Skip to content
Agents tracked: 258 Downloads (7d): 219M up 6.1% GitHub stars: 5.5M VS Code installs: 148M Releases (7d): 327 Agent status: 1 with issues Updated Oct 7, 2026
AgentGid
Showcase Longsurf AI

Run an open-source charting app with your own AI agents using OpenChart

Longsurf AI publishes OpenChart, an open-source desktop charting app that lets users connect their own Claude, Codex or Gemini accounts to research markets, build indicators and set up alerts. The project is a GitHub repository with a macOS download and a from-source build.

The problem

Charting platforms typically limit charts, indicators and alerts by plan and bundle their own AI. The project positions OpenChart as an alternative where users bring the AI agents and accounts they already have.

How they did it

  1. Download the macOS (Apple Silicon) desktop app and install it from the disk image.
  2. Or build from source: install Node.js 24, npm 11.11.1, Bun 1.4.2 and Just.
  3. Clone the repository, then run just install --frozen-lockfile and just desktop.
  4. Connect your own Claude, Codex or Gemini account as the agent provider.
  5. Follow the setup guide to create a first chart and alert.
  6. Describe what to watch so the agent builds Tea monitors that check incoming data.

From the official docs

git clone https://github.com/longsurf-ai/openchart.git
cd openchart
just install --frozen-lockfile
just desktop

Results

  • Charts, indicators and price and indicator alerts have no software plan limits, according to the README.
  • Charts can be expanded to a 4×4 grid, with indicators and Volume Profile.
  • Agents can research a selected price move and pin source-linked annotations to the bars.
  • Desktop is free, AI usage follows the agent provider's plan, and optional Cloud market data is priced separately.

As reported by the source (OpenChart GitHub repository README); AgentGid did not measure these figures.

Takeaway. If you already pay for an AI coding or chat agent, you can reuse it as the research and alerting layer of a charting tool instead of buying a separate AI add-on.
AgentGid's take

Suits individual traders or developers who already pay for Claude, Codex or Gemini and are comfortable with a GitHub project; the macOS Apple Silicon download is simplest, while other platforms mean building from source with Node.js, Bun and Just. Watch the costs: the "no plan limits" claim comes from the README, AI usage still runs against your provider's plan, and Cloud market data is priced separately. AgentGid has no listed alternatives for this case.

Read the full story at OpenChart GitHub repository README ↗

Similar use cases

Case studyNorges Bank Investment Management (NBIM)

How NBIM rolled out Claude to investment and compliance staff

NBIM, which manages Norway's sovereign wealth fund, deployed Claude across investment research, ESG analysis, compliance and data operations. Anthropic reports weekly time savings…

According to Anthropic, employees save 20% of their week on the analytical and operational work they now do with Claude.

Claude CodeClaudeResearch · Data analysis
Recipe

Run LangChain's Open Deep Research multi-agent pipeline locally

LangChain's open-source deep research agent, built on LangGraph, runs research sub-agents in parallel, compresses what they find and writes a final report. It works with many mode…

On Deep Research Bench, the default GPT-4.1 configuration scored 0.4309 and the GPT-5 configuration 0.4943.

LangGraphResearch · Reporting
ShowcaseWeave

Route between coding-agent models with the open-source Weave Router 2.0

The Weave team presented Weave Router 2.0 in a Show HN post. It is an open-source routing model that sits in front of coding agents and switches between LLMs per turn, and the aut…

As reported by the Weave author on Hacker News: on Terminal Bench 4.0 and SWE Atlas, the router had equivalent pass rates to GPT-6 Astra.

Claude CodeOpenAI CodexOpenCodeWeave RouterCodexDevOps and CI · Workflow automation