Directory · Subagents

claude-esp

Go TUI that streams Claude Code's thinking, tool calls, and subagent activity to a separate terminal in real time.

★ 155 stars · last updated 2026-09-22 · Free, open source · View on GitHub

Best for

• Watching collapsed thinking and tool output without pressing Ctrl+O in the main session
• Monitoring subagents and background tasks across multiple active Claude Code sessions
• Tracking token usage and per-agent context size during long sessions
• tmux split-pane workflows alongside an interactive claude session

Install

go install github.com/phiat/claude-esp@latest

Our take

Read-only watcher that tails Claude Code's JSONL transcripts under ~/.claude/projects using fsnotify, with a polling fallback for filesystems like NFS or some WSL2 setups. It surfaces many session events (hooks, compaction, cache misses, cost summaries) and offers per-session filtering, solo, and auto-collapse. Requires Go 1.23+ to build, with pre-built binaries for Linux, macOS, and Windows; a Rust port also exists, and parsing depends on Claude Code's undocumented transcript format.

Similar subagents

• Awesome Claude Code Subagents (VoltAgent): A curated collection of 161+ Claude Code subagent definitions across 10 categories, installable as plugins or individual agent files.
• claude-devtools: Desktop and web app that reads local Claude Code session logs to show tool calls, token usage, subagent trees, and context.
• AI Marketing Suite for Claude Code: Claude Code skills and parallel subagents for marketing audits, copywriting, email sequences, ad copy, and client-ready reports.
• pentest-ai-agents: 50 Claude Code subagents turning Claude into an offensive security research assistant for authorized penetration testing.
• Translate Book: Agent skill for Claude Code, Codex, and OpenClaw that translates whole PDF/DOCX/EPUB books using parallel subagents per chunk.
• Claude Code Sub-Agents (lst97): A collection of 33 specialized Claude Code subagents for full-stack development, plus an agent-organizer for multi-agent orchestration.