HN Explorer

Show HN: OpenChart – OSS TradingView alternative with your own AI agent (github.com)

6 points by Warren93 ↗ HN
Hi HN, I'm Weilun, cofounder of OpenChart.

We built OpenChart because we wanted Claude and Codex to interface with the markets, like most of humans do, through charts rather than through CLIs.

With your existing AI plans, your agent can work directly with your charts: annotate a setup, write an indicator, investigate a market move, or create an alert. The chart, conversation, and research live in the same workspace.

OpenChart alerts on any market move: draw any shape on a chart and attach an alert. When price crosses it, the alert triggers your agent to investigate the move and save the research in your workspace. The agents can work with charts, indicators, and alerts. Custom indicators and alert conditions are written in [Tea](https://github.com/longsurf-ai/tea), a programming language we built for the markets.

We believe software shouldn’t impose artificial friction on your workflow. OpenChart is built on that belief with no software cap. The source code is publicly available, and you can use free market data from day one. We also offer optional paid cloud market data for lower latency.

Everything is private. Your charts, research, and indicator code are stored on your own computer, with the app's backend running locally too.

We currently support only macOS on Apple Silicon, but we're expanding to more platforms.

Website: https://openchart.co/

Download: https://downloads.longsurf.ai/openchart/darwin/arm64/OpenCha...

We built OpenChart because we want to explore how assets can be co-manages by agents and humans. I'd especially like to hear how you are using agents to help with your investment journey.

If you like what we're building, a star on GitHub would mean a lot to us: https://github.com/longsurf-ai/openchart

27 comments

[ 4.0 ms ] story [ 25.6 ms ] thread
aurielws
Really like the design choice of keeping everything local (charts, research, indicator code). Privacy-first + open source + agent-native is a combination I haven't seen anyone else ship for markets. Following this closely.
Warren93
Right, privacy is really important for a lot of traders. It also comes with the benefit that agents knows your investing context, which is usually stored in your local laptop.
ranli
Very interesting work, finally we have a local first unification layer on codex and cc
Warren93
thanks! We design our system to work with any harness (with a communication protocol that is provider agnostic). In theory we should be able to support any one of them.
aidiveyt
Watch alert-triggered runs: after an hour idle my Claude Code sessions rewrote ~130k cache tokens.
homerg
a local tradingview to me, great work
indigo-lu
I really need an open-source alternative to TradingView, ideally something that can run locally. Now got it, thanks :)
Warren93
Thanks, we really think that creating software friction is not a good thing in 2026..

Glad you like it!

crosscorsair
Haven’t been this excited about a project in a long time! I haven’t found any other tool that integrates a Claude subscription as seamlessly as OpenChart does. Well done guys!

As a casual trader, I’d personally love to see iOS/Android support at some point. That would make this incredibly useful for me day to day.

Warren93
Thanks! Part of the hard part is that the AI subscription cannot run easily on the mobile, but we ARE expanding to more platforms very soon
suki_buildz
The alert waking the agent to investigate on its own is the part I find interesting. Annotating a chart is easy to undo, but is there a line where it has to stop and ask, like anything that places an order or sends something out?
cw1993cw
amazing app. i tried for a few hours and i feel it save tons of my time to do analysis of stocks
onel
Great work and props for focusing on keeping everything local and private
k10shah
I really like what you guys have done with this. Congratulations!

How do we add our own integrations to integrate my brokers api for say datafeed, alerts (and eventually orders)

Integrating a RAG so that I can store my custom data would make it super useful when using LLMs

Again highly impressed! Best wishes