diff --git a/CLAUDE.md b/CLAUDE.md
index 5b058a9..e4f77b3 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -4,11 +4,14 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 ## Project Overview
 
-Single-script Python tool that extracts credit card transactions from BAC Costa Rica statement PDFs. Parses sections B (purchases), D (other charges), and E (voluntary services) and outputs JSON.
+Python tools for BAC Costa Rica credit card statement processing:
+- `bac_extract.py`: Extracts transactions from statement PDFs to JSON
+- `bac_analyze.py`: Analyzes JSON output with categorization and graphs
 
 ## Dependencies
 
-- pdfplumber (>=0.10.0)
+- pdfplumber (>=0.10.0) - PDF extraction
+- matplotlib (>=3.5.0) - graphs (optional, only for bac_analyze.py --graph)
 
 ## Commands
 
@@ -16,22 +19,22 @@ Single-script Python tool that extracts credit card transactions from BAC Costa
 # Run tests
 python testStatements/run_tests.py
 
-# Run extractor
-python bac_extract.py <pdf_file> [options]
-
-# Examples
-python bac_extract.py EstadodeCuenta.pdf --pretty
+# Extract transactions from PDF
+python bac_extract.py statement.pdf --pretty
 python bac_extract.py statement.pdf -o output.json -v
-```
 
-Options:
-- `-o, --output`: Output JSON path (default: transactions.json)
-- `--pretty`: Pretty-print JSON
-- `-v, --verbose`: Enable debug logging
+# Analyze transactions (supports multiple JSON files)
+python bac_analyze.py transactions.json
+python bac_analyze.py *.json --graph all
+python bac_analyze.py *.json --graph bar -o spending.png
+python bac_analyze.py *.json --categories my_categories.json
+```
 
 ## Architecture
 
-The extraction pipeline:
+### bac_extract.py
+
+Extraction pipeline:
 1. Validates PDF is a BAC statement (`is_bac_statement`)
 2. Iterates pages line-by-line, detecting section boundaries via `SECTIONS` dict patterns
 3. Parses transactions matching `TRANSACTION_PATTERN` regex
@@ -41,7 +44,10 @@ Key data structures:
 - `SECTIONS`: Maps section IDs (B/D/E) to start/end regex patterns and output keys
 - `SPANISH_MONTHS`: Spanish month abbreviations for date parsing
 
-Key parsing functions:
-- `parse_spanish_date`: Converts "15-ENE-25" to "2025-01-15"
-- `parse_amount`: Handles "1,234.56" and trailing negatives "100.00-"
-- `matches_patterns`: Generic regex pattern matcher for section detection
+### bac_analyze.py
+
+Analysis pipeline:
+1. Loads transactions from one or more JSON files (purchases only)
+2. Categorizes by matching description against patterns in `categories.json`
+3. Aggregates by category and month, keeping CRC/USD separate
+4. Outputs text summary and optional graphs (bar/pie/timeline/all)
diff --git a/README.md b/README.md
index a56332a..709c00d 100644
--- a/README.md
+++ b/README.md
@@ -1,13 +1,16 @@
-# BAC Statement Extractor
+# BAC Statement Tools
 
-Extracts credit card transactions from BAC Costa Rica statement PDFs. Parses sections B (purchases), D (other charges), and E (voluntary services) and outputs JSON.
+Tools for processing BAC Costa Rica credit card statement PDFs.
 
 ## Dependencies
 
 - Python 3.10+
 - pdfplumber (>=0.10.0)
+- matplotlib (>=3.5.0) - optional, for graphs
 
-## Usage
+## Extraction
+
+Extract transactions from statement PDFs to JSON.
 
 ```bash
 python bac_extract.py <pdf_file> [options]
@@ -24,6 +27,56 @@ python bac_extract.py statement.pdf --pretty
 python bac_extract.py statement.pdf -o output.json -v
 ```
 
+## Analysis
+
+Analyze extracted transactions with category breakdowns and graphs.
+
+```bash
+python bac_analyze.py <json_files...> [options]
+```
+
+**Options:**
+- `--graph {bar,pie,timeline,all}`: Generate graph(s)
+- `-o, --output`: Output file for graph (default: spending_<type>.png)
+- `--show`: Display graph interactively
+- `--categories`: Custom categories file (default: categories.json)
+
+**Examples:**
+```bash
+# Text summary
+python bac_analyze.py transactions.json
+
+# Analyze multiple statements
+python bac_analyze.py *.json
+
+# Generate all graphs
+python bac_analyze.py *.json --graph all
+
+# Generate bar chart with custom output
+python bac_analyze.py *.json --graph bar -o spending.png
+
+# Use custom categories
+python bac_analyze.py *.json --categories my_categories.json
+```
+
+## Categories
+
+Create a `categories.json` file to customize spending categories. Each category maps to a list of merchant name patterns (case-insensitive substring match).
+
+```json
+{
+  "Groceries": ["SUPERMARKET", "WALMART", "FRESH MARKET"],
+  "Gas": ["SERVICENTRO", "DELTA", "SHELL"],
+  "Restaurants": ["RESTAURANT", "CAFE", "PIZZA", "SUSHI"],
+  "Transportation": ["UBER", "TAXI", "PARKING"],
+  "Entertainment": ["CINEMA", "NETFLIX", "STEAM"],
+  "Utilities": ["ELECTRIC", "WATER", "INTERNET"],
+  "Subscriptions": ["SPOTIFY", "YOUTUBE", "CHATGPT"]
+}
+```
+
+Transactions not matching any pattern are categorized as "Other".
+
 ## Output Format
 
 ```json