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 Thumbnail

mlx-code

Local coding agent for Mac with git-backed subagents

Open Source
Developer Tools
Artificial Intelligence
GitHub
YouTube
Visit WebsiteSee on Product HuntYouTubeGithub

Hunted byJosef AlbersJosef Albers

mlx-code is an open-source coding agent for Mac built on Apple's MLX. It supports local models and external APIs, plus subagenting for delegation when context starts to decay. You can customize behavior with system prompts, skills, custom tools, and alternate harnesses, while keeping every step captured in git commits for full traceability and easy rollback. It’s designed as a flexible building block for agent workflows, from conversational coding to sandboxed multi-agent systems.

Top comment

mlx-code is built for people who want agents they can shape, inspect, and trust. Every agent action happens in an isolated git worktree and is captured as a commit, giving you a complete audit trail, instant rewind to any point, and no risk to your working branch. You can spin up separate agents for separate concerns, review their commits, and merge only what you want. It also works the way you work: chain it through terminal pipelines, import it in Python to build custom workflows, connect it to local models or APIs, or swap in your own harness and custom tools. Whether you want a simple local coding assistant or to script a complex, multi-agent CI pipeline, mlx-code gives you the exact pieces you need.

Comment highlights

No comment highlights available yet. Please check back later!

About mlx-code on Product Hunt

Local coding agent for Mac with git-backed subagents

mlx-code was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #143 on the daily leaderboard. mlx-code is an open-source coding agent for Mac built on Apple's MLX. It supports local models and external APIs, plus subagenting for delegation when context starts to decay. You can customize behavior with system prompts, skills, custom tools, and alternate harnesses, while keeping every step captured in git commits for full traceability and easy rollback. It’s designed as a flexible building block for agent workflows, from conversational coding to sandboxed multi-agent systems.

mlx-code was featured in Open Source (68.5k followers), Developer Tools (514k followers), Artificial Intelligence (471k followers), GitHub (41.3k followers) and YouTube (16.9k followers) on Product Hunt. Together, these topics include over 211.9k products, making this a competitive space to launch in.

Who hunted mlx-code?

mlx-code was hunted by Josef Albers. 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 mlx-code stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.