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).
Cometline
An AI companion that remembers, learns, and gets things done
Cometline is a local-first desktop AI assistant with semantic memory, agent delegation, slash-command skills, multi-provider support, MCP tools, and a native-feeling macOS interface.
Hey Product Hunt!
I’ve always loved exploring software. Some of my favorite products include Heptabase, Dia Browser, Hermes Agent, and Cursor. Whenever I discover a feature that feels truly thoughtful, I still get excited and think: it’s amazing that we get to live in a time like this.
When the Agentic AI wave started taking off, I wanted to join in and learn by building. I also remembered the “submersion learning” approach I experienced at school: jump in, get overwhelmed, and learn while doing 😌
That’s how Cometline came to life.
Cometline started as a toy project — a BYOK AI chat app inspired by the parts I love from different tools, with a few personal ideas added on top. It supports:
1. Workspace-based context isolation
2. Discord integration
3. Spawning sub-agents through ACP
4. Coding delegation with claude code, opencode and codex
5. Long-term memory and reusable skills
6. A carefully crafted desktop UI/UX
The frontend is built with Svelte and Electron, while the agent core and database layer are written in Go with SQLite.
There’s still a lot to improve, but I recently realized that Cometline can now help me improve Cometline itself. That felt like a small but meaningful milestone.
So today is the day I’m finally sharing it with everyone. 🎉 Thanks for checking it out!
the local-first approach is exactly what i've been looking for, especially the semantic memory piece. one thing that would really help me is a quick way to export my agent's memory and conversation history to plain markdown files so i can back them up outside the app without needing to dig into a database.
The slash-command skills feel snappy and the semantic memory actually surfaces useful context from past threads. Native macOS feel is a nice touch.
About Cometline on Product Hunt
“An AI companion that remembers, learns, and gets things done”
Cometline was submitted on Product Hunt and earned 6 upvotes and 5 comments, placing #160 on the daily leaderboard. Cometline is a local-first desktop AI assistant with semantic memory, agent delegation, slash-command skills, multi-provider support, MCP tools, and a native-feeling macOS interface.
Cometline was featured in Productivity (656.2k followers), Artificial Intelligence (473.7k followers), GitHub (41.3k followers), Tech (628k followers) and Vercel Day (26 followers) on Product Hunt. Together, these topics include over 445.8k products, making this a competitive space to launch in.
Who hunted Cometline?
Cometline was hunted by Tom Liu. 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 Cometline stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Tom Liu