Replay your AI coding sessions
PR diffs show what changed. vibe-replay shows why — every prompt, every thought, every edit, in one shareable file.
A local dashboard shows every session across Claude Code, Claude Desktop, Claude Cowork, Cursor, Codex, OpenCode, Hermes, Pi, and Grok Bot — with activity heatmaps, project analytics, cost estimates, and filters for repositories, tools, MCP servers, skills, and compactions. Muse support is on main and ships in the next npm release. Generate a replay in one click, or add remote Codex/Claude Code/Pi sources over SSH. Watch the Eng+GTM Grok Bot demo.
$ npx vibe-replay -d
Pick a session and step through every prompt, thinking block, tool call, and code diff. Three view modes — All (full detail), Compact (condensed), and Custom (your filters). Navigate with the outline sidebar, search, or playback controls.
Drill into any session for auto-generated analytics: token burn & cost per turn, context window usage, cache accounting, tool/MCP/skill breakdowns, model distribution, percentile views, coverage, and data-quality notes.
See the big picture — GitHub-style activity heatmap, streaks, weekly trends, top projects, model usage, provider breakdown, and cost tracking across all your sessions. Filter by time range to see how your coding evolves.
Export a self-contained HTML file, animated SVG, GIF, or markdown summary, or publish via GitHub Gist/cloud. On current main for the next npm release, Quick Share adds a temporary E2E-encrypted link to one replay without uploading it, while vibe-replay relay enables encrypted remote browse and live-tail. Local HTML stays offline with no automatic external requests.
Try it on your own sessions — takes 10 seconds.
No account or setup is required for local replays. Run npx vibe-replay and pick a session. Optional Settings add remote SSH sources, cloud publishing, and the embedded AI Studio — no external coding CLI required.
Every replay is a single self-contained HTML file with no automatic external requests. Drop it in Slack, email it, open it on a plane. Remote images load only after an explicit click.
Claude Code, Claude Desktop, Claude Cowork, Cursor, Codex, OpenCode, Hermes, Pi, and Grok Bot — all auto-discovered from local files out of the box, including multi-file and resumed sessions. Muse support is on main and ships in the next npm release. Watch the Eng+GTM Grok Bot demo.
Your AI coding wrapped: GitHub-style heatmap, streaks, weekly trends, top projects, model usage, and cost tracking — with drilldowns by provider, tool, MCP server, and time range. Works for local sessions and remote SSH sources alike.
Deep per-session analytics: token burn over time, context window usage, cache hit rates, tool call breakdown, model breakdown, and cost estimates with data-quality hints.
Export HTML, markdown, SVG, or GIF for PRs, or publish via GitHub Gist/cloud. Quick Share is on main for the next npm release: a temporary E2E-encrypted link without uploading the replay. Secret redaction built in.
Analyze, translate, and professionalize replays with the embedded Pi runtime and the provider/model you choose. Bring OpenAI-compatible local gateways or hosted endpoints — no external coding CLI required.
Ask read-only questions about sessions, scenes, tools, MCP usage, coverage, projects, and Insights. Get a stable link back to the exact replay or dashboard view — never an unreviewed mutation.
Add Codex, Claude Code, or Pi sessions from an OpenSSH host using your existing aliases, keys, agents, and ProxyJump setup. Remote data is cached locally and excluded from cloud insight sync.
Install vibe-replay as a plugin and your AI agent learns to generate replays on its own — during PR creation, session review, or on command. No context switching, no manual steps.
Finds your current session automatically — no file paths, no flags.
Generates markdown summary + animated GIF, embeds them in your PR description.
Just say "create a PR with session replay" and the agent handles everything.
Built on the open Agent Skills standard — works in Claude Code, Cursor, Codex, and more.
Install · recommended
/plugin, open the Discover tab, search vibe-replay, and install.Or via CLI
Then use it
Muse keeps one JSONL per agent under ~/agents — with session_header/item/compaction_checkpoint records, thinking as a first-class citizen, and a source field on every item naming the runtime subsystem that wrote it.
Grok Bot’s durable tool timeline is cloud-box agent-transcripts JSONL. The Mac app also keeps a recent UI replica under Application Support, and replay merges the two.
Hermes keeps session metadata, token accounting, reasoning, and tool calls in SQLite — with named profiles, Bot Chat, and two different compaction signals.
Install in seconds. No account needed. No config. Just run the command and share your session.