)

researching a topic and creating a spreadsheet

works pretty well, try it out - pip install lmnr-index

any need for browser agent observability?

which model are you using? try gemini pro/flash, they are very fast

Oh I see, didn't know about that, fastest and easiest thing you can do is to play around with pro via our chat UI https://lmnr.ai/chat - it's free up to 10 messages.

For the CLI and custom models, you can clone the repo, then go to the cli.py and manually add your model there. I will work on proper support of custom models.

Gemini 2.5 pro is available. Is it missing on your side? Do you run index via CLI?

I'm pretty confident it can do it. Try it out and see for yourself. Just install the package, run cli and give it your prompt.

pip install lmnr-index playwright install chromium index run

Also try experimenting with different models. So far, Gemini 2.5 Pro is the best in terms of quality/speed. Claude 3.7 is also pretty good.

- research task, agent is smart enough to understand which links to click next without the need to hardcode the parsing and navigation logic

- any task that requires UI interaction, button clicking, filter selection, form filling and so on. Just prompt it, it's surprisingly very robust and self-healing.

- complex long-running task that require extensive context - e.g. researching one topic and then creating spreadsheet, creating a presentation for a topic and so on.

Essentially, any task that can be done within a browser environment that previously required flacky hardcoded predefined scripts. Also, website testing is a great example.

there's also a demo right in the repo https://github.com/lmnr-ai/index

here's a demo of a chat UI https://x.com/skull8888888888/status/1910763169489764374

here's a demo of CLI https://x.com/skull8888888888/status/1914728292193628330

isn't browser use sota on web voyager? At this point web voyager seems to be outdated, there's def a need for a new harder benchmark.

apologies for hijacking your launch (congrats btw!)

thanks Marc :)

We launched Laminar couple of months ago, https://www.lmnr.ai. Extremely fast, great DX and written in Rust. Definitely worth a look.

there's def truth in that

yep, here's one https://github.com/lmnr-ai/flow?tab=readme-ov-file#llm-agent...

here's a good one https://github.com/lmnr-ai/flow?tab=readme-ov-file#llm-agent...

Thank you for your comment and wanted to add some clarifications.

1. tasks are not explicitly called from another task In your example greet() is never called, instead task with id=greet will be pushed to the queue

2. The reason I opted for distributed task approach is precisely to eliminate await task_1 await task_2 ...

Going to the point 1, task_2 just says to the engine, ok buddy, now it is time to spawn task_2. With that semantics we isolate tasks and don't deal with the outer tasks which calls another tasks. Also, parallel task execution is extremely simply with that approach.

3. Deadlocks will happen iff you will wait for the data that is never assigned, which is expected. Otherwise, with the design of state and engine itself, they will never happen.

https://github.com/lmnr-ai/flow/blob/main/src/lmnr_flow/stat...

https://github.com/lmnr-ai/flow/blob/main/src/lmnr_flow/flow...

4. For your last point, I would argue the opposite is true, it's actually much harder to maintain and add new changes when you hardcode everything, hence why this project exists in the first place.

5. Regarding deployment. Flow is not a temporal-like (yet), everything is in-memory and but I will def look into how to make it more robust

burr looks very interesting!

For me Agent is essentially a decision making machine. I had many iterations on the software around building agents and Flow is the culmination of all of the learnings.

For some reason some LLM specific examples just slipped of my mind because I really wanted to show the barebone nature of this engine and how powerful it is despite its simplicity.

But you also right, it's general enough that you can build any task based system or rebuild complex system with task architecture with Flow.

Signal is clear, add more agent specific examples.

oh, got it :)

- AI auditor of Otel traces - wealth manager advisor - AI data engineer to name most interesting cases without giving too much details

but also many chat bots and assistants too