Silu

taste. strategy. imagination.

[Silu @stevensilu]

@saen_dev I index a useful slice of each session: titles, prompt summaries, workspace paths, dates, and output files - which is enough for your identify the one you are looking for. The full conversation stays in the original tool, with a link back when you need more context.

[Silu @stevensilu]

Have you ever remembered the project, but forgotten whether the conversation was in Codex, Claude, or Kimi?

That kept happening to me, so I built my first open-source project with coding agents: AI Project Finder.

It creates a private, local search index for work spread across different AI tools. Search with whatever clue you remember: a project or client name, a prompt fragment, a workspace, or a filename.

Key features:
• Indexes local Codex, Claude Code, and Kimi Code histories
• Organizes results by session or project
• Returns you to the matching AI session and workspace
• Keeps the index on your computer
• Supports macOS and Windows

Here is a 26-second demo. GitHub is in the first reply.

#BuildInPublic #AIAgents

[Silu @stevensilu]

@0xhashlol Yes. I use source-specific adapters for each tool, then map everything into one normalized local index. ：）

[Silu @stevensilu]

GitHub:

https://t.co/S5Ok4l87NR