# Seedeep

> What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each subagent on its ow…

- **Website:** https://github.com/duqaXxX/seedeep
- **Pricing:** unknown
- **Categories:** Design, Developer Tools
- **Tags:** design, developer-tools, ai-agents
- **Platforms:** Web, macOS, Windows, Linux, CLI
- **Last verified:** 2026-09-10
- **Canonical page:** https://linkrena.com/tools/seedeep

## About

Claude Code writes a session log to disk as it runs. seedeep tails that log and rebuilds the turn while it is still happening: the context window filling, every API call with its latency and token split, every tool call and its result, and each subagent folded under the spawn that launched it. The same view is there afterwards to walk through.

Read-only. No proxy, no daemon, no session content leaves the machine.

One turn, from 3% to 26% of the window: six subagents on three different models, 2.9M tokens billed, 2.5M of them the same context read again.

Eight things a Claude Code session does not report, and what seedeep shows instead.

A failed API call ends the turn silently. An expired login, a session limit, an overloaded server: the turn stops, the terminal keeps looking normal, and the transcript's last line is the error itself. seedeep turns the tab red, files the session under Broken , and turns the menu-bar icon red above every other signal.

An approval dialog reaches no log at all, so a session stopped on a permission prompt looks identical to one that is thinking. seedeep reads Claude Code's own live state, turns the tab amber the moment it stops, and names what is waiting to be approved.

## Related tools

- [Mulmoterminal](https://linkrena.com/tools/mulmoterminal): Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you.
- [Pr Lens](https://linkrena.com/tools/pr-lens): PR Lens draws every PR as animated architecture and data-flow diagrams, inside the pull request itself.
- [Tare](https://linkrena.com/tools/tare): Ask Claude Code where your usage went.
- [Kit](https://linkrena.com/tools/kit): Kit is a coding agent runtime.
- [OverCLI](https://linkrena.com/tools/overcli): Desktop control plane for Claude Code, Codex, Gemini, Copilot, and Ollama, with credit-aware model routing.
- [Routi](https://linkrena.com/tools/routi): Routi Bot: persistent bots with their own minds and screens, on any AI provider - narralabs/routi