Zap cleans leftover agent git worktrees

// 20m agoPRODUCT LAUNCH

Zap cleans leftover agent git worktrees

Zap is an open-source Go CLI and TUI that automatically detects and clears abandoned Git worktrees left behind by coding agents like Claude Code, Cursor, and Codex. It features interactive safety checks, automatic branch backups, and an undo command to reclaim gigabytes of disk space consumed by duplicated dependencies.

// ANALYSIS

As coding agents standardize on multi-worktree execution to isolate parallel edits, developers are discovering that background tasks silently balloon local disk usage with duplicate build caches. Zap addresses a glaring quality-of-life hole in the agentic development toolchain by turning tedious worktree hygiene into a safe, one-command routine.

–Coding agents like Claude Code create dedicated worktrees per prompt, but merged tasks leave heavy node_modules and target directories lingering indefinitely.
–Interactive TUI inspection (`zap map`) surfaces hidden storage hogs across agent transcripts, session caches, and linked worktrees.
–Safety-first defaults require explicit repository opt-in (`.zap`), check for uncommitted changes or open shells, and back up Git refs before deletion.
–Dedicated agent skill integration (`SKILL.md`) allows agents to self-audit and clean their own worktree footprint programmatically.

// TAGS

zapai-codingcoding-agentdevtoolcliopen-source

DISCOVERED

20m ago

2026-11-15

PUBLISHED

53m ago

2026-11-15

RELEVANCE

7/ 10

AUTHOR

nsxdavid

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE50m ago

super.engineering slashes memory, CPU after ADEMark

super.engineering rolled out performance optimizations inspired by the new ADEMark benchmark, cutting startup memory by 42% and active agent CPU load from 20% to 8%. The native Rust agent harness also reduced per-chat memory by 40% and tab-naming token usage by 88%.

OPEN SOURCE2h ago

GGML hits 1.0, slashes prompt latency

The foundational C/C++ tensor library behind llama.cpp has officially reached version 1.0.0, establishing a stabilized public API alongside significant prefill and inference optimizations. Benchmarks demonstrate immediate performance gains on unchanged hardware, cutting runtime on a 50K-token prompt from 4:22 down to 3:59.

RESEARCH3h ago

NVIDIA cuts reasoning distillation compute 38%

NVIDIA researchers demonstrate that forward-KL reasoning LLM distillation requires supervising students on only the teacher's top probability tokens rather than the full vocabulary. Distilling exclusively from truncated teacher support matches full-distribution benchmark accuracy while cutting training step time by 38% and peak memory by 24%.