** 지난 주 버그가 해결되었습니다. 다음 에이전트 세션은 아이디어가 없습니다.**

CLI Agent를 위한 Local-first Memory layer. sessiongrep]는 Claude Code, Codex CLI, Cursor, Antigravity, Pi session histories를 단일 SQLite + FTS5 데이터베이스에 색인하여 항목, repo, 공급자 또는 recency에 의해 이전 작업을 검색하는 CLI/TUI를 제공합니다. 또한 MCP 서버를 배송하므로 에이전트는 자신의 역사를 검색 할 수 있습니다.

실제 payoff는 휴대용 컨텍스트입니다: 세션 역사는 하나의 도구로 갇혀 있지 않습니다. Claude Code에서 시작된 작업은 Codex에서 계속 될 수 있으며, 에이전트는 복구 할 수 있습니다. 그리고 심지어 critique - 당신이 사용하는 모든 도구의 사전 이유.

발표를 읽으십시오: Sessiongrep: CLI 대리인을 위한 국부적으로 첫번째 기억 층.

왜

세션 성적표는 이미 기계에 살고 있습니다. ~/.claude/projects, ~/.codex/sessions], ~/.cursor/projects] opaque filename을 가진 noisy JSONL로 흩어져 있습니다. 이 정보는 누락되지 않습니다. 인간은 그것을 읽을 필요가 없습니다; 대리인은 그것을 검색하는 방법을 모른다. 툴 페이로드에서 JSONL 드론에 Grep. Shell History는 명령을 캡처하지만 이유가 없습니다.

sessiongrep

You solved that bug last week. Your next agent session has no idea.

A local-first memory layer for CLI agents. sessiongrep indexes your Claude Code, Codex CLI, Cursor, Antigravity, and Pi session histories into a single SQLite + FTS5 database, then gives you one CLI/TUI to find old work by topic, repo, provider, or recency. It also ships an MCP server so your agent can search its own history.

The real payoff is portable context: your session history isn’t trapped in one tool. Work you started in Claude Code can continue in Codex, and an agent can recover — and even critique — its own prior reasoning across every tool you use.

Read the announcement: Sessiongrep: a local-first memory layer for CLI agents.

Why

Session transcripts already live on your machine — scattered across ~/.claude/projects, ~/.codex/sessions, ~/.cursor/projects as noisy JSONL with opaque filenames. The information is not missing, it’s stranded. Humans don’t want to read it; agents don’t know how to retrieve it. Grep over JSONL drowns in tool payloads. Shell history captures commands but not reasoning. Cloud-synced or vector-backed alternatives bring secrets and URLs into systems that aren’t yours.

sessiongrep keeps recall local. One static binary, one SQLite file, no daemon, no server. The index is a disposable cache — delete it and rebuild it whenever you want.

How it works

Provider adapters normalize Claude, Codex, Cursor, Antigravity, and Pi transcripts into a single Session model and write them into SQLite (WAL mode) with an FTS5 virtual table over transcript text, title, summary, and preview. Every read command runs an incremental reindex first — files whose mtime and size haven’t changed are skipped, so search and list stay fast even as your history grows.

Only the conversation is indexed: your prompts and the agent’s replies. Tool calls and their output, injected context (AGENTS.md, skill bodies, system reminders), and sub-agent transcripts are left out, so a hit points at what was discussed rather than at every file an agent happened to read. Titles come from each tool’s own session names where they exist (Claude Code’s /rename and generated titles, Codex thread names), falling back to the first prompt.

Installation

You need session history from at least one of Claude Code, Codex CLI, Cursor, Antigravity, or Pi.

Prebuilt binaries (macOS, Linux)