Porch is an open-source work log for your coding agents, as a Mac app. It summarises your Claude Code and Codex work by project, day, week and month: what you did, where the time went, and what got stuck — leaving out breaks over ten minutes, counting parallel work once, and saying so when the records do not show why something stalled. Summaries can be saved as Markdown into a folder you pick, usually an Obsidian vault, and a notification shows the one-line summary when one finishes. It also lists sessions across whichever terminal or editor launched them, and reports tokens and API-equivalent cost by project, model and tool.
Be the first to rate Porch. Your feedback helps other users decide.
Open Porch for what you did today, this week or this month, per project, with time per task and blockers.
Have summaries written as Markdown into your Obsidian vault or another folder.
See tokens and API-equivalent cost by project, model and tool, plus Claude and Codex limit windows.
Similar tools in the same category — compare side-by-side
Chelis is a numerical computing language for code that agents write and people supervise. Tensors ca...
paste-preview is a Claude Code mod for the images you paste. In a terminal a pasted image is just [I...
what-would-it-cost is a Claude Code cost tracker: what your Pro or Max subscription would cost at AP...
Guides and comparisons about code tools
Ten Show HN launches that turn an opaque agent run into something you can see: step progress, session state, approvals, image paste and voice.
Nine launches that draw the line around an agent: policy proxies, guard hooks, semantic permissions, sandboxes, worktrees and a proof checker.
Eight launches that give agents a place to work: a browser, a terminal grid, a recording runtime, a process CLI and a reverse-engineering IDE.
Seven launches for the edges of the tool set: decision records, calibrated decision models, interpretability, teaching apps and agent marketplaces.
Four Show HN launches that verify agent work rather than trusting its summary: an execution record, an AI-app scanner, a local guardrail and adversarial tests.
