# AI use cases for Openchart (longsurf-ai/openchart) Repo: [longsurf-ai/openchart](https://github.com/longsurf-ai/openchart) | Use cases: 5 | Page: https://dedupedai.com/use-cases/longsurf-ai-openchart/ OpenChart is an open source TypeScript trading workspace where AI agents help with charts, indicators, alerts, and market research. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Draw a price level and get alerted when it breaks: https://dedupedai.com/use-cases/longsurf-ai-openchart/draw-chart-and-alert-on-levels/ - Explain what moved a chart with sourced annotations: https://dedupedai.com/use-cases/longsurf-ai-openchart/explain-a-price-move-with-sourced-notes/ - Turn a plain-language watch rule into a Tea monitor: https://dedupedai.com/use-cases/longsurf-ai-openchart/build-alert-monitor-from-plain-language/ - Write a custom indicator in Tea: https://dedupedai.com/use-cases/longsurf-ai-openchart/write-custom-indicator-in-tea/ - Set up a source build to contribute to OpenChart: https://dedupedai.com/use-cases/longsurf-ai-openchart/set-up-source-build-for-contributors/ ## How to draw a price level and get alerted when it breaks with Openchart Repo: [longsurf-ai/openchart](https://github.com/longsurf-ai/openchart) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Install the Desktop app, draw a line or zone on a chart, and set an alert for when price crosses it. **Who it is for:** A retail investor who watches a few assets and wants a chart with alerts at key price levels, without writing code. **The problem:** Checking charts all day to see if price has reached a level you care about takes time and attention. **The outcome:** A chart with your own drawn level and an alert that fires when price crosses it. ### Steps 1. Download Desktop for macOS (Apple Silicon) from the link in the README and open the disk image. 2. Install OpenChart from the disk image and open the app. 3. Open a chart for the asset you follow and draw a line or zone at your target price. 4. Set an alert on that drawn level, then follow the setup guide at https://openchart.co/docs/getting-started/ if you need help with your first alert. ### Prompt to paste into your agent ```text Using the OpenChart app on my Mac, help me draw a line at on the chart and set an alert for when price crosses it. Expected output: a confirmed alert on that level. Verify the alert appears in the app's alert list before you finish. ``` ### Caveat The README gives only the Apple Silicon macOS download, so other platforms need the source build path. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/longsurf-ai-openchart/draw-chart-and-alert-on-levels/ ## How to explain what moved a chart with sourced annotations with Openchart Repo: [longsurf-ai/openchart](https://github.com/longsurf-ai/openchart) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README Select a price range and have your agent research the move, with source-linked notes pinned to the bars. **Who it is for:** A trader or analyst who sees a sharp move on a chart and needs to know what drove it before deciding anything. **The problem:** Finding the news and context behind a price move by hand across many sources is slow. **The outcome:** Annotations pinned to the relevant bars, each linked to the source the agent used. ### Steps 1. Download and open Desktop, following the install steps in the README. 2. Connect your agent provider account (Claude, Codex, or Gemini models) so the agent can run. 3. Open a chart and select the range of bars where the move happened. 4. Ask the agent to explain the move, then review the source-linked annotations pinned to the bars. ### Prompt to paste into your agent ```text In the OpenChart app, select the bars from to on the chart and ask the agent what moved the price. Expected output: annotations pinned to those bars, each with a source link. Verify that each annotation links to a source you can open before you rely on it. ``` ### Caveat The README does not say how the agent chooses its sources, so check each linked source yourself before trading on the explanation. Risk, credentials: The agent runs on your own provider account, so keep those login details private and do not paste them into chats or screenshots. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/longsurf-ai-openchart/explain-a-price-move-with-sourced-notes/ ## How to turn a plain-language watch rule into a Tea monitor with Openchart Repo: [longsurf-ai/openchart](https://github.com/longsurf-ai/openchart) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Describe a market condition to your agent and get a Tea monitor that checks incoming data and investigates when it fires. **Who it is for:** An investor with a specific rule in mind, such as a volume or price pattern, who does not want to write monitoring code. **The problem:** Watching for a specific market condition across assets is hard to keep up with by eye. **The outcome:** A Tea monitor that evaluates incoming data for your condition and runs an investigation when it fires. ### Steps 1. Run `just install --frozen-lockfile` from the cloned Openchart folder to install dependencies and build Tea. 2. Run `just desktop` to start the app. 3. Describe in plain words the condition you want to watch, and let your agent build the Tea monitor. 4. Confirm the monitor is set to evaluate incoming data and investigate when the condition fires. ### Prompt to paste into your agent ```text In the openchart repo, create a Tea monitor that watches for on and investigates when it fires. Expected output: a monitor definition that evaluates incoming data and triggers an investigation. Verify by checking that the monitor compiles and that the condition matches the rule I described. ``` ### Caveat The README does not document the monitor file format or how Tea monitors are deployed, so the agent should read the Tea documentation before relying on its output. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/longsurf-ai-openchart/build-alert-monitor-from-plain-language/ ## How to write a custom indicator in Tea with Openchart Repo: [longsurf-ai/openchart](https://github.com/longsurf-ai/openchart) | Difficulty: Advanced | Time: 2 hours | Basis: From the README Code your own indicator or condition in Tea using functions, loops, state, and collections. **Who it is for:** A developer or quant who wants a market indicator that the built-in studies do not provide. **The problem:** Off-the-shelf indicators may not match the exact logic you want to test. **The outcome:** A custom Tea indicator that evaluates as market data flows in, running inside OpenChart. ### Steps 1. Clone the repo with `git clone https://github.com/longsurf-ai/openchart.git`, then run `cd openchart`. 2. Run `just install --frozen-lockfile`, which also initializes and builds Tea. 3. Read the Tea compiler and runtime at https://github.com/longsurf-ai/tea and write your indicator with functions, loops, state, and collections. 4. Run `just desktop` and load the indicator on a chart to check how it evaluates as data arrives. ### Prompt to paste into your agent ```text In the openchart repo, write a Tea indicator that computes on the chart. Expected output: a Tea source file that compiles and draws the indicator on the chart. Verify by loading it with `just desktop` and checking the values against a few bars you calculate by hand. ``` ### Caveat The README lists the Tea language features but does not document Tea syntax, so the Tea repo is the source of truth for writing indicators. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/longsurf-ai-openchart/write-custom-indicator-in-tea/ ## How to set up a source build to contribute to OpenChart with Openchart Repo: [longsurf-ai/openchart](https://github.com/longsurf-ai/openchart) | Difficulty: Advanced | Time: 1 hour | Basis: From the README Clone the repo, install the pinned toolchain, run the app from source, and run checks before a pull request. **Who it is for:** A developer who wants to improve OpenChart's built-in studies, documentation, or code. **The problem:** Contributing needs a working local build that matches the project's pinned tool versions. **The outcome:** A running Desktop app built from source, with the project checks passing before you open a pull request. ### Steps 1. Install Node.js 24, npm 11.11.1, Bun 1.4.2, and Just, using the links in the README. 2. Run `git clone https://github.com/longsurf-ai/openchart.git` and then `cd openchart`. 3. Run `just install --frozen-lockfile` and then `just desktop`. 4. Read docs/development.md and docs/architecture/code-organization.md, make your change, then run `just check` before submitting a pull request. ### Prompt to paste into your agent ```text In the openchart repo, make the change described in and prepare a pull request. Expected output: a branch with the change and a passing `just check` run. Verify that `just check` passes before you open the pull request. ``` ### Caveat The README pins exact versions of npm and Bun, so using different versions may break the build. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/longsurf-ai-openchart/set-up-source-build-for-contributors/