This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Bullpen.sh
Stock and portfolio research through your own coding agent
Desktop app for stock and portfolio research through coding agents like Claude Code, Codex, and Gemini. Reports with sources. Your keys, your keychain. Data stays on your machine.
I've been building Bullpen.sh lately. It's one of a few "one-skill-apps" I'm working on, all following the same pattern: a thin layer of opinionated GUI + data structure on top of my local coding agents. All using the combo of Tauri + AgentClientProtocol + MCP. Super strong
The idea is simple. I take something I do over and over freeform with an agent. Put structure around it. Force the agent to submit findings in a schema, store it in a structured DB, and visualize it.
So far these mini one-skill-apps perform better for me than raw agents + skills. Not sure they're 10x better for anyone else, but they're 10x better fit for my needs than just using the agent itself.
No comment highlights available yet. Please check back later!
About Bullpen.sh on Product Hunt
“Stock and portfolio research through your own coding agent”
Bullpen.sh was submitted on Product Hunt and earned 3 upvotes and 1 comments, placing #84 on the daily leaderboard. Desktop app for stock and portfolio research through coding agents like Claude Code, Codex, and Gemini. Reports with sources. Your keys, your keychain. Data stays on your machine.
Bullpen.sh was featured in Productivity (650.8k followers), Open Source (68.4k followers), Investing (26.6k followers) and GitHub (41.2k followers) on Product Hunt. Together, these topics include over 167.6k products, making this a competitive space to launch in.
Who hunted Bullpen.sh?
Bullpen.sh was hunted by Shy Alter. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Bullpen.sh stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Shy Alter
I've been building Bullpen.sh lately. It's one of a few "one-skill-apps" I'm working on, all following the same pattern: a thin layer of opinionated GUI + data structure on top of my local coding agents. All using the combo of Tauri + AgentClientProtocol + MCP. Super strong
The idea is simple. I take something I do over and over freeform with an agent. Put structure around it. Force the agent to submit findings in a schema, store it in a structured DB, and visualize it.
So far these mini one-skill-apps perform better for me than raw agents + skills. Not sure they're 10x better for anyone else, but they're 10x better fit for my needs than just using the agent itself.