ContextFind — Search your local AI coding sessions

Instantly find and resume any past Claude Code / Codex session across projects and machines.

Problem

Heavy users of Claude Code, Codex and similar local AI harnesses accumulate session transcripts scattered across project folders and machines. Recovering that one conversation about a migration script means digging through shell history and files. Someone already hand-built a local cross-project, cross-machine search-and-resume tool, which proves the pain is real and currently self-solved.

Solution

A local daemon indexes session files and transcripts from popular harnesses, exposing full-text search from a CLI and a lightweight GUI. Users filter by keyword, project, time or file, then resume in-context or copy the thread into any harness to continue. Everything stays offline and local by default.

Users

Indie developers and small teams who use two or more AI coding harnesses across multiple machines daily.

MVP

Local scan plus full-text index, starting with just Claude Code and Codex directory layouts; a CLI command that outputs matching session summaries and paths; one-shot resume command printing; plain-text index stored in the user's home with a clear wipe option.

Revenue

Free open-source CLI for distribution; Pro subscription at $5–8/month adds cross-machine sync via user's own object storage, semantic search, tagging and team-shared indexes.

Why now

AI coding harnesses are proliferating, session fragmentation is just beginning, and no accepted retrieval layer exists yet. A local index needs no API or cloud and can ship in one to two weeks.