Skip to main content

Post-crash Claude Code session recovery TUI

Project description

resume-resume

resume-resume

New free tool we're dropping.

Resume Ask Claude Resume to find old programming sessions in plain English, and pick up where you left off.
Prioritize Claude Resume auto-ranks your past chats based on recency and incomplete worktrees, so you don't leave important work unfinished or uncommitted.
Speed Claude Resume uses parallelized search to look through gigabytes of past chats in seconds.
Cost Savings Claude Resume uses Haiku (smallest Claude model) to summarize past context once, then caches it permanently — so after the first run, searching thousands of sessions costs nothing.
Merge Ask Claude Resume to merge multiple old chats together, pulling your thoughts across sessions into a single conversation.

MCP Server

Add it to Claude Code and every session on your machine can search, read, and merge your full session history — in plain English.

pip install resume-resume
claude mcp add resume-resume -- resume-resume-mcp

Or manually in your MCP config:

{
  "mcpServers": {
    "resume-resume": {
      "command": "resume-resume-mcp"
    }
  }
}

We built Eidos, a multi-agent AI system. In our benchmark, Eidos outperformed Claude Opus 4.6 by 3.6x in both accuracy and speed on complex tasks with 15+ reasoning chains. Below, we use Claude Resume to pick up where we left off across multiple sessions.

Finding the benchmark where Eidos beat Claude Opus 4.6

"use resume-resume to find the eidos test where we beat claude"

Claude Resume eidos benchmark search

Searching for a past session in plain English

"use resume-resume to find the latest chats about eidos philosophy docs"

Claude Resume search example

Merging multiple past sessions into this chat

"use claude resume to merge march 14th conversations and Eidos v5 Pipeline Telemetry convo from march 11th into this chat"

Claude Resume merge example

Two sessions — one about eidos-philosophy doc changes (Mar 14) and one with a full 28-task strategic plan (Mar 11) — merged into the current conversation with a single command.

MCP Tools

Tool What it does
boot_up(hours) Crash recovery — finds sessions that didn't exit cleanly, scored by urgency
search_sessions(query) Full-text search across 5,000+ sessions in ~3s, ranked by RRF
recent_sessions(hours) List recently active sessions
read_session(id, keyword) Read actual messages from a session, with optional keyword filter
session_summary(id) AI summary — cached instantly, generated in ~15s if not
merge_context(id, mode) Import context from another session (summary, messages, or hybrid)
session_timeline(id) Structured milestone timeline — file edits, commits, instructions
session_thread(id) Follow continuation links across a multi-session thread
resume_in_terminal(id) Open a session in a new terminal window (iTerm2 or Terminal.app)
session_insights(section) Deep analytics across all sessions — patterns, personality, predictions
session_xray(id) Single-session breakdown — duration, tokens, tool counts, branches

TUI

For when your machine died and you just need to get back to work.

pip install resume-resume
resume-resume        # last 4 hours
cr 24                # last 24 hours
cr --all             # everything

resume-resume TUI

Key Action
Navigate sessions
r Resume directly — exec into the session
Enter Copy resume command to clipboard
Space Select for multi-resume (opens all in iTerm tabs)
x Export context briefing as markdown
/ Search across all session content
D Deep dive summary
p Analyze prompting patterns
b Toggle automated/bot sessions

Requires Python 3.11+ and Claude Code.


How It Works

  1. Scans ~/.claude/projects/ for JSONL session files
  2. Scores each by interruption severity — crashed mid-tool-use sessions first, lifecycle-aware for bookmarked ones
  3. Summarizes via claude -p with Haiku, cached permanently after first run
  4. Classifies sessions as human or automated using a gradient boosting model trained on 3,800 sessions — bot sessions hidden by default
  5. Surfaces bookmark data (lifecycle badges, next actions, blockers) when present

Run /bookmark inside any Claude Code session to capture lifecycle state (done, paused, blocked, handoff) before closing. An auto-bookmark Stop hook captures minimal state when you don't.


Related

  • claude-session-commons — Shared session parsing, caching, and classification used by this repo and others
  • claude-resume-duet — Web UI companion with session browser and resume-resume:// URL scheme handler

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

resume_resume-0.1.7.tar.gz (106.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

resume_resume-0.1.7-py3-none-any.whl (106.5 kB view details)

Uploaded Python 3

File details

Details for the file resume_resume-0.1.7.tar.gz.

File metadata

  • Download URL: resume_resume-0.1.7.tar.gz
  • Upload date:
  • Size: 106.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.7

File hashes

Hashes for resume_resume-0.1.7.tar.gz
Algorithm Hash digest
SHA256 d89d3901cdc00182b6da84e85159518cf5fe51a6fe4dfc589ad65150ddbd085c
MD5 59df29aa25e9795d1ba81991bcd99a61
BLAKE2b-256 eb6372ad6b50f4ed689a79f5579cdd9b5b8434e2fea9964586c1ba2bc7acfb09

See more details on using hashes here.

File details

Details for the file resume_resume-0.1.7-py3-none-any.whl.

File metadata

  • Download URL: resume_resume-0.1.7-py3-none-any.whl
  • Upload date:
  • Size: 106.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.7

File hashes

Hashes for resume_resume-0.1.7-py3-none-any.whl
Algorithm Hash digest
SHA256 23723efb766bbe8413a454bd7d3a456ff28581b6d68d18f56b1d48cb234ae883
MD5 55427cbda18f530a626896ea70f964fc
BLAKE2b-256 2028ebc48edd02db0afd527cbe81e160b4f85850d2798f6cd116cf49123bcc62

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page