Singularity 是面向开发者的 AI 编码智能体编排工具，用独立 Git worktree 把任务拆成原子工单，支持多仓库并行运行智能体并审查合并，减少上下文消耗。
热门评论
PH 用户
Hey Product Hunt 👋
I'm Antony, co-founder of Meteor Factory with Mehdi and Marine. I've spent 10+ years in DevOps and SRE, and over the last year I kept hitting the same wall with AI coding tools: the chat loop. Prompt, correct, re-prompt. The context fills up, the agent drifts, and you end up babysitting it.
So we built Singularity around a different unit of work: the ticket. One ticket gets one scope, one isolated Git worktree and only the context it needs. You can run several agents in parallel across many repos, get a native notification when one finishes, review the diff and merge.
A real week of use for us: 227 tickets shipped, 86 features, 11 projects, up to 8 agents at once, and about 2 messages per ticket.
What you get: • Code editor, terminal, Git and a ticket board in one desktop app • Works with Claude, Codex, Copilot and Gemini, using your own API key • Your code stays on your machine, only LLM calls go out • Free core: unlimited agents, projects and worktrees
It's in beta, so we'd love your honest feedback: what breaks, what's missing, and how it compares to what you use today. We'll be here all day answering questions.
PH 用户
the 2 messages per ticket number is the part I'd want to pressure-test before trusting this. that's believable for self-contained tickets (add a field, fix a lint rule) but the tickets that actually eat my time are the ones where the fix touches three files I didn't expect and the agent needs a round of "no, not like that" before it lands. does the isolated-worktree model hold up when 8 parallel tickets turn out to overlap in the same file, or is the merge step where all the actual babysitting just moves to instead of disappearing?
PH 用户
I use conductor, how does it compare ?
PH 用户
Can tickets depend on each other, or does each agent always work independently?
I'm Antony, co-founder of Meteor Factory with Mehdi and Marine. I've spent 10+ years in DevOps and SRE, and over the last year I kept hitting the same wall with AI coding tools: the chat loop. Prompt, correct, re-prompt. The context fills up, the agent drifts, and you end up babysitting it.
So we built Singularity around a different unit of work: the ticket. One ticket gets one scope, one isolated Git worktree and only the context it needs. You can run several agents in parallel across many repos, get a native notification when one finishes, review the diff and merge.
A real week of use for us: 227 tickets shipped, 86 features, 11 projects, up to 8 agents at once, and about 2 messages per ticket.
What you get:
• Code editor, terminal, Git and a ticket board in one desktop app
• Works with Claude, Codex, Copilot and Gemini, using your own API key
• Your code stays on your machine, only LLM calls go out
• Free core: unlimited agents, projects and worktrees
It's in beta, so we'd love your honest feedback: what breaks, what's missing, and how it compares to what you use today. We'll be here all day answering questions.