Engineering Memory Overview
See collaboration patterns through agent activity, token trends, smart tags, and bookmarked sessions.
v0.7.2 Latest
Turn AI coding historyinto reusable engineering memory.
CodeSesh discovers local sessions from Claude Code, Cursor, Kimi, Codex, and OpenCode, then preserves problems, reasoning, attempts, file activity, and outcomes in one project-aware searchable memory layer.
Start from your machine
$ npx codesesh Requires Node.js 18+ · Runs locally from your terminal
$ npx codesesh ╭────────────CodeSesh──────────────╮ │ │ │ v0.7.2 • local session browser │ │ │ ╰──────────────────────────────────╯ ℹ Indexing Claude Code, OpenCode, Kimi-Cli, Codex, Cursor sessions in the background.ℹ The Web UI will update automatically as sessions are discovered. http://localhost:4521
Product Tour
How engineering memory compounds in daily work
From overview to replay, from project browsing to structured search, CodeSesh makes coding history across agents visible again.
Structured Global Search
Search titles, messages, tool output, and file paths, then filter by project, tag, tool, file activity, and cost.
Session Replay
Replay messages, tool calls, and file changes in the order a feature or bug fix unfolded.
Keyboard Navigation
Move through projects, sessions, and results efficiently so browsing history fits daily work.
Features
Designed for long-term accumulation
CodeSesh follows the real loop of AI-assisted engineering: discover, organize, recover, and replay.
Discover
Bring local sessions from different agents into one index.
-
Zero Configuration
Run one command and scan supported agent sessions on your filesystem.
-
Live Refresh
Local session changes appear automatically as new collaboration records are written.
-
Unified Timeline
Browse Claude Code, Cursor, Kimi, Codex, and OpenCode sessions in one interface.
Organize
Put sessions back into project, task, and engineering context.
-
Engineering Memory Overview
See cross-agent activity, models, tokens, smart tags, and bookmarked sessions together.
-
Project-Aware Session Tree
Group sessions by repository and project identity across supported agents.
-
Smart Tags
Label bugfix, refactor, feature, testing, docs, planning, Git, build, and exploration work.
Recover
Bring old decisions, paths, and context back into the current task.
-
Structured Global Search
Search titles, messages, tool output, and file paths with project, tag, tool, file activity, and cost filters.
-
Session Bookmarks
Save important records so solutions, debugging paths, and key decisions stay traceable.
-
Keyboard Navigation
Move across views, focus search, and navigate groups from the keyboard.
Replay
Reconstruct the full path from problem to result.
-
Full Conversation Replay
Read every message, tool call, and reasoning step in sequence.
-
File Activity Index
Jump to files that were read, edited, created, deleted, or moved, and recover sessions by file activity.
-
Cost & Token Visibility
See token totals, cache tokens, recorded costs, and model-based estimates.
-
SQLite Migrations & Local Index
Use one local database for fast restore, structured search, file activity indexing, and schema migrations.
-
Local & Private
Your data stays on your machine. No accounts, cloud sync, or telemetry.
Supported Agents
Built for the local AI coding stack
Unify multi-agent workflows into one engineering memory layer.
-
Claude Code -
Cursor -
Kimi -
Codex -
OpenCode
FAQ
AI-readable product answers
These answers make CodeSesh easier for search engines and AI systems to extract, cite, and describe accurately.
What is CodeSesh?
CodeSesh is a local developer tool for discovering, aggregating, searching, and replaying AI coding session history. It turns local records from Claude Code, Cursor, Kimi, Codex, and OpenCode into a project-aware engineering memory layer for recovering decisions, file activity, and complete collaboration paths.
Which AI coding tools does CodeSesh support?
CodeSesh currently supports Claude Code, Cursor, Kimi, Codex, and OpenCode. Each tool connects through an agent adapter in the core package, then contributes sessions to unified lists, project browsing, structured search indexes, file activity, smart tags, token statistics, and full replay views.
Does CodeSesh upload local AI session data?
CodeSesh runs on the user's machine and uses a local SQLite index with a local Web UI. Session content, file paths, token statistics, and cost estimates stay on the local computer, which suits developers who want ownership of AI coding context.
How do you install and start CodeSesh?
The fastest way to start CodeSesh is running npx codesesh. CodeSesh scans supported local AI coding sessions and opens the Web UI at http://localhost:4521; if that default port is busy, it automatically tries the next available port. The published CLI requires Node.js 18+; source development uses Node.js 20.19+ and pnpm 10+.