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).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Praxis Chat
Praxis Chat is a private AI workspace for Windows
Your models, your files, your PC. Free during the beta.
Hey Product Hunt 👋 I’m Shanmukh, maker of Praxis Chat.
What it is: a local-first AI coding workspace for Windows. You bring your own model keys (Claude, GPT, Gemini, DeepSeek, Moonshot, anything OpenAI-compatible), point it at a code folder, and agents work on it. Your code, index and history stay in a SQLite file on your PC. The only network calls are to the provider you chose. No telemetry.
Why I built it: I was spending frontier-model money on tasks that a cheap model could do if it just knew the codebase properly. So Praxis builds an exact symbol index of your project (every function, class, call site, with file:line ranges and content hashes) and gives the agent tools to fetch exactly the code it needs instead of reading whole files. A lead model plans, cheap workers execute, and every edit is hash-checked against the file on disk so stale state can’t slip through. We measure all of it on an in-house benchmark of real tasks across four codebases, with DeepSeek V4.1 Flash as the baseline model, and we’ll publish those numbers rather than claims.
What’s in the box today: Windows 10/11 x64, one installer, auto-updates, Python and TypeScript/JavaScript indexed with full precision, LSP via Pyright and the TypeScript server, open beta, and the code is open source.
What’s rough: it’s Windows-only for now (Linux later). Code signing is still in approval, so SmartScreen will warn you on install for another week or so. C#, Java, Go and Rust indexing are next. Expect bugs; there’s a one-click bug report in the chat and I read every one.
What I’d love from you: try it on a real project with the cheapest model you have, and tell me where it fell over. That’s the only feedback that makes it better.
Thanks for having a look.
About Praxis Chat on Product Hunt
“Praxis Chat is a private AI workspace for Windows”
Praxis Chat was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #134 on the daily leaderboard. Your models, your files, your PC. Free during the beta.
On the analytics side, Praxis Chat competes within Developer Tools, Artificial Intelligence and Tech — topics that collectively have 1.6M followers on Product Hunt. The dashboard above tracks how Praxis Chat performed against the three products that launched closest to it on the same day.
Who hunted Praxis Chat?
Praxis Chat was hunted by shanmukh ram. 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.
For a complete overview of Praxis Chat including community comment highlights and product details, visit the product overview.
Hey Product Hunt 👋 I’m Shanmukh, maker of Praxis Chat.
What it is: a local-first AI coding workspace for Windows. You bring your own model keys (Claude, GPT, Gemini, DeepSeek, Moonshot, anything OpenAI-compatible), point it at a code folder, and agents work on it. Your code, index and history stay in a SQLite file on your PC. The only network calls are to the provider you chose. No telemetry.
Why I built it: I was spending frontier-model money on tasks that a cheap model could do if it just knew the codebase properly. So Praxis builds an exact symbol index of your project (every function, class, call site, with file:line ranges and content hashes) and gives the agent tools to fetch exactly the code it needs instead of reading whole files. A lead model plans, cheap workers execute, and every edit is hash-checked against the file on disk so stale state can’t slip through. We measure all of it on an in-house benchmark of real tasks across four codebases, with DeepSeek V4.1 Flash as the baseline model, and we’ll publish those numbers rather than claims.
What’s in the box today: Windows 10/11 x64, one installer, auto-updates, Python and TypeScript/JavaScript indexed with full precision, LSP via Pyright and the TypeScript server, open beta, and the code is open source.
What’s rough: it’s Windows-only for now (Linux later). Code signing is still in approval, so SmartScreen will warn you on install for another week or so. C#, Java, Go and Rust indexing are next. Expect bugs; there’s a one-click bug report in the chat and I read every one.
What I’d love from you: try it on a real project with the cheapest model you have, and tell me where it fell over. That’s the only feedback that makes it better.
Thanks for having a look.