diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index ccff9d2d3..7513579ff 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -26,6 +26,7 @@ exclude: |
     | gget/constants/
     | tests/fixtures/
     | tests/pytest_results.*\.txt
+    | \.github/badges/.*\.json
   )
 repos:
   - repo: https://github.com/biomejs/pre-commit
diff --git a/gget/gget_8cube.py b/gget/gget_8cube.py
index 16481e7cf..4e76c4dde 100644
--- a/gget/gget_8cube.py
+++ b/gget/gget_8cube.py
@@ -2,7 +2,7 @@
 
 import io
 import json as json_package
-from typing import Any
+from typing import Any, Literal, overload
 
 import pandas as pd
 import requests
@@ -54,12 +54,30 @@ def _normalize_gene_list(gene_list: list[str] | tuple[str, ...]) -> list[str]:
 # --------------------------------------------------------------------
 # 1. SPECIFICITY
 # --------------------------------------------------------------------
+@overload
+def specificity(
+    gene_list: list[str] | tuple[str, ...],
+    json: Literal[False] = False,
+    save: bool = False,
+    verbose: bool = True,
+) -> pd.DataFrame: ...
+
+
+@overload
+def specificity(
+    gene_list: list[str] | tuple[str, ...],
+    json: Literal[True],
+    save: bool = False,
+    verbose: bool = True,
+) -> list[dict[str, Any]]: ...
+
+
 def specificity(
     gene_list: list[str] | tuple[str, ...],
     json: bool = False,
     save: bool = False,
     verbose: bool = True,
-) -> Any:
+) -> pd.DataFrame | list[dict[str, Any]]:
     """Retrieve gene-level specificity statistics from the 8cubeDB.
 
     (https://eightcubedb.onrender.com/).
@@ -126,6 +144,28 @@ def specificity(
 # --------------------------------------------------------------------
 # 2. PSI BLOCK
 # --------------------------------------------------------------------
+@overload
+def psi_block(
+    gene_list: list[str] | tuple[str, ...],
+    analysis_level: str,
+    analysis_type: str,
+    json: Literal[False] = False,
+    save: bool = False,
+    verbose: bool = True,
+) -> pd.DataFrame: ...
+
+
+@overload
+def psi_block(
+    gene_list: list[str] | tuple[str, ...],
+    analysis_level: str,
+    analysis_type: str,
+    json: Literal[True],
+    save: bool = False,
+    verbose: bool = True,
+) -> list[dict[str, Any]]: ...
+
+
 def psi_block(
     gene_list: list[str] | tuple[str, ...],
     analysis_level: str,
@@ -133,7 +173,7 @@ def psi_block(
     json: bool = False,
     save: bool = False,
     verbose: bool = True,
-) -> Any:
+) -> pd.DataFrame | list[dict[str, Any]]:
     """Retrieve ψ_block (psi-block) specificity scores from the 8cubeDB.
 
     ψ_block quantifies the specificity of a gene to a particular block
@@ -194,6 +234,28 @@ def psi_block(
 # --------------------------------------------------------------------
 # 3. GENE EXPRESSION
 # --------------------------------------------------------------------
+@overload
+def gene_expression(
+    gene_list: list[str] | tuple[str, ...],
+    analysis_level: str,
+    analysis_type: str,
+    json: Literal[False] = False,
+    save: bool = False,
+    verbose: bool = True,
+) -> pd.DataFrame: ...
+
+
+@overload
+def gene_expression(
+    gene_list: list[str] | tuple[str, ...],
+    analysis_level: str,
+    analysis_type: str,
+    json: Literal[True],
+    save: bool = False,
+    verbose: bool = True,
+) -> list[dict[str, Any]]: ...
+
+
 def gene_expression(
     gene_list: list[str] | tuple[str, ...],
     analysis_level: str,
@@ -201,7 +263,7 @@ def gene_expression(
     json: bool = False,
     save: bool = False,
     verbose: bool = True,
-) -> Any:
+) -> pd.DataFrame | list[dict[str, Any]]:
     """Retrieve normalized gene expression values from 8cubeDB.
 
     This endpoint returns mean and variance of normalized expression for the
diff --git a/gget/gget_archs4.py b/gget/gget_archs4.py
index 36a46d4e0..e582dfaf5 100644
--- a/gget/gget_archs4.py
+++ b/gget/gget_archs4.py
@@ -2,7 +2,7 @@
 
 import io
 import json as json_package
-from typing import Any
+from typing import Any, Literal, overload
 
 import pandas as pd
 import requests
@@ -17,6 +17,32 @@
 from .gget_info import info  # noqa: E402
 
 
+@overload
+def archs4(
+    gene: str,
+    ensembl: bool = False,
+    which: str = "correlation",
+    gene_count: int = 100,
+    species: str = "human",
+    json: Literal[True] = ...,
+    save: bool = False,
+    verbose: bool = True,
+) -> list[dict[str, Any]] | None: ...
+
+
+@overload
+def archs4(
+    gene: str,
+    ensembl: bool = False,
+    which: str = "correlation",
+    gene_count: int = 100,
+    species: str = "human",
+    json: Literal[False] = False,
+    save: bool = False,
+    verbose: bool = True,
+) -> pd.DataFrame | None: ...
+
+
 def archs4(
     gene: str,
     ensembl: bool = False,
diff --git a/gget/gget_bgee.py b/gget/gget_bgee.py
index 0fe5ac3ef..d35e629b5 100644
--- a/gget/gget_bgee.py
+++ b/gget/gget_bgee.py
@@ -2,7 +2,7 @@
 
 import json as json_
 from importlib.metadata import PackageNotFoundError, version
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING, Any, Literal, overload
 
 from .utils import dig, http_json, json_list_to_df, set_up_logger
 
@@ -180,13 +180,41 @@ def _bgee_expression(gene_id: str | list[str], json: bool = False, verbose: bool
         return df
 
 
+@overload
+def bgee(
+    gene_id: str | list[str],
+    type: str,
+    json: Literal[True],
+    verbose: bool = ...,
+) -> list[dict[str, Any]]: ...
+
+
+@overload
+def bgee(
+    gene_id: str | list[str],
+    type: str = ...,
+    *,
+    json: Literal[True],
+    verbose: bool = ...,
+) -> list[dict[str, Any]]: ...
+
+
+@overload
+def bgee(
+    gene_id: str | list[str],
+    type: str = ...,
+    json: Literal[False] = False,
+    verbose: bool = ...,
+) -> pd.DataFrame: ...
+
+
 # noinspection PyShadowingBuiltins
 def bgee(
     gene_id: str | list[str],
     type: str = "orthologs",
     json: bool = False,
     verbose: bool = True,
-) -> pd.DataFrame | Any:
+) -> pd.DataFrame | list[dict[str, Any]]:
     """Get orthologs/expression data for a gene from Bgee (https://www.bgee.org/).
 
     Args:
diff --git a/gget/gget_blast.py b/gget/gget_blast.py
index bb0f5b48c..c072820d3 100644
--- a/gget/gget_blast.py
+++ b/gget/gget_blast.py
@@ -3,7 +3,7 @@
 import json as json_package
 import time
 from io import StringIO
-from typing import Any
+from typing import Any, Literal, overload
 from urllib.parse import urlencode
 
 # Using urllib instead of requests here because requests does not
@@ -25,6 +25,39 @@
 )
 
 
+@overload
+def blast(
+    sequence: str,
+    program: str = "default",
+    database: str = "default",
+    limit: int = 50,
+    expect: float = 10.0,
+    low_comp_filt: bool = False,
+    megablast: bool = True,
+    verbose: bool = True,
+    wrap_text: bool = False,
+    *,
+    json: Literal[True],
+    save: bool = False,
+) -> list[dict[str, Any]] | None: ...
+
+
+@overload
+def blast(
+    sequence: str,
+    program: str = "default",
+    database: str = "default",
+    limit: int = 50,
+    expect: float = 10.0,
+    low_comp_filt: bool = False,
+    megablast: bool = True,
+    verbose: bool = True,
+    wrap_text: bool = False,
+    json: Literal[False] = False,
+    save: bool = False,
+) -> pd.DataFrame | None: ...
+
+
 def blast(
     sequence: str,
     program: str = "default",
diff --git a/gget/gget_blat.py b/gget/gget_blat.py
index d1f88509f..0939eb0a0 100644
--- a/gget/gget_blat.py
+++ b/gget/gget_blat.py
@@ -3,7 +3,7 @@
 import json as json_package
 import time
 from json.decoder import JSONDecodeError
-from typing import Any
+from typing import Any, Literal, overload
 from urllib import request
 from urllib.error import HTTPError, URLError
 
@@ -18,6 +18,28 @@
 _BLAT_BACKOFF_BASE_SECONDS = 1.5
 
 
+@overload
+def blat(
+    sequence: str,
+    seqtype: str = ...,
+    assembly: str = ...,
+    json: Literal[True] = ...,
+    save: bool = ...,
+    verbose: bool = ...,
+) -> list[dict[str, Any]] | None: ...
+
+
+@overload
+def blat(
+    sequence: str,
+    seqtype: str = ...,
+    assembly: str = ...,
+    json: Literal[False] = ...,
+    save: bool = ...,
+    verbose: bool = ...,
+) -> pd.DataFrame | None: ...
+
+
 def blat(
     sequence: str,
     seqtype: str = "default",
@@ -133,7 +155,7 @@ def blat(
 
     ## Build data frame to resemble BLAT web search results
     # Define dataframe from dictionary
-    df_dict = {}
+    df_dict: dict[str, list[Any]] = {}
 
     for field in results["fields"]:
         df_dict.update({field: []})
diff --git a/gget/gget_cosmic.py b/gget/gget_cosmic.py
index 020fdad58..594e9bf8e 100644
--- a/gget/gget_cosmic.py
+++ b/gget/gget_cosmic.py
@@ -9,7 +9,7 @@
 import shutil
 import subprocess
 import tarfile
-from typing import Any
+from typing import Any, Literal, overload
 
 import pandas as pd
 
@@ -315,6 +315,53 @@ def match_and_limit(mask, extract_fn):
     return results
 
 
+@overload
+def cosmic(
+    searchterm: str | None,
+    cosmic_tsv_path: str | None = None,
+    limit: int = 100,
+    *,
+    json: Literal[True],
+    download_cosmic: bool = False,
+    cosmic_project: str | None = None,
+    cosmic_version: int | None = None,
+    grch_version: int = 37,
+    email: str | None = None,
+    password: str | None = None,
+    gget_mutate: bool = False,
+    keep_genome_info: bool = False,
+    remove_duplicates: bool = False,
+    seq_id_column: str = "seq_ID",
+    mutation_column: str = "mutation",
+    mut_id_column: str = "mutation_id",
+    out: str | None = None,
+    verbose: bool = True,
+) -> list[dict[str, Any]] | None: ...
+
+
+@overload
+def cosmic(
+    searchterm: str | None,
+    cosmic_tsv_path: str | None = None,
+    limit: int = 100,
+    json: Literal[False] = False,
+    download_cosmic: bool = False,
+    cosmic_project: str | None = None,
+    cosmic_version: int | None = None,
+    grch_version: int = 37,
+    email: str | None = None,
+    password: str | None = None,
+    gget_mutate: bool = False,
+    keep_genome_info: bool = False,
+    remove_duplicates: bool = False,
+    seq_id_column: str = "seq_ID",
+    mutation_column: str = "mutation",
+    mut_id_column: str = "mutation_id",
+    out: str | None = None,
+    verbose: bool = True,
+) -> pd.DataFrame | None: ...
+
+
 def cosmic(
     searchterm: str | None,
     cosmic_tsv_path: str | None = None,
@@ -334,7 +381,7 @@ def cosmic(
     mut_id_column: str = "mutation_id",
     out: str | None = None,
     verbose: bool = True,
-) -> Any:
+) -> pd.DataFrame | list[dict[str, Any]] | None:
     """Search for genes, mutations, etc associated with cancers using the COSMIC database.
 
     (Catalogue Of Somatic Mutations In Cancer) database
diff --git a/gget/gget_diamond.py b/gget/gget_diamond.py
index f68bef39f..455b2bf7d 100644
--- a/gget/gget_diamond.py
+++ b/gget/gget_diamond.py
@@ -6,7 +6,9 @@
 import subprocess
 import sys
 import uuid
-from typing import Any
+from typing import Any, Literal, overload
+
+import pandas as pd
 
 from .compile import PACKAGE_PATH
 from .utils import (
@@ -26,6 +28,37 @@
     PRECOMPILED_DIAMOND_PATH = os.path.join(PACKAGE_PATH, f"bins/{platform.system()}/diamond")
 
 
+@overload
+def diamond(
+    query: str | list[str],
+    reference: str | list[str],
+    translated: bool = ...,
+    diamond_db: str | None = ...,
+    sensitivity: str = ...,
+    threads: int = ...,
+    diamond_binary: str | None = ...,
+    verbose: bool = ...,
+    *,
+    json: Literal[True],
+    out: str | None = ...,
+) -> list[dict[str, Any]]: ...
+
+
+@overload
+def diamond(
+    query: str | list[str],
+    reference: str | list[str],
+    translated: bool = ...,
+    diamond_db: str | None = ...,
+    sensitivity: str = ...,
+    threads: int = ...,
+    diamond_binary: str | None = ...,
+    verbose: bool = ...,
+    json: Literal[False] = False,
+    out: str | None = ...,
+) -> pd.DataFrame: ...
+
+
 def diamond(
     query: str | list[str],
     reference: str | list[str],
@@ -37,7 +70,7 @@ def diamond(
     verbose: bool = True,
     json: bool = False,
     out: str | None = None,
-) -> Any:
+) -> pd.DataFrame | list[dict[str, Any]]:
     """Align multiple protein or translated DNA sequences using DIAMOND (https://www.nature.com/articles/nmeth.3176).
 
     Args:
diff --git a/gget/gget_elm.py b/gget/gget_elm.py
index f53e6f59e..f45680ae9 100644
--- a/gget/gget_elm.py
+++ b/gget/gget_elm.py
@@ -3,7 +3,7 @@
 import json as json_package
 import os
 import re
-from typing import Any
+from typing import Any, Literal, overload
 
 import numpy as np
 import pandas as pd
@@ -223,6 +223,34 @@ def regex_match(sequence: str) -> pd.DataFrame:
     return df_final
 
 
+@overload
+def elm(
+    sequence: str,
+    uniprot: bool = ...,
+    sensitivity: str = ...,
+    threads: int = ...,
+    diamond_binary: str | None = ...,
+    expand: bool = ...,
+    verbose: bool = ...,
+    json: Literal[True] = ...,
+    out: str | None = ...,
+) -> tuple[list[dict[str, Any]], list[dict[str, Any]]]: ...
+
+
+@overload
+def elm(
+    sequence: str,
+    uniprot: bool = ...,
+    sensitivity: str = ...,
+    threads: int = ...,
+    diamond_binary: str | None = ...,
+    expand: bool = ...,
+    verbose: bool = ...,
+    json: Literal[False] = ...,
+    out: str | None = ...,
+) -> tuple[pd.DataFrame, pd.DataFrame]: ...
+
+
 def elm(
     sequence: str,
     uniprot: bool = False,
@@ -233,7 +261,7 @@ def elm(
     verbose: bool = True,
     json: bool = False,
     out: str | None = None,
-) -> tuple[Any, Any]:
+) -> tuple[pd.DataFrame, pd.DataFrame] | tuple[list[dict[str, Any]], list[dict[str, Any]]]:
     """Locally predicts Eukaryotic Linear Motifs from an amino acid sequence or UniProt Acc using
 
     data from the ELM database (http://elm.eu.org/).
diff --git a/gget/gget_enrichr.py b/gget/gget_enrichr.py
index 769316d6c..deb2c75b7 100644
--- a/gget/gget_enrichr.py
+++ b/gget/gget_enrichr.py
@@ -2,7 +2,7 @@
 
 import json as json_package
 import textwrap
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING, Any, Literal, overload
 
 # Plotting packages
 import matplotlib.pyplot as plt
@@ -64,6 +64,46 @@ def clean_genes_list(genes_list: list[Any]) -> list[Any]:
     return genes_clean
 
 
+@overload
+def enrichr(
+    genes: str | list[str],
+    database: str,
+    species: str = "human",
+    background_list: list[str] | None = None,
+    background: bool = False,
+    ensembl: bool = False,
+    ensembl_bkg: bool = False,
+    plot: bool = False,
+    figsize: tuple[float, float] = (10, 10),
+    ax: Axes | None = None,
+    kegg_out: str | None = None,
+    kegg_rank: int = 1,
+    json: Literal[True] = ...,
+    save: bool = False,
+    verbose: bool = True,
+) -> list[dict[str, Any]] | None: ...
+
+
+@overload
+def enrichr(
+    genes: str | list[str],
+    database: str,
+    species: str = "human",
+    background_list: list[str] | None = None,
+    background: bool = False,
+    ensembl: bool = False,
+    ensembl_bkg: bool = False,
+    plot: bool = False,
+    figsize: tuple[float, float] = (10, 10),
+    ax: Axes | None = None,
+    kegg_out: str | None = None,
+    kegg_rank: int = 1,
+    json: Literal[False] = False,
+    save: bool = False,
+    verbose: bool = True,
+) -> pd.DataFrame | None: ...
+
+
 def enrichr(
     genes: str | list[str],
     database: str,
diff --git a/gget/gget_info.py b/gget/gget_info.py
index c38bd794f..a4005f612 100644
--- a/gget/gget_info.py
+++ b/gget/gget_info.py
@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import json as json_package
-from typing import Any
+from typing import Any, Literal, overload
 
 import numpy as np
 import pandas as pd
@@ -29,6 +29,37 @@
 
 
 ## gget info
+@overload
+def info(
+    ens_ids: str | list[str],
+    wrap_text: bool = ...,
+    ncbi: bool = ...,
+    uniprot: bool = ...,
+    pdb: bool = ...,
+    *,
+    json: Literal[True],
+    verbose: bool = ...,
+    save: bool = ...,
+    expand: bool = ...,
+    ensembl_only: bool = ...,
+) -> dict[str, Any] | None: ...
+
+
+@overload
+def info(
+    ens_ids: str | list[str],
+    wrap_text: bool = ...,
+    ncbi: bool = ...,
+    uniprot: bool = ...,
+    pdb: bool = ...,
+    json: Literal[False] = ...,
+    verbose: bool = ...,
+    save: bool = ...,
+    expand: bool = ...,
+    ensembl_only: bool = ...,
+) -> pd.DataFrame | None: ...
+
+
 def info(
     ens_ids: str | list[str],
     wrap_text: bool = False,
@@ -393,7 +424,7 @@ def info(
 
     ens_ids = []
     # Dictionary to save clean info
-    data = {
+    data: dict[str, list[Any]] = {
         "all_transcripts": [],
         "transcript_biotypes": [],
         "transcript_names": [],
diff --git a/gget/gget_muscle.py b/gget/gget_muscle.py
index 69d0dcd82..a5053954d 100644
--- a/gget/gget_muscle.py
+++ b/gget/gget_muscle.py
@@ -122,7 +122,7 @@ def muscle(fasta: str | list[str], super5: bool = False, out: str | None = None,
         # Get the titles and sequences from the generated .afa file
         titles = []
         seqs_master = []
-        seqs = []
+        seqs: list[str] = []
         with open(abs_out_path) as aln_file:
             for i, line in enumerate(aln_file):
                 # Recognize title lines by the '>' character
diff --git a/gget/gget_opentargets.py b/gget/gget_opentargets.py
index edd90bc3f..8037fb342 100644
--- a/gget/gget_opentargets.py
+++ b/gget/gget_opentargets.py
@@ -2,7 +2,7 @@
 
 import json as json_
 import textwrap
-from typing import Any
+from typing import Any, Literal, overload
 
 import pandas as pd
 
@@ -255,6 +255,30 @@ def _unhash(x: Any) -> Any:
     return x
 
 
+@overload
+def opentargets(
+    ensembl_id: str,
+    resource: str = "diseases",
+    limit: int | None = None,
+    verbose: bool = True,
+    wrap_text: bool = False,
+    filters: dict[str, Any] | None = None,
+    json: Literal[False] = False,
+) -> pd.DataFrame: ...
+
+
+@overload
+def opentargets(
+    ensembl_id: str,
+    resource: str = "diseases",
+    limit: int | None = None,
+    verbose: bool = True,
+    wrap_text: bool = False,
+    filters: dict[str, Any] | None = None,
+    json: Literal[True] = ...,
+) -> list[dict[str, Any]]: ...
+
+
 def opentargets(
     ensembl_id: str,
     resource: str = "diseases",
@@ -263,7 +287,7 @@ def opentargets(
     wrap_text: bool = False,
     filters: dict[str, Any] | None = None,
     json: bool = False,
-) -> Any:
+) -> pd.DataFrame | list[dict[str, Any]]:
     """Query OpenTargets for data associated with a given Ensembl gene ID.
 
     Args:
diff --git a/gget/gget_ref.py b/gget/gget_ref.py
index f81b7fc4a..b16391c41 100644
--- a/gget/gget_ref.py
+++ b/gget/gget_ref.py
@@ -359,7 +359,7 @@ def ref(
     ## Return results
     # If FTP=False, return dictionary/json of specified results
     if ftp is False:
-        ref_dict = {species: {}}
+        ref_dict: dict[str, dict[str, Any]] = {species: {}}
         for return_val in which:
             if return_val == "all":
                 ref_dict = {
diff --git a/gget/gget_search.py b/gget/gget_search.py
index a5ed75529..e8df84c85 100644
--- a/gget/gget_search.py
+++ b/gget/gget_search.py
@@ -3,7 +3,7 @@
 import json as json_package
 import time
 import warnings
-from typing import Any
+from typing import Any, Literal, overload
 
 import mysql.connector as sql
 import numpy as np
@@ -37,6 +37,38 @@ def clean_cols(x: Any) -> Any:
         return x
 
 
+@overload
+def search(
+    searchwords: str | list[str],
+    species: str,
+    release: int | None = None,
+    id_type: str = "gene",
+    seqtype: str | None = None,
+    andor: str = "or",
+    limit: int | None = None,
+    wrap_text: bool = False,
+    json: Literal[True] = ...,
+    save: bool = False,
+    verbose: bool = True,
+) -> list[dict[str, Any]] | None: ...
+
+
+@overload
+def search(
+    searchwords: str | list[str],
+    species: str,
+    release: int | None = None,
+    id_type: str = "gene",
+    seqtype: str | None = None,
+    andor: str = "or",
+    limit: int | None = None,
+    wrap_text: bool = False,
+    json: Literal[False] = False,
+    save: bool = False,
+    verbose: bool = True,
+) -> pd.DataFrame | None: ...
+
+
 def search(
     searchwords: str | list[str],
     species: str,
@@ -49,7 +81,7 @@ def search(
     json: bool = False,
     save: bool = False,
     verbose: bool = True,
-) -> Any:
+) -> pd.DataFrame | list[dict[str, Any]] | None:
     """Function to query Ensembl for genes based on species and free form search terms.
 
     Automatically fetches results from latest Ensembl release, unless user specifies database (see 'species' argument)
diff --git a/gget/gget_virus.py b/gget/gget_virus.py
index 8a04dfdec..7742e6a91 100644
--- a/gget/gget_virus.py
+++ b/gget/gget_virus.py
@@ -1453,7 +1453,7 @@ def fetch_virus_metadata(
         # e.g., "NC_045512.2%2CMN908947.3%2CMT020781.1"
         url = f"{NCBI_API_BASE}/virus/accession/{virus}/dataset_report"
         logger.debug("Using accession endpoint for virus: %s", virus)
-        params = {}
+        params: dict[str, Any] = {}
     else:
         # For taxon names/IDs (e.g., 'Zika Virus', 'influenza'), use the taxon endpoint
         url = f"{NCBI_API_BASE}/virus/taxon/{virus}/dataset_report"
@@ -4381,7 +4381,7 @@ def _load_metadata_dict_from_temp_jsonl(temp_file_path: str) -> dict[str, Any]:
               Same format as load_metadata_from_api_reports().
 
     """
-    metadata_dict = {}
+    metadata_dict: dict[str, Any] = {}
     processed_count = 0
     skipped_count = 0
 
@@ -4471,7 +4471,7 @@ def _load_cached_metadata_from_jsonl(jsonl_path: str) -> dict[str, Any]:
         dict: Dictionary mapping accession numbers to metadata dictionaries.
 
     """
-    metadata_dict = {}
+    metadata_dict: dict[str, Any] = {}
     processed_count = 0
 
     if not jsonl_path or not os.path.exists(jsonl_path):
@@ -4565,7 +4565,7 @@ def _stream_filter_cached_metadata_from_jsonl(
     if "min_release_date" in filters_active:
         min_release_date_parsed = _parse_date(min_release_date, filtername="min_release_date")
 
-    metadata_dict = {}
+    metadata_dict: dict[str, Any] = {}
     total_records = 0
     filter_stats = {
         "host": 0,
@@ -4967,7 +4967,7 @@ def filter_sequences(
 
     # Initialize lists to store filtered results (metadata is small, kept in memory)
     filtered_metadata = []  # Will store corresponding metadata dictionaries
-    protein_headers = []  # Will store protein/segment information from FASTA headers
+    protein_headers: list[Any] = []  # Will store protein/segment information from FASTA headers
     filtered_count = 0  # Count of sequences passing all filters
 
     # Counters for logging filter statistics
@@ -5264,7 +5264,7 @@ def save_command_summary(
                     f.write(f"Average sequence length: {sum(lengths) / len(lengths):.0f} bp\n\n")
 
                 # Completeness breakdown
-                completeness_counts = {}
+                completeness_counts: dict[str, int] = {}
                 for meta in filtered_metadata:
                     comp = meta.get("completeness", "unknown")
                     completeness_counts[comp] = completeness_counts.get(comp, 0) + 1
@@ -5274,7 +5274,7 @@ def save_command_summary(
                 f.write("\n")
 
                 # Source database breakdown
-                source_counts = {}
+                source_counts: dict[str, int] = {}
                 for meta in filtered_metadata:
                     source = meta.get("sourceDatabase", "unknown")
                     source_counts[source] = source_counts.get(source, 0) + 1
@@ -6181,7 +6181,7 @@ def fetch_genbank_metadata(
     _log_memory_usage("GenBank fetch start")
 
     # Initialize tracking variables
-    all_metadata = {}  # Only used for final return; populated from temp JSONL at end
+    all_metadata: dict[str, Any] = {}  # Only used for final return; populated from temp JSONL at end
     failed_batches = []
     total_metadata_written = 0  # Counter for metadata records streamed to disk
 
@@ -7053,7 +7053,7 @@ def _parse_genbank_xml(xml_content: str) -> dict[str, Any]:
             logger.debug("Processing GenBank record: %s", accession)
 
             # Initialize metadata dictionary for this record
-            metadata = {
+            metadata: dict[str, Any] = {
                 "accession": accession,
                 "genbank_data": {},  # Store GenBank-specific fields
             }
@@ -8741,14 +8741,14 @@ def virus(
     refseq_only = False
 
     # Initialize filter stats for each stage (populated by filter functions)
-    metadata_filter_stats = {}
-    genbank_filter_stats = {}
-    sequence_filter_stats = {}
+    metadata_filter_stats: dict[str, int] = {}
+    genbank_filter_stats: dict[str, int] = {}
+    sequence_filter_stats: dict[str, int] = {}
     total_after_genbank_filter = None
     total_after_sequence_filter = None
 
     # Initialize failed commands tracker for tracking all types of failures
-    failed_commands = {
+    failed_commands: dict[str, Any] = {
         "api_timeout": None,
         "empty_response": None,
         "sequence_batches": [],
@@ -9768,7 +9768,7 @@ def virus(
                             logger.warning("No sequences will pass the GenBank-based filters.")
                             filtered_accessions = []
                             filtered_metadata = []
-                            genbank_data_prefetch = {}
+                            genbank_data_prefetch: dict[str, Any] = {}
 
                             save_command_summary(
                                 outfolder=outfolder,
@@ -9985,7 +9985,7 @@ def virus(
             # For large datasets (millions of sequences), this avoids OOM errors
             total_final_sequences = _stream_copy_fasta(fna_file, output_fasta_file)
             filtered_metadata_final = filtered_metadata  # No change to metadata
-            protein_headers = []
+            protein_headers: list[Any] = []
             logger.info("All %d downloaded sequences were streamed to output", total_final_sequences)
             _log_memory_usage("after streaming sequences to output")
         else:
diff --git a/gget/utils.py b/gget/utils.py
index 2d86a564c..dfa4a2011 100644
--- a/gget/utils.py
+++ b/gget/utils.py
@@ -1138,7 +1138,7 @@ def json_list_to_df(json_list: list[Any], columns: list[tuple[str, str]]) -> pd.
 
     Returns data frame with columns as specified in keys.
     """
-    tmp_columns = [[] for _ in range(len(columns))]
+    tmp_columns: list[list[Any]] = [[] for _ in range(len(columns))]
 
     for json_obj in json_list:
         for i, column_key in enumerate(columns):
@@ -1186,7 +1186,7 @@ def parse(filename: str, format: str | None = None) -> Iterator[FastaRecord]:
         with open(filename, encoding="utf-8") as handle:
             current_id = None
             current_description = ""
-            current_seq = []
+            current_seq: list[str] = []
 
             for line in handle:
                 line = line.strip()