claude-history

"This is the best thing ever thanks for this project." — @andrewle8

claude-history is a companion CLI for Claude Code. It lets you search recent conversations recorded in Claude's local project history with a built-in terminal UI, then view the selected transcript directly in the terminal with scrolling, search, and export capabilities.

Run it from the project directory you work on with Claude Code and it will discover the matching transcript folder automatically.

Install · Features · Usage · Configuration · Changelog

Features

• Fuzzy search across all conversations with field-aware relevance scoring, prefix matching, word boundary awareness, and tool output indexing
• Conversation viewer with vim-style scrolling, in-viewer search, message navigation, and markdown rendering
• Resume and fork conversations directly from the TUI with configurable keybindings
• Cross-project fork — fork a conversation from any project into your current working directory, useful when working across git worktrees
• Worktree-aware project filtering for workmux users
• Export and copy conversations or individual messages to clipboard
• Configurable display options, keybindings, and default resume arguments

Install

Quick install

curl -fsSL https://raw.githubusercontent.com/raine/claude-history/main/scripts/install.sh | bash

Homebrew (macOS/Linux)

brew install raine/claude-history/claude-history

Cargo

cargo install claude-history

Updating

claude-history update

Homebrew users should use brew upgrade claude-history instead.

Usage

Run the tool from inside the project directory you're interested in:

$ claude-history

This opens a terminal UI listing all conversations, sorted by recency. Type to search across all transcripts. Each item shows a preview of the conversation and match context is highlighted when your search matches content not visible in the preview.

Keyboard navigation (List mode)

Key	Action
↑ / ↓	Move selection
← / →	Move cursor in search
Ctrl+P / Ctrl+N	Move selection (vi-style)
Ctrl+D / Ctrl+U	Half page down/up (vim-style)
Page Up / Page Down	Jump by page
Home / End	Jump to first/last
Enter	Open conversation viewer
Ctrl+O	Select and exit (for scripting)
Ctrl+W	Delete word before cursor
Ctrl+R	Resume conversation
Ctrl+F	Fork and resume conversation
Ctrl+X	Delete conversation
Tab	Toggle all / workspace scope
?	Show keyboard shortcuts
Esc	Clear search input, or quit
Ctrl+C	Quit

Keyboard navigation (Viewer mode)

Key	Action
j / ↓	Scroll down
k / ↑	Scroll up
J / ]	Jump to next message
K / [	Jump to previous message
d / Ctrl+D	Half page down
u / Ctrl+U	Half page up
Page Down	Full page down
Page Up	Full page up
g / Home	Jump to top
G / End	Jump to bottom
/	Start search
n	Next search match
N	Previous search match
t	Cycle tools: off/truncated/full
T	Toggle thinking
e	Export conversation to file
y	Copy to clipboard (message if selected, else menu)
p	Show file path
Y	Copy file path to clipboard
I	Copy session ID to clipboard
Ctrl+R	Resume conversation
Ctrl+F	Fork and resume conversation
Ctrl+X	Delete conversation
?	Show keyboard shortcuts
q / Esc	Return to list (or quit in direct file input mode)
Ctrl+C	Quit

Message navigation

Press J/K or [/] to enter message navigation mode. A teal ▌ marker appears in the gutter showing which message is focused. While in this mode:

• J / ] — jump to next message
• K / [ — jump to previous message
• y — copy the focused message to clipboard (raw markdown)
• Esc — exit message navigation mode

Searching with / also activates message navigation, focusing the message containing each match as you move through results with n/N.

Search

Search uses fuzzy word matching with the following features:

• Case-insensitive: "config" matches "CONFIG"
• Underscore as separator: "api key" matches "API_KEY"
• Prefix matching: "auth" matches "authentication", "authorize"
• Word boundary: matches start at word boundaries, so "red" won't match inside "fired"
• Multi-word AND logic: all query words must match, each word is highlighted individually
• Tool output indexing: search matches content inside tool results (bash output, file contents, grep results, etc.), not just user/assistant text
• UUID lookup: paste a full session UUID (e.g. e7d318b1-4274-4ee2-a341-e94893b5df49) to jump directly to that session, even if it belongs to a different project

Results are ranked by relevance using field-aware scoring: matches in the title, project name, and summary are weighted higher than body text. Within equally relevant results, recent conversations rank first.

Direct file input

You can open a JSONL conversation file directly, bypassing the conversation selection UI:

$ claude-history /path/to/conversation.jsonl

All display options work in this mode:

$ claude-history --show-tools --show-thinking /path/to/conversation.jsonl

Press q or Esc to quit when viewing a file directly.

Conversation viewer

Press Enter on a conversation to open the built-in viewer. The viewer displays conversations in a ledger-style format with scrolling support.

Features:

• Scrolling: Navigate with vim-style keys (j/k) or arrow keys
• Search: Press / to search within the conversation, then n/N to navigate matches
• Cycle tools: Press t to cycle tool display (off → truncated → full)
• Toggle thinking: Press T to show/hide thinking blocks
• Show path: Press p to display the conversation file path
• Light/dark theme: Automatically detects terminal background color and applies an appropriate color theme

Press q or Esc to return to the conversation list.

View Claude conversation history

Usage: claude-history [OPTIONS] [FILE]
       claude-history [COMMAND]

Commands:
  update  Update claude-history to the latest version

Arguments:
  [FILE]  JSONL conversation file to view directly

Options:
  -t, --show-tools       Show tool calls in the conversation output
      --no-tools         Hide tool calls from the conversation output
  -d, --show-dir         Print the conversation directory path and exit
  -l, --last             Show the last messages in the TUI preview (default)
      --first            Show the first messages in the TUI preview
      --show-thinking    Show thinking blocks and subagent internals in the conversation output
      --hide-thinking    Hide thinking blocks and subagent internals from the conversation output
  -c, --resume           Resume the selected conversation in Claude Code
      --fork-session     Fork the session when resuming
  -p, --show-path        Print the selected conversation file path
  -i, --show-id          Print the selected conversation session ID
      --plain            Output plain text without ledger formatting
      --delete <SESSION_ID>  Delete a session by its UUID and exit
      --debug-search <QUERY>  Debug search result scoring for a query
      --debug [<LEVEL>]  Print debug information (optionally filter by level: debug, info, warn, error)
  -L, --local            Show only conversations from the current workspace directory
      --pager            Display output through a pager (less)
      --no-pager         Disable pager output
      --render <FILE>    Render a JSONL file in ledger format and exit
      --no-color         Disable colored output
  -h, --help             Print help
  -V, --version          Print version

Preview modes

• claude-history shows the last messages in the preview (default)
• claude-history --first flips the preview to the first messages

Showing tool calls

In the TUI viewer, tool calls default to truncated mode — showing the tool header plus the first few body lines with a "(N more lines...)" indicator. Press t to cycle through modes: off → truncated → full. Use --show-tools (or -t) to start in full mode, or --no-tools to start with tools hidden.

Showing thinking blocks and subagent messages

Extended thinking models (like Claude Sonnet 4.5) include reasoning steps in their output. When Claude uses the Task tool to spawn subagents, the internal tool calls and messages within those subagents are also hidden by default. Use --show-thinking (or press T in the TUI) to display both thinking blocks and subagent internals. Subagent messages appear dimmed with a ↳ prefix to distinguish them from top-level conversation entries.

Resuming conversations

If you want to continue a conversation, launch claude-history with --resume and it will hand off to claude --resume <conversation-id>.

To fork a conversation (creating a new session branching from the original), use --resume --fork-session or press Ctrl+F in the TUI.

Within the same project, this passes --fork-session to claude, which creates a new session ID branching from the original. When forking a conversation from a different project, the session files are copied to your CWD's project directory and resumed there — the copy continues independently without affecting the original.

You can configure default arguments to pass to the claude command every time you resume a conversation. This is useful if you typically run Claude with specific flags (like --dangerously-skip-permissions) and want them applied automatically when resuming:

# ~/.config/claude-history/config.toml
[resume]
default_args = ["--dangerously-skip-permissions"]

With this configuration, when you resume a conversation, it will run:

claude --resume <conversation-id> --dangerously-skip-permissions

This provides a cleaner alternative to shell aliases, as the arguments are applied specifically when resuming through claude-history, without affecting how you normally invoke Claude.

If you use a shell alias for claude with extra flags, you can use --show-id to select a session and resume it manually:

claude --resume $(claude-history --show-id)

In the viewer, press I to copy the session ID to clipboard.

Markdown rendering

Claude's responses are rendered with markdown formatting for better terminal readability. Use --plain to disable rendering and get raw text output.

Plain output mode

Use --plain to output conversations without ledger formatting:

$ claude-history --plain

This produces simple Role: content output without colors, text wrapping, or markdown rendering, suitable for piping to other tools or LLMs:

You: How do I fix this bug?

Claude: Looking at the code, the issue is...

Pager output

By default, conversation output is piped through a pager (less -R) when stdout is a terminal. This enables scrolling through long conversations. Use --no-pager to disable this behavior and print directly to stdout.

The pager respects the $PAGER environment variable. If not set, it defaults to less -R (which preserves ANSI colors).

Scope: all conversations vs current workspace

By default, claude-history shows all conversations from every project, sorted by modification time (newest first). Each conversation shows its project path so you can identify which project it belongs to.

Press Tab to toggle between all conversations and the current workspace only. Use -L/--local to start with the workspace filter active.

For workmux users, worktree paths are displayed in a compact format: [project/worktree] instead of just the worktree folder name. The project filter (toggled with Tab) is worktree-aware: it includes conversations from the main repo and all its worktrees, regardless of which one you're currently in.

The --resume flag works across projects. It will automatically run Claude in the correct project directory for the selected conversation.

Integration with other scripts

You can integrate claude-history into other tools to pass conversation context to new Claude Code sessions. This is useful when you want Claude to understand what you were working on previously.

For example, a commit message generator script could use the conversation history to write more contextual commit messages:

# Get conversation history if --context flag is set
conversation_context=""
if [ "$include_history" = true ]; then
    echo "Loading conversation history..."
    conversation_history=$(claude-history --plain 2>/dev/null)
    if [ -n "$conversation_history" ]; then
        conversation_context="

=== START CONVERSATION CONTEXT ===
$conversation_history
=== END CONVERSATION CONTEXT ===

"
    fi
fi

# Pass to Claude CLI with the conversation context
prompt="Write a commit message for these changes.
${conversation_context}
Staged changes:
$staged_diff"

claude -p "$prompt"

Configuration

You can set default preferences for display options in ~/.config/claude-history/config.toml. Command-line flags will override these settings.

Create the config file:

mkdir -p ~/.config/claude-history
cat > ~/.config/claude-history/config.toml << 'EOF'
[display]
# Tool display: true = hidden, false = full (default: unset = truncated)
# no_tools = false

# Show last messages in TUI preview (default: true)
# last = true

# Show thinking blocks (default: false)
show_thinking = false

# Use plain output without ledger formatting (default: false)
plain = false

# Use pager for output (default: true when stdout is a terminal)
pager = true

[resume]
# Default arguments to pass to claude command when resuming
# Example: default_args = ["--dangerously-skip-permissions"]

[keys]
# Customize keybindings (default: ctrl+r, ctrl+f, ctrl+x)
# Supports ctrl+<key> and alt+<key> combinations
# fork = "alt+f"

EOF

Available options

Display options

• no_tools (boolean): When true, hides tool calls; when false, shows them in full. When unset (default), tools display in truncated mode
• last (boolean): Show last messages instead of first in TUI preview (default: true)
• show_thinking (boolean): Show thinking blocks and subagent internals in conversation output (default: false)
• plain (boolean): Output plain text without ledger formatting (default: false)
• pager (boolean): Pipe output through a pager for scrolling (default: true when stdout is a terminal)

Resume options

• default_args (array of strings): Arguments to pass to the claude command when resuming conversations. Useful for flags like --dangerously-skip-permissions that you want applied every time you resume. Example: default_args = ["--dangerously-skip-permissions", "--verbose"]

Key bindings

Customize the keybindings for resume, fork, and delete actions. Values are key combinations like "ctrl+r" or "alt+f". Only single-character keys with ctrl+ or alt+ modifiers are supported.

• resume (string): Resume conversation (default: "ctrl+r")
• fork (string): Fork and resume conversation (default: "ctrl+f")
• delete (string): Delete conversation (default: "ctrl+x")

Overriding config

Each display option has opposing flags for explicit override:

• --no-tools / --show-tools
• --last / --first
• --hide-thinking / --show-thinking
• --plain (no opposite flag)
• --no-pager / --pager

For example, if your config has no_tools = false (showing tools), you can temporarily hide them with --no-tools.

Filtering details

The tool filters out some noisy artifacts before showing conversations, so you only see transcripts that are likely to matter for your recent work.

• Skips the "Warmup / I'm Claude Code…" exchanges that are sometimes injected without user interaction
• Skips conversations that only contain the /clear terminal command

Development

The repository includes just recipes:

$ just check

This runs cargo fmt, cargo clippy --fix, and cargo build in parallel.

Related projects

• workmux — Git worktrees + tmux windows for parallel AI agent workflows
• git-surgeon — Non-interactive hunk-level git staging for AI agents
• consult-llm-mcp — MCP server that lets Claude Code consult stronger AI models (o3, Gemini, GPT-5.1 Codex)
• tmux-file-picker — Pop up fzf in tmux to quickly insert file paths, perfect for AI coding assistants