diff --git a/backend/README.md b/backend/README.md
index 9867cbeae..82cf21cc3 100644
--- a/backend/README.md
+++ b/backend/README.md
@@ -10,6 +10,8 @@ The backend is intended to be run as a daemon process. See the
 `4cat-daemon.py` script in the parent folder for instructions on how to start 
 and control the daemon.
 
+Also see the [architecture diagrams](architecture.md).
+
 ## What it does
 Queries a central job queue for outstanding jobs, and starts workers compatible
 with those jobs once any are available.
diff --git a/backend/architecture.md b/backend/architecture.md
new file mode 100644
index 000000000..b94800552
--- /dev/null
+++ b/backend/architecture.md
@@ -0,0 +1,272 @@
+# Architecture for 'backend'
+
+## classes
+
+:::mermaid
+classDiagram
+  class BasicHTTPScraper {
+    category : str
+    log_level : str
+    prefix
+    after_process()
+    get_url()*
+    not_found()
+    parse(data)
+    process(data)*
+    work()
+  }
+  class BasicJSONScraper {
+    parse(data)
+  }
+  class BasicProcessor {
+    category : str
+    config : NoneType
+    dataset : NoneType
+    db : NoneType
+    description : str
+    extension : str
+    filepath : NoneType
+    is_hidden : bool
+    is_running_in_preset : bool
+    job : NoneType
+    owner : NoneType
+    parameters
+    source_dataset : NoneType
+    source_file : NoneType
+    abort()
+    add_field_to_parent(field_name, new_data, which_parent, update_existing)
+    after_process()
+    create_standalone()
+    exclude_followup_processors(processor_type)
+    extract_archived_file_by_name(filename, archive_path, staging_area)
+    get_extension(parent_dataset)
+    get_mapped_item(item)
+    get_options(parent_dataset, user)
+    get_status()
+    is_4cat_processor()
+    is_filter()
+    is_from_collector()
+    is_rankable(multiple_items)
+    is_top_dataset()
+    iterate_archive_contents(path, staging_area, immediately_delete, filename_filter)
+    map_item_method_available(dataset)
+    process()*
+    remove_files()
+    unpack_archive_contents(path, staging_area)
+    work()
+    write_archive_and_finish(files, num_items, compression, finish)
+    write_csv_items_and_finish(data)
+  }
+  class BasicWorker {
+    INTERRUPT_CANCEL : int
+    INTERRUPT_NONE : bool
+    INTERRUPT_RETRY : int
+    config : NoneType
+    db : Database
+    init_time : int
+    interrupted : bool
+    job : NoneType
+    log : NoneType
+    manager : NoneType
+    max_workers : int
+    modules : NoneType
+    name : str
+    queue : NoneType
+    type : str
+    abort()*
+    clean_up()*
+    is_4cat_class()
+    is_4cat_processor()
+    request_interrupt(level)
+    run()
+    work()*
+  }
+  class DatasetCanceller {
+    max_workers : int
+    type : str
+    work()
+  }
+  class DatasourceMetrics {
+    ensure_job : dict
+    max_workers : int
+    type : str
+    data_stats()
+    folder_size(path)
+    general_stats()
+    work()
+  }
+  class FourcatRestarterAndUpgrader {
+    max_workers : int
+    type : str
+    work()
+  }
+  class InternalAPI {
+    ensure_job : dict
+    host : dict
+    max_workers : int
+    port : dict
+    type : str
+    api_response(client, address)
+    process_request(request, payload)
+    work()
+  }
+  class InternalAPIException {
+  }
+  class MySQLDatabase {
+    connection : Connection
+    cursor : NoneType
+    log : NoneType
+    close()
+    commit()
+    fetchall(query)
+    fetchone(query)
+    mogrify(query, replacements)
+    query(query, replacements)
+    rollback()
+  }
+  class ProcessorPreset {
+    after_process()
+    get_processor_pipeline()*
+    process()
+  }
+  class QueryCanceller {
+    max_workers : int
+    type : str
+    work()
+  }
+  class Search {
+    import_error_count : int
+    import_warning_count : int
+    max_workers : int
+    prefix : str
+    return_cols : list
+    type : str
+    get_items(query)*
+    import_from_file(path)
+    items_to_archive(items, filepath)
+    items_to_csv(results, filepath)
+    items_to_ndjson(items, filepath)
+    process()
+    search(query)
+  }
+  class SearchWithScope {
+    fetch_posts(post_ids, where, replacements)*
+    fetch_threads(thread_ids)*
+    get_items(query)*
+    get_items_complex(query)*
+    get_items_simple(query)*
+    get_search_mode(query)
+    get_thread_sizes(thread_ids, min_length)*
+    search(query)
+  }
+  class TempFileCleaner {
+    days_to_keep : int
+    ensure_job : dict
+    max_workers : int
+    tracking_file
+    type : str
+    work()
+  }
+  class ThingExpirer {
+    ensure_job : dict
+    max_workers : int
+    type : str
+    expire_datasets()
+    expire_notifications()
+    expire_users()
+    work()
+  }
+  class UpdateChecker {
+    ensure_job : dict
+    max_workers : int
+    type : str
+    work()
+  }
+  class WorkerManager {
+    db : NoneType
+    job_mapping : dict
+    log : NoneType
+    looping : bool
+    modules : NoneType
+    pool : list
+    queue : NoneType
+    worker_pool : dict
+    abort(signal, stack)
+    delegate()
+    loop()
+    request_interrupt(interrupt_level, job, remote_id, jobtype)
+    validate_datasources()
+  }
+  ProcessorPreset --|> BasicProcessor
+  BasicProcessor --|> BasicWorker
+  BasicHTTPScraper --|> BasicWorker
+  BasicJSONScraper --|> BasicHTTPScraper
+  Search --|> BasicProcessor
+  SearchWithScope --|> Search
+  InternalAPI --|> BasicWorker
+  DatasetCanceller --|> BasicWorker
+  QueryCanceller --|> BasicWorker
+  UpdateChecker --|> BasicWorker
+  TempFileCleaner --|> BasicWorker
+  DatasourceMetrics --|> BasicWorker
+  ThingExpirer --|> BasicWorker
+  FourcatRestarterAndUpgrader --|> BasicWorker
+:::
+
+## packages
+
+:::mermaid
+classDiagram
+  class backend {
+  }
+  class bootstrap {
+  }
+  class lib {
+  }
+  class database_mysql {
+  }
+  class manager {
+  }
+  class preset {
+  }
+  class processor {
+  }
+  class scraper {
+  }
+  class search {
+  }
+  class worker {
+  }
+  class workers {
+  }
+  class api {
+  }
+  class cancel_dataset {
+  }
+  class cancel_query {
+  }
+  class check_updates {
+  }
+  class cleanup_tempfiles {
+  }
+  class datasource_metrics {
+  }
+  class expire_items {
+  }
+  class restart_4cat {
+  }
+  bootstrap --> manager
+  preset --> processor
+  processor --> worker
+  scraper --> worker
+  search --> processor
+  api --> worker
+  cancel_dataset --> worker
+  cancel_query --> worker
+  check_updates --> worker
+  cleanup_tempfiles --> worker
+  datasource_metrics --> worker
+  expire_items --> worker
+  restart_4cat --> worker
+:::
+
diff --git a/common/README.md b/common/README.md
index b5e91f577..59eb4aedb 100644
--- a/common/README.md
+++ b/common/README.md
@@ -3,4 +3,6 @@
 This folder contains files used by both the back-end daemon and the front-end
 web app.
 
-Additionally, it contains assets (i.e. static files) used for analyses.
\ No newline at end of file
+Additionally, it contains assets (i.e. static files) used for analyses.
+
+Also see the [architecture diagrams](architecture.md).
diff --git a/common/architecture.md b/common/architecture.md
new file mode 100644
index 000000000..12d3f3896
--- /dev/null
+++ b/common/architecture.md
@@ -0,0 +1,454 @@
+# Architecture for 'common'
+
+## classes
+
+:::mermaid
+classDiagram
+  class ConfigDummy {
+  }
+  class ConfigException {
+  }
+  class ConfigManager {
+    cache : dict
+    config_definition : dict
+    core_settings : dict
+    db : NoneType
+    dbconn : NoneType
+    tag_context : list
+    delete_for_tag(attribute_name, tag)
+    ensure_database()
+    get(attribute_name, default, is_json, user, tags)
+    get_active_tags(user, tags)
+    get_all(is_json, user, tags)
+    load_core_settings()
+    load_user_settings()
+    set(attribute_name, value, is_json, tag, overwrite_existing)
+    with_db(db)
+  }
+  class ConfigWrapper {
+    config
+    request : NoneType
+    tags : NoneType
+    user : NoneType
+    get()
+    get_active_tags(user, tags)
+    get_all()
+    request_override(tags)
+    set()
+  }
+  class CsvDialectException {
+  }
+  class DataSet {
+    available_processors : NoneType
+    children : NoneType
+    data : NoneType
+    db : NoneType
+    folder : NoneType
+    genealogy : NoneType
+    is_new : bool
+    key : str
+    modules : NoneType
+    no_status_updates : bool
+    owners : NoneType
+    parameters : NoneType
+    preset_parent : NoneType
+    result_file
+    staging_areas : NoneType
+    tagged_owners : NoneType
+    add_owner(username, role)
+    change_datasource(datasource)
+    check_dataset_finished()
+    clear_log()
+    copy(shallow)
+    copy_ownership_from(dataset, recursive)
+    delete(commit, queue)
+    delete_parameter(parameter, instant)
+    detach()
+    finish(num_rows)
+    finish_with_error(error)
+    get_all_children(recursive)
+    get_annotation_fields()
+    get_annotations()
+    get_available_processors(user, exclude_hidden)
+    get_breadcrumbs()
+    get_columns()
+    get_compatible_processors(user)
+    get_extension()
+    get_genealogy(inclusive)
+    get_key(query, parameters, parent, time_offset)
+    get_label(parameters, default)
+    get_log_path()
+    get_media_type()
+    get_metadata()
+    get_modules()
+    get_own_processor()
+    get_owners(role)
+    get_owners_users(role)
+    get_parameters()
+    get_parent()
+    get_place_in_queue(update)
+    get_progress()
+    get_result_url()
+    get_results_folder_path()
+    get_results_path()
+    get_staging_area()
+    get_status()
+    get_version_url(file)
+    is_accessible_by(username, role)
+    is_dataset()
+    is_expired(user)
+    is_expiring(user)
+    is_finished()
+    is_from_collector()
+    is_rankable(multiple_items)
+    is_top_dataset()
+    iterate_items(processor, warn_unmappable, map_missing)
+    link_job(job)
+    link_parent(key_parent)
+    log(log)
+    nearest(type_filter)
+    refresh_owners()
+    remove_owner(username)
+    remove_staging_areas()
+    reserve_result_file(parameters, extension)
+    set_key(key)
+    top_parent()
+    update_children()
+    update_label(label)
+    update_progress(progress)
+    update_status(status, is_final)
+    update_version(version)
+    warn_unmappable_item(item_count, processor, error_message, warn_admins)
+  }
+  class DataSetException {
+  }
+  class DataSetNotFoundException {
+  }
+  class Database {
+    appname : str
+    connection
+    cursor : NoneType
+    interruptable_job : NoneType
+    interruptable_timeout : int
+    interrupted : bool
+    log : NoneType
+    close()
+    commit()
+    delete(table, where, commit)
+    execute(query, replacements)
+    execute_many(query, commit, replacements)
+    fetchall(query)
+    fetchall_interruptable(queue, query)
+    fetchone(query)
+    get_cursor()
+    insert(table, data, commit, safe, constraints, return_field)
+    query(query, replacements, cursor)
+    rollback()
+    update(table, data, where, commit)
+    upsert(table, data, commit, constraints)
+  }
+  class DatabaseQueryInterruptedException {
+  }
+  class DatasetItem {
+    mapped_object
+    missing_fields
+    original
+  }
+  class DmiServiceManager {
+    local_or_remote
+    num_files_to_process : NoneType
+    path_to_files : NoneType, Path
+    path_to_results : NoneType, Path
+    processed_files : int
+    processor
+    server_address
+    server_file_collection_name : NoneType
+    server_results_folder_name : NoneType
+    check_gpu_memory_available(service_endpoint)
+    check_progress()
+    check_service_exists()
+    count_local_files(directory)
+    download_results(filenames_to_download, folder_name, local_output_dir, timeout)
+    get_folder_name(dataset)
+    process_files(input_file_dir, filenames, output_file_dir, server_file_collection_name, server_results_folder_name)
+    process_results(local_output_dir)
+    request_folder_files(folder_name)
+    sanitize_filenames(filename)
+    send_files(file_collection_name, results_name, files_to_upload, dir_with_files)
+    send_request_and_wait_for_results(service_endpoint, data, wait_period, check_process, callback)
+  }
+  class DmiServiceManagerException {
+  }
+  class DsmConnectionError {
+  }
+  class DsmOutOfMemory {
+  }
+  class FourcatException {
+    frame : NoneType
+  }
+  class FourcatModule {
+  }
+  class HTMLStripper {
+    convert_charrefs : bool
+    fed : list
+    strict : bool
+    get_data()
+    handle_data(data)
+  }
+  class HashCache {
+    hash_cache : dict
+    hasher
+    update_cache(value)
+  }
+  class Job {
+    data : dict
+    db : NoneType
+    details
+    is_claimed : bool
+    is_finished : bool
+    claim()
+    finish(delete)
+    get_by_ID(database)
+    get_by_data(database)
+    get_by_remote_ID(database, jobtype)
+    get_place_in_queue()
+    is_claimable()
+    release(delay, claim_after)
+  }
+  class JobAlreadyExistsException {
+  }
+  class JobClaimedException {
+  }
+  class JobNotFoundException {
+  }
+  class JobQueue {
+    db : NoneType
+    log : NoneType
+    add_job(jobtype, details, remote_id, claim_after, interval)
+    get_all_jobs(jobtype, remote_id, restrict_claimable)
+    get_job(jobtype, timestamp, restrict_claimable)
+    get_job_count(jobtype)
+    get_place_in_queue(job)
+    release_all()
+  }
+  class Logger {
+    alert_level : str
+    db : NoneType
+    levels : dict
+    log_path : NoneType
+    logger : NoneType
+    previous_report : int
+    print_logs : bool
+    critical(message, frame)
+    debug(message, frame)
+    error(message, frame)
+    fatal(message, frame)
+    info(message, frame)
+    log(message, level, frame)
+    warning(message, frame)
+  }
+  class MapItemException {
+  }
+  class MappedItem {
+    data
+    message : str
+    missing
+    get_item_data(safe)
+    get_message()
+    get_missing_fields()
+  }
+  class MappedItemIncompleteException {
+  }
+  class MissingMappedField {
+    value
+  }
+  class ModuleCollector {
+    PROCESSOR : int
+    WORKER : int
+    datasources : dict
+    ignore : list
+    log_buffer : NoneType
+    missing_modules : dict
+    processors : dict
+    workers : dict
+    expand_datasources()
+    is_4cat_class(object, only_processors)
+    load_datasources()
+    load_modules()
+    load_worker_class(worker)
+  }
+  class NullAwareTextIOWrapper {
+  }
+  class ProcessorException {
+  }
+  class ProcessorInterruptedException {
+  }
+  class QueryException {
+  }
+  class QueryNeedsExplicitConfirmationException {
+  }
+  class QueryNeedsFurtherInputException {
+    config
+  }
+  class QueryParametersException {
+  }
+  class QueueException {
+  }
+  class RequirementsNotMetException {
+  }
+  class SlackLogHandler {
+    mapLogRecord(record)
+  }
+  class User {
+    config : NoneType
+    data : NoneType
+    db : NoneType
+    is_active : bool
+    is_admin
+    is_anonymous : bool
+    is_authenticated : bool
+    is_deactivated
+    is_special
+    name : str
+    userdata : NoneType
+    add_notification(notification, expires, allow_dismiss)
+    add_tag(tag)
+    authenticate()
+    can_access_dataset(dataset, role)
+    clear_token()
+    delete(also_datasets)
+    dismiss_notification(notification_id)
+    email_token(new)
+    generate_token(username, regenerate)
+    get_by_login(db, name, password, config)
+    get_by_name(db, name, config)
+    get_by_token(db, token, config)
+    get_id()
+    get_name()
+    get_notifications()
+    get_token()
+    get_value(key, default)
+    remove_tag(tag)
+    set_password(password)
+    set_value(key, value)
+    sort_user_tags()
+    with_config(config)
+  }
+  class UserInput {
+    OPTIONS_COSMETIC : tuple
+    OPTION_CHOICE : str
+    OPTION_DATASOURCES : str
+    OPTION_DATE : str
+    OPTION_DATERANGE : str
+    OPTION_DIVIDER : str
+    OPTION_FILE : str
+    OPTION_HUE : str
+    OPTION_INFO : str
+    OPTION_MULTI : str
+    OPTION_MULTI_SELECT : str
+    OPTION_TEXT : str
+    OPTION_TEXT_JSON : str
+    OPTION_TEXT_LARGE : str
+    OPTION_TOGGLE : str
+    parse_all(options, input, silently_correct)
+    parse_value(settings, choice, other_input, silently_correct)
+  }
+  class WebHookLogHandler {
+    server_name : str
+    emit(record)
+  }
+  class WorkerInterruptedException {
+  }
+  DataSet --|> FourcatModule
+  DsmConnectionError --|> DmiServiceManagerException
+  DsmOutOfMemory --|> DmiServiceManagerException
+  ConfigException --|> FourcatException
+  CsvDialectException --|> FourcatException
+  DataSetException --|> FourcatException
+  DataSetNotFoundException --|> DataSetException
+  DatabaseQueryInterruptedException --|> WorkerInterruptedException
+  JobAlreadyExistsException --|> QueueException
+  JobClaimedException --|> QueueException
+  JobNotFoundException --|> QueueException
+  MapItemException --|> ProcessorException
+  MappedItemIncompleteException --|> MapItemException
+  ProcessorException --|> FourcatException
+  ProcessorInterruptedException --|> WorkerInterruptedException
+  QueryException --|> FourcatException
+  QueryNeedsExplicitConfirmationException --|> QueryException
+  QueryNeedsFurtherInputException --|> QueryException
+  QueryParametersException --|> QueryException
+  QueueException --|> FourcatException
+  WorkerInterruptedException --|> FourcatException
+  SlackLogHandler --|> WebHookLogHandler
+  ConfigManager --* User : config
+  Database --* ConfigManager : db
+  ModuleCollector --* DataSet : modules
+:::
+
+## packages
+
+:::mermaid
+classDiagram
+  class common {
+  }
+  class config_manager {
+  }
+  class lib {
+  }
+  class config_definition {
+  }
+  class database {
+  }
+  class dataset {
+  }
+  class dmi_service_manager {
+  }
+  class exceptions {
+  }
+  class fourcat_module {
+  }
+  class helpers {
+  }
+  class item_mapping {
+  }
+  class job {
+  }
+  class logger {
+  }
+  class module_loader {
+  }
+  class queue {
+  }
+  class user {
+  }
+  class user_input {
+  }
+  config_manager --> config_definition
+  config_manager --> database
+  config_manager --> exceptions
+  config_manager --> user_input
+  config_definition --> user_input
+  database --> exceptions
+  dataset --> config_manager
+  dataset --> exceptions
+  dataset --> fourcat_module
+  dataset --> helpers
+  dataset --> item_mapping
+  dataset --> job
+  dataset --> module_loader
+  dmi_service_manager --> helpers
+  helpers --> config_manager
+  helpers --> user_input
+  job --> exceptions
+  logger --> config_manager
+  module_loader --> config_manager
+  queue --> job
+  user --> config_manager
+  user --> dataset
+  user --> exceptions
+  user --> helpers
+  user_input --> exceptions
+  user_input --> helpers
+:::
+
diff --git a/helper-scripts/generate-diagrams.sh b/helper-scripts/generate-diagrams.sh
new file mode 100644
index 000000000..c5ba1938f
--- /dev/null
+++ b/helper-scripts/generate-diagrams.sh
@@ -0,0 +1,44 @@
+#!/usr/bin/env sh
+
+####################################################################################################
+# This script uses pyreverse (from the pylint package) to automatically generate architecture
+# diagrams for each package in the project.
+####################################################################################################
+
+if ! command -v pyreverse &> /dev/null
+then
+    echo "pyreverse could not be found. Please install pylint."
+    exit 1
+fi
+
+OUTPUT_FORMAT="mmd"
+PYREVERSE_OPTIONS="--colorized -o $OUTPUT_FORMAT"
+
+SEARCH_DEPTH=2  # Search for Python packages up to this depth
+
+for PACKAGE_INIT in $(find . -d $SEARCH_DEPTH -name __init__.py)
+do
+    PACKAGE_NAME=$(echo $PACKAGE_INIT | cut -f 2 -d /)
+    echo "Generating class diagram for package '$PACKAGE_NAME'..."
+    pyreverse $PYREVERSE_OPTIONS -p $PACKAGE_NAME $PACKAGE_NAME
+
+    OUTPUT_FILE="$PACKAGE_NAME/architecture.md"
+    echo "Writing to file '$OUTPUT_FILE'..."
+    echo "# Architecture for '$PACKAGE_NAME'" > $OUTPUT_FILE
+    echo "" >> $OUTPUT_FILE
+
+    for PREFIX in "classes" "packages"
+    do
+        echo "## $PREFIX" >> $OUTPUT_FILE
+        echo "" >> $OUTPUT_FILE
+        echo ":::mermaid" >> $OUTPUT_FILE
+        
+        MERMAID_FILE=${PREFIX}_${PACKAGE_NAME}.${OUTPUT_FORMAT}
+        cat $MERMAID_FILE >> $OUTPUT_FILE
+        rm $MERMAID_FILE
+        
+        echo ":::" >> $OUTPUT_FILE
+        echo "" >> $OUTPUT_FILE
+
+    done
+done
diff --git a/setup.py b/setup.py
index 4f40eb5e4..9144b07e5 100644
--- a/setup.py
+++ b/setup.py
@@ -40,6 +40,7 @@
 	"packaging",
 	"pandas==1.5.3",
 	"Pillow>=10.3",
+	"pylint~=2.17",	# pin PyLint version 2 for 4Cat and pyreverse
 	"praw~=7.0",
 	"prawcore~=2.0",
 	"psutil~=5.0",
diff --git a/webtool/architecture.md b/webtool/architecture.md
new file mode 100644
index 000000000..2971ea2fa
--- /dev/null
+++ b/webtool/architecture.md
@@ -0,0 +1,89 @@
+# Architecture for 'webtool'
+
+## classes
+
+:::mermaid
+classDiagram
+  class OpenAPICollector {
+    apis : set
+    endpoints : dict
+    flask_app : NoneType
+    type_map : dict
+    endpoint(api_id)
+    generate(api_id)
+    schema_to_schema(schema)
+  }
+  class Pagination {
+    has_next
+    has_prev
+    page
+    pages
+    per_page
+    route : str
+    route_args : dict
+    total_count
+    iter_pages(left_edge, left_current, right_current, right_edge)
+  }
+:::
+
+## packages
+
+:::mermaid
+classDiagram
+  class webtool {
+  }
+  class lib {
+  }
+  class helpers {
+  }
+  class openapi_collector {
+  }
+  class template_filters {
+  }
+  class views {
+  }
+  class api_explorer {
+  }
+  class api_standalone {
+  }
+  class api_tool {
+  }
+  class views_admin {
+  }
+  class views_dataset {
+  }
+  class views_extensions {
+  }
+  class views_misc {
+  }
+  class views_restart {
+  }
+  class views_user {
+  }
+  webtool --> helpers
+  webtool --> openapi_collector
+  webtool --> views_admin
+  template_filters --> webtool
+  template_filters --> helpers
+  api_explorer --> webtool
+  api_explorer --> helpers
+  api_standalone --> webtool
+  api_standalone --> helpers
+  api_tool --> webtool
+  api_tool --> helpers
+  views_admin --> webtool
+  views_admin --> helpers
+  views_dataset --> webtool
+  views_dataset --> helpers
+  views_dataset --> api_tool
+  views_extensions --> webtool
+  views_misc --> webtool
+  views_misc --> helpers
+  views_misc --> views_dataset
+  views_restart --> webtool
+  views_restart --> helpers
+  views_user --> webtool
+  views_user --> helpers
+  views_user --> api_tool
+:::
+