HN Showcase
Back to browse
GitHub Repository

Fast CLI to search across all Claude Code session history

29 starsRust

Search-sessions – Search all your Claude Code session history in <300ms

by sinzin91·Feb 23, 2026·4 points·4 comments
Visit ProjectView on HN

AI Analysis

●●●BangerSolve My ProblemShip ItNiche Gem

Skip the database entirely—raw JSONL search for Claude sessions in 18ms.

Strengths
  • •Zero-dependency Rust binary is the right tool choice; ripgrep integration gives 3-5x speedup without forced bloat.
  • •Directly solves Claude Code's biggest friction: sessions are lost after context window, making repeated problem-solving impossible.
  • •Seamless Claude integration—tool works *inside* Claude Code via `/search-sessions` skill, not a separate TUI to learn.
Weaknesses
  • •Niche audience—only valuable if you're already deep in Claude Code workflow; won't appeal to Continue or Copilot users.
Target Audience

Claude Code / OpenClaw users managing months of session history

Similar To

Cursor's session persistence · Continue IDE extension (broader LLM memory) · Sourcegraph Cody (broader codebase Q&A)

Post Description

Claude Code forgets everything between sessions. After months of heavy use, I had 1.6GB of JSONL session files buried in ~/.claude/projects/. Architecture decisions, debugging breakthroughs, and solutions I couldn't find again. There’s nothing more annoying that solving the same problem twice.

I tried RAG pipelines and local vector DBs, but they added complexity for a problem that's really just text search over structured files. So I built search-sessions: a single Rust binary that searches your session history directly. No database, no indexing step, no dependencies.

It supports two modes: index search (~18ms) for finding the right session, and deep search (~280ms with ripgrep, ~1s without) for matching against full message bodies. Each result includes the session UUID so you can resume any conversation with `claude --resume`.

The design choice that makes it work: skip the database entirely. JSONL files are already structured — just search them fast. Under the hood it's just files and a CLI, so it's easy to inspect, backup, and delete. You install it as a Claude Code skill, then ask "do you remember that auth refactor?" and Claude searches your history and picks up the thread. It also works with OpenClaw.

MIT licensed. macOS and Linux:

brew install sinzin91/tap/search-sessions

or

cargo install search-sessions

Curious what people think about exact vs fuzzy vs semantic search as a default — and which other coding CLIs you’d like supported.

Similar Projects