Home / simular-ai / Agent-S
AI Slop Code RIsk Monitor

simular-ai/Agent-S

Agent S: an open agentic framework that uses computers like a human

53.0 High pattern signal View on GitHub

Maintenance and Governance Review

This report summarizes scanner evidence for simular-ai/Agent-S, a Python project with 12,582 GitHub stars. SynthScan examined 22,267 lines of code across 109 source files, recording 444 pattern matches distributed across 18 syntactic categories. The legacy adjusted pattern signal is 53.0 (High pattern signal); it is not an authorship estimate.

Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.

53.0
Adjusted Signal
53.0
Raw Pattern Score
100%
Time Factor
2026-10-08
Last Push
12.6K
Stars
Python
Language
22.3K
Lines of Code
109
Files
444
Pattern Hits
2026-10-12
Scan Date
1.31
HC Hit Rate

Risk Review · v3

Use each vector to guide manual verification of the underlying findings.

Cognitive Ownership Risk 40.4/100 · MEDIUM

Can maintainers explain intent, assumptions, and trade-offs? 175 finding(s).

Hallucinated Dependency & Supply Chain Risk 31.7/100 · MEDIUM

Are imports declared and package/API names verified? 38 finding(s).

Agent Over-Engineering Ratio 84.5/100 · CRITICAL

Are wrappers, guards, and repeated structures necessary? 283 finding(s).

PR Review Velocity Impact 93.9/100 · CRITICAL

Which changes need focused human review? 444 finding(s).

What These Metrics Mean

Adjusted Signal
Legacy pattern score normalized per 1,000 scanned lines and multiplied by the repository-level time factor. It is not an estimate of AI authorship.
Raw Pattern Score
Sum of severity- and context-weighted pattern findings before applying the time factor.
Time Factor
A coarse multiplier based on repository last-push metadata. It does not identify when individual code was written.
Pattern Hits
Count of configured pattern findings. Review each location and surrounding code before acting.
HC Hit Rate
High- and critical-severity findings per scanned file. Severity is a configured detector weight, not proof of a vulnerability or authorship.
Lines / Files
Scan coverage denominators used by the legacy normalized score.

Pattern-Signal History

This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.

Severity Breakdown

Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.

CRITICAL 0HIGH 143MEDIUM 43LOW 258

Directory Score Breakdown

This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.

Pattern Findings

The scanner identified 444 distinct pattern matches across 18 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Cross-File Repetition109 hits · 545 pts
SeverityFileLineSnippetContext
HIGHgui_agents/s2/cli_app.py0get a single character from stdin without pressing enterSTRING
HIGHgui_agents/s3/cli_app.py0get a single character from stdin without pressing enterSTRING
HIGHgui_agents/s1/cli_app.py0get a single character from stdin without pressing enterSTRING
HIGHgui_agents/s2_5/cli_app.py0get a single character from stdin without pressing enterSTRING
HIGHgui_agents/s2/cli_app.py0handle ctrl+c signal for debugging during agent executionSTRING
HIGHgui_agents/s3/cli_app.py0handle ctrl+c signal for debugging during agent executionSTRING
HIGHgui_agents/s1/cli_app.py0handle ctrl+c signal for debugging during agent executionSTRING
HIGHgui_agents/s2_5/cli_app.py0handle ctrl+c signal for debugging during agent executionSTRING
HIGHgui_agents/s2/cli_app.py0show a platform-specific permission dialog and return true if approved.STRING
HIGHgui_agents/s3/cli_app.py0show a platform-specific permission dialog and return true if approved.STRING
HIGHgui_agents/s1/cli_app.py0show a platform-specific permission dialog and return true if approved.STRING
HIGHgui_agents/s2_5/cli_app.py0show a platform-specific permission dialog and return true if approved.STRING
HIGHgui_agents/s2/core/mllm.py0generate the next response based on previous messagesSTRING
HIGHgui_agents/s3/core/mllm.py0generate the next response based on previous messagesSTRING
HIGHgui_agents/s1/mllm/MultimodalAgent.py0generate the next response based on previous messagesSTRING
HIGHgui_agents/s2_5/core/mllm.py0generate the next response based on previous messagesSTRING
HIGHgui_agents/s2/core/knowledge.py0summarize the narrative experience for lifelong learning reflection args: trajectory: str: the narrative experience to bSTRING
HIGHgui_agents/s2/agents/manager.py0summarize the narrative experience for lifelong learning reflection args: trajectory: str: the narrative experience to bSTRING
HIGHgui_agents/s1/core/Manager.py0summarize the narrative experience for lifelong learning reflection args: trajectory: str: the narrative experience to bSTRING
HIGHgui_agents/s2/memory/procedural_memory.py0your response should be formatted like this: (previous action verification) carefully analyze based on the screenshot ifSTRING
HIGHgui_agents/s3/memory/procedural_memory.py0your response should be formatted like this: (previous action verification) carefully analyze based on the screenshot ifSTRING
HIGHgui_agents/s2_5/memory/procedural_memory.py0your response should be formatted like this: (previous action verification) carefully analyze based on the screenshot ifSTRING
HIGHgui_agents/s2/memory/procedural_memory.py0you are an expert in graphical user interfaces. your task is to process a phrase of text, and identify the most relevantSTRING
HIGHgui_agents/s2_5/memory/procedural_memory.py0you are an expert in graphical user interfaces. your task is to process a phrase of text, and identify the most relevantSTRING
HIGHgui_agents/s3/memory/procedural_memory.py0you are an expert in graphical user interfaces. your task is to process a phrase of text, and identify the most relevantSTRING
HIGHgui_agents/s2/agents/worker.py0predict the next action(s) based on the current observation.STRING
HIGHgui_agents/s3/agents/worker.py0predict the next action(s) based on the current observation.STRING
HIGHgui_agents/s1/core/Worker.py0predict the next action(s) based on the current observation.STRING
HIGHgui_agents/s2_5/agents/worker.py0predict the next action(s) based on the current observation.STRING
HIGHgui_agents/s2/agents/agent_s.py0generate next action prediction args: instruction: natural language instruction observation: current ui state observatioSTRING
HIGHgui_agents/s3/agents/agent_s.py0generate next action prediction args: instruction: natural language instruction observation: current ui state observatioSTRING
HIGHgui_agents/s1/core/AgentS.py0generate next action prediction args: instruction: natural language instruction observation: current ui state observatioSTRING
HIGHgui_agents/s2_5/agents/agent_s.py0generate next action prediction args: instruction: natural language instruction observation: current ui state observatioSTRING
HIGHgui_agents/s2/agents/grounding.py0import subprocess; import difflib; import pyautogui; import time; pyautogui.press('escape'); time.sleep(0.5); output = sSTRING
HIGHgui_agents/s1/aci/LinuxOSACI.py0import subprocess; import difflib; import pyautogui; import time; pyautogui.press('escape'); time.sleep(0.5); output = sSTRING
HIGHgui_agents/s1/aci/windowsagentarena/GroundingAgent.py0import subprocess; import difflib; import pyautogui; import time; pyautogui.press('escape'); time.sleep(0.5); output = sSTRING
HIGHgui_agents/s2_5/agents/grounding.py0import subprocess; import difflib; import pyautogui; import time; pyautogui.press('escape'); time.sleep(0.5); output = sSTRING
HIGHgui_agents/s3/agents/grounding.py0import subprocess; import difflib; import pyautogui; import time; pyautogui.press('escape'); time.sleep(0.5); output = sSTRING
HIGHgui_agents/s2/agents/grounding.py0click on the element args: element_description:str, a detailed descriptions of which element to click on. this descriptiSTRING
HIGHgui_agents/s3/agents/grounding.py0click on the element args: element_description:str, a detailed descriptions of which element to click on. this descriptiSTRING
HIGHgui_agents/s2_5/agents/grounding.py0click on the element args: element_description:str, a detailed descriptions of which element to click on. this descriptiSTRING
HIGHgui_agents/s2/agents/grounding.py0import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});STRING
HIGHgui_agents/s3/agents/grounding.py0import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});STRING
HIGHgui_agents/s1/aci/LinuxOSACI.py0import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});STRING
HIGHgui_agents/s1/aci/MacOSACI.py0import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});STRING
HIGHgui_agents/s1/aci/windowsagentarena/GroundingAgent.py0import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});STRING
HIGHgui_agents/s2_5/agents/grounding.py0import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});STRING
HIGHgui_agents/s2/agents/grounding.py0switch to a different application that is already open args: app_code:str the code name of the application to switch to STRING
HIGHgui_agents/s3/agents/grounding.py0switch to a different application that is already open args: app_code:str the code name of the application to switch to STRING
HIGHgui_agents/s1/aci/LinuxOSACI.py0switch to a different application that is already open args: app_code:str the code name of the application to switch to STRING
HIGHgui_agents/s2_5/agents/grounding.py0switch to a different application that is already open args: app_code:str the code name of the application to switch to STRING
HIGHgui_agents/s2/agents/grounding.py0type text/unicode into a specific element args: element_description:str, a detailed description of which element to enteSTRING
HIGHgui_agents/s2_5/agents/grounding.py0type text/unicode into a specific element args: element_description:str, a detailed description of which element to enteSTRING
HIGHgui_agents/s3/agents/grounding.py0type text/unicode into a specific element args: element_description:str, a detailed description of which element to enteSTRING
HIGHgui_agents/s2/agents/grounding.py0save facts, elements, texts, etc. to a long-term knowledge bank for reuse during this task. can be used for copy-pastingSTRING
HIGHgui_agents/s3/agents/grounding.py0save facts, elements, texts, etc. to a long-term knowledge bank for reuse during this task. can be used for copy-pastingSTRING
HIGHgui_agents/s1/aci/LinuxOSACI.py0save facts, elements, texts, etc. to a long-term knowledge bank for reuse during this task. can be used for copy-pastingSTRING
HIGHgui_agents/s1/aci/windowsagentarena/GroundingAgent.py0save facts, elements, texts, etc. to a long-term knowledge bank for reuse during this task. can be used for copy-pastingSTRING
HIGHgui_agents/s2_5/agents/grounding.py0save facts, elements, texts, etc. to a long-term knowledge bank for reuse during this task. can be used for copy-pastingSTRING
HIGHgui_agents/s2/agents/grounding.py0drag from the starting description to the ending description args: starting_description:str, a very detailed descriptionSTRING
49 more matches not shown…
Excessive Try-Catch Wrapping105 hits · 170 pts
SeverityFileLineSnippetContext
LOWgui_agents/s2/agents/worker.py225 except Exception as e:STRING
LOWgui_agents/s2/agents/agent_s.py361 except Exception as e:CODE
LOWgui_agents/s2/agents/grounding.py305 except Exception as e:STRING
LOWgui_agents/s2/utils/common_utils.py36 except Exception as e:CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py79 print("Error: Invalid JSON")CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py82 print("Error: 'dag' key not found in JSON")CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py85 print(f"Error: Invalid data structure - {e}")CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py88 print("Error: JSON not found")CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py109 print("Error: JSON not found in either <json> tags or ```json``` fence")CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py115 print(f"Error: Invalid JSON ({e})")CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py119 print("Error: 'dag' key not found in JSON")CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py125 print(f"Error: Invalid data structure - {e}")CODE
LOW⚡gui_agents/s2/utils/common_utils.py204 except Exception as e:CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py205 print(f"Error loading knowledge base: {e}")CODE
LOW⚡gui_agents/s2/utils/common_utils.py213 except Exception as e:CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py214 print(f"Error loading embeddings: {e}")CODE
LOW⚡gui_agents/s2/utils/common_utils.py222 except Exception as e:CODE
MEDIUM⚡gui_agents/s2/utils/common_utils.py223 print(f"Error saving embeddings: {e}")CODE
LOWgui_agents/s3/bbon/comparative_judge.py57 except Exception as e:CODE
MEDIUMgui_agents/s3/bbon/comparative_judge.py58 print(f"Error loading image {image_path}: {e}")CODE
LOWgui_agents/s3/agents/worker.py329 except Exception as e:STRING
LOWgui_agents/s3/agents/code_agent.py47 except Exception as e:CODE
LOWgui_agents/s3/agents/code_agent.py329 except Exception as e:STRING
LOWgui_agents/s3/agents/grounding.py74 except Exception:CODE
LOWgui_agents/s3/agents/grounding.py78 except Exception:CODE
LOWgui_agents/s3/utils/formatters.py26 except Exception as e:CODE
LOWgui_agents/s3/utils/local_env.py40 except Exception as e:CODE
LOWgui_agents/s3/utils/local_env.py64 except Exception as e:CODE
LOWgui_agents/s3/utils/common_utils.py50 except Exception as e:CODE
LOWgui_agents/s3/utils/common_utils.py139 except Exception as e:CODE
LOWgui_agents/s1/core/AgentS.py318 except Exception as e:CODE
MEDIUM⚡gui_agents/s1/utils/common_utils.py437 print("Error: Invalid JSON")CODE
MEDIUM⚡gui_agents/s1/utils/common_utils.py440 print("Error: 'dag' key not found in JSON")CODE
MEDIUM⚡gui_agents/s1/utils/common_utils.py443 print(f"Error: Invalid data structure - {e}")CODE
MEDIUM⚡gui_agents/s1/utils/common_utils.py446 print("Error: JSON not found")CODE
MEDIUM⚡gui_agents/s1/utils/common_utils.py845 print(f"Error loading knowledge base: {e}")CODE
MEDIUM⚡gui_agents/s1/utils/common_utils.py854 print(f"Error loading embeddings: {e}")CODE
MEDIUM⚡gui_agents/s1/utils/common_utils.py863 print(f"Error saving embeddings: {e}")CODE
LOW⚡gui_agents/s1/utils/common_utils.py844 except Exception as e:CODE
LOW⚡gui_agents/s1/utils/common_utils.py853 except Exception as e:CODE
LOW⚡gui_agents/s1/utils/common_utils.py862 except Exception as e:CODE
LOWgui_agents/s1/utils/common_utils.py67 except Exception as e:CODE
LOWgui_agents/s1/aci/LinuxOSACI.py249 except Exception as e:CODE
MEDIUMgui_agents/s1/aci/LinuxOSACI.py250 print(f"Error: {e}")CODE
LOWgui_agents/s1/aci/WindowsOSACI.py133 except Exception as e:CODE
MEDIUMgui_agents/s1/aci/WindowsOSACI.py134 print(f"Error: {e}")CODE
LOW⚡gui_agents/s1/aci/WindowsOSACI.py194 except Exception as e:CODE
MEDIUM⚡gui_agents/s1/aci/WindowsOSACI.py195 print(f"Error accessing foreground window: {e}")CODE
LOWgui_agents/s1/aci/WindowsOSACI.py471 except Exception as e:CODE
MEDIUMgui_agents/s1/aci/WindowsOSACI.py472 print(f"Error accessing children: {e}")CODE
MEDIUMgui_agents/s1/aci/WindowsOSACI.py468def children(self):CODE
LOWgui_agents/s1/aci/MacOSACI.py154 except Exception as e:CODE
MEDIUMgui_agents/s1/aci/MacOSACI.py155 print(f"Error: {e}")CODE
LOWgui_agents/s1/aci/windowsagentarena/GroundingAgent.py211 except Exception as e:CODE
MEDIUMgui_agents/s1/aci/windowsagentarena/GroundingAgent.py212 print(f"Error: {e}")CODE
LOWgui_agents/s2_5/agents/worker.py186 except Exception as e:STRING
LOWgui_agents/s2_5/agents/grounding.py305 except Exception as e:STRING
LOWgui_agents/s2_5/utils/common_utils.py20 except Exception as e:CODE
LOWgui_agents/s2_5/utils/common_utils.py40 except Exception as e:CODE
LOWintegrations/openclaw/agent_s_wrapper.py108 except Exception as e:CODE
45 more matches not shown…
Magic Placeholder Names21 hits · 152 pts
SeverityFileLineSnippetContext
HIGH⚡README.md143export OPENAI_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡README.md143export OPENAI_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡README.md151os.environ["OPENAI_API_KEY"] = "<YOUR_API_KEY>"CODE
HIGH⚡README.md151os.environ["OPENAI_API_KEY"] = "<YOUR_API_KEY>"CODE
HIGH⚡models.md6export OPENAI_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡models.md6export OPENAI_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡models.md12export ANTHROPIC_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡models.md12export ANTHROPIC_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡models.md18export GEMINI_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡models.md18export GEMINI_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡models.md26export AZURE_OPENAI_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡models.md26export AZURE_OPENAI_API_KEY=<YOUR_API_KEY>CODE
HIGHmodels.md40export OPENROUTER_API_KEY=<YOUR_API_KEY>CODE
HIGHmodels.md40export OPENROUTER_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡gui_agents/s1/README.md64export OPENAI_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡gui_agents/s1/README.md64export OPENAI_API_KEY=<YOUR_API_KEY>CODE
HIGH⚡gui_agents/s1/README.md71os.environ["OPENAI_API_KEY"] = "<YOUR_API_KEY>"CODE
HIGH⚡gui_agents/s1/README.md71os.environ["OPENAI_API_KEY"] = "<YOUR_API_KEY>"CODE
HIGH⚡integrations/openclaw/README.md33 export ANTHROPIC_API_KEY="your-api-key-here"CODE
HIGH⚡integrations/openclaw/README.md38 export OPENAI_API_KEY="your-api-key-here"CODE
HIGH⚡integrations/openclaw/README.md43 export GEMINI_API_KEY="your-api-key-here"CODE
Empty Error Handlers12 hits · 60 pts
SeverityFileLineSnippetContext
HIGHgui_agents/s1/utils/common_utils.py318except ValueError:CODE
HIGHgui_agents/s1/utils/common_utils.py626except ValueError:CODE
HIGHgui_agents/s1/aci/LinuxOSACI.py644except NotImplementedError:CODE
HIGHgui_agents/s1/aci/LinuxOSACI.py651except NotImplementedError:CODE
HIGHgui_agents/s1/aci/LinuxOSACI.py657except NotImplementedError:CODE
HIGHgui_agents/s1/aci/LinuxOSACI.py674except NotImplementedError:CODE
HIGHgui_agents/s1/aci/LinuxOSACI.py689except NotImplementedError:CODE
HIGHgui_agents/s1/aci/LinuxOSACI.py620except NotImplementedError:CODE
HIGHgui_agents/s1/aci/LinuxOSACI.py672except:CODE
HIGHosworld_setup/s3/bbon/generate_facts.py31except:CODE
HIGHosworld_setup/s3/bbon/generate_facts.py93except:CODE
HIGHosworld_setup/s3/bbon/utils.py252except ValueError:CODE
Deep Nesting61 hits · 58 pts
SeverityFileLineSnippetContext
LOWgui_agents/s2/cli_app.py48CODE
LOWgui_agents/s2/cli_app.py154CODE
LOWgui_agents/s2/core/mllm.py18CODE
LOWgui_agents/s2/core/mllm.py112CODE
LOWgui_agents/s2/agents/agent_s.py210CODE
LOWgui_agents/s2/utils/common_utils.py129CODE
LOWgui_agents/s3/cli_app.py49CODE
LOWgui_agents/s3/cli_app.py155CODE
LOWgui_agents/s3/core/mllm.py18CODE
LOWgui_agents/s3/core/mllm.py175CODE
LOWgui_agents/s3/agents/worker.py90CODE
LOWgui_agents/s3/agents/worker.py178CODE
LOWgui_agents/s1/cli_app.py46CODE
LOWgui_agents/s1/cli_app.py154CODE
LOWgui_agents/s1/core/Worker.py85CODE
LOWgui_agents/s1/core/AgentS.py187CODE
LOWgui_agents/s1/utils/common_utils.py193CODE
LOWgui_agents/s1/utils/common_utils.py466CODE
LOWgui_agents/s1/utils/common_utils.py515CODE
LOWgui_agents/s1/utils/common_utils.py556CODE
LOWgui_agents/s1/utils/common_utils.py595CODE
LOWgui_agents/s1/aci/LinuxOSACI.py581CODE
LOWgui_agents/s1/aci/LinuxOSACI.py140CODE
LOWgui_agents/s1/aci/LinuxOSACI.py225CODE
LOWgui_agents/s1/aci/WindowsOSACI.py26CODE
LOWgui_agents/s1/aci/WindowsOSACI.py104CODE
LOWgui_agents/s1/aci/MacOSACI.py125CODE
LOWgui_agents/s1/aci/windowsagentarena/GroundingAgent.py105CODE
LOWgui_agents/s1/aci/windowsagentarena/GroundingAgent.py187CODE
LOWgui_agents/s1/mllm/MultimodalAgent.py22CODE
LOWgui_agents/s1/mllm/MultimodalAgent.py108CODE
LOWgui_agents/s2_5/cli_app.py48CODE
LOWgui_agents/s2_5/cli_app.py154CODE
LOWgui_agents/s2_5/core/mllm.py18CODE
LOWgui_agents/s2_5/core/mllm.py112CODE
LOWgui_agents/s2_5/agents/worker.py75CODE
LOWgui_agents/s2_5/utils/common_utils.py44CODE
LOWosworld_setup/s2/run.py160CODE
LOWosworld_setup/s2/run.py305CODE
LOWosworld_setup/s2/run.py342CODE
LOWosworld_setup/s3/run.py80CODE
LOWosworld_setup/s3/run.py362CODE
LOWosworld_setup/s3/run.py462CODE
LOWosworld_setup/s3/run.py499CODE
LOWosworld_setup/s3/run_local.py176CODE
LOWosworld_setup/s3/run_local.py303CODE
LOWosworld_setup/s3/run_local.py340CODE
LOWosworld_setup/s3/bbon/run_judge.py78CODE
LOWosworld_setup/s3/bbon/generate_facts.py145CODE
LOWosworld_setup/s3/bbon/utils.py50CODE
LOWosworld_setup/s3/bbon/utils.py163CODE
LOWosworld_setup/s1/run.py121CODE
LOWosworld_setup/s1/run.py241CODE
LOWosworld_setup/s1/run.py278CODE
LOWosworld_setup/s2_5/run.py76CODE
LOWosworld_setup/s2_5/run.py356CODE
LOWosworld_setup/s2_5/run.py456CODE
LOWosworld_setup/s2_5/run.py493CODE
LOWosworld_setup/s2_5/run_local.py176CODE
LOWosworld_setup/s2_5/run_local.py306CODE
1 more matches not shown…
Hyper-Verbose Identifiers49 hits · 48 pts
SeverityFileLineSnippetContext
LOWgui_agents/s2/core/knowledge.py161 def retrieve_narrative_experience(self, instruction: str) -> Tuple[str, str]:CODE
LOWgui_agents/s2/core/knowledge.py198 def retrieve_episodic_experience(self, instruction: str) -> Tuple[str, str]:CODE
LOWgui_agents/s2/core/knowledge.py312 def initialize_task_trajectory(self, instruction: str) -> None:CODE
LOWgui_agents/s2/core/knowledge.py338 def handle_subtask_trajectory(self, meta_data: Dict) -> None:CODE
LOWgui_agents/s2/memory/procedural_memory.py8 def construct_worker_procedural_memory(agent_class, skipped_actions):CODE
LOWgui_agents/s2/agents/worker.py247 def clean_worker_generation_for_reflection(self, worker_generation: str) -> str:STRING
LOWgui_agents/s2/agents/manager.py100 def _generate_step_by_step_plan(CODE
LOW⚡gui_agents/s2/utils/common_utils.py129def parse_single_code_from_string(input_string):CODE
LOWgui_agents/s2/utils/common_utils.py189def extract_first_agent_function(code_string):CODE
LOWgui_agents/s3/memory/procedural_memory.py13 def construct_simple_worker_procedural_memory(agent_class, skipped_actions):STRING
LOWgui_agents/s3/bbon/behavior_narrator.py85 def get_mouse_action_representation(mouse_actions: list[str]) -> str:CODE
LOWgui_agents/s3/bbon/comparative_judge.py10def get_final_screenshot_file(task_dir: str) -> str:CODE
LOWgui_agents/s3/bbon/comparative_judge.py31def image_to_openai_message_format(CODE
LOWgui_agents/s1/core/ProceduralMemory.py7 def construct_worker_procedural_memory(agent_class):CODE
LOWgui_agents/s1/core/Knowledge.py154 def retrieve_narrative_experience(self, instruction: str) -> Tuple[str, str]:CODE
LOWgui_agents/s1/core/Knowledge.py190 def retrieve_episodic_experience(self, instruction: str) -> Tuple[str, str]:CODE
LOWgui_agents/s1/core/Manager.py86 def _generate_step_by_step_plan(CODE
LOWgui_agents/s1/utils/ocr_server.py19def text_cvt_orc_format_paddle(paddle_result):CODE
LOW⚡gui_agents/s1/utils/common_utils.py595def parse_action_from_fixed_code(action_string, linearized_accessibility_tree):CODE
LOW⚡gui_agents/s1/utils/common_utils.py599 def parse_action_from_agent_code(action_str):CODE
LOWgui_agents/s1/utils/common_utils.py360def linearize_accessibility_tree(accessibility_tree, platform="ubuntu", tag=False):CODE
LOWgui_agents/s1/utils/common_utils.py466def parse_actions_from_string(input_string):CODE
LOWgui_agents/s1/utils/common_utils.py500def parse_fixed_action_from_string(input_string):CODE
LOWgui_agents/s1/utils/common_utils.py556def parse_single_code_from_string(input_string):CODE
LOWgui_agents/s1/utils/common_utils.py695def parse_code_from_som_string(input_string, masks):CODE
LOWgui_agents/s1/utils/common_utils.py769def text_cvt_orc_format_paddle(paddle_result):CODE
LOWgui_agents/s1/utils/common_utils.py829def extract_first_agent_function(code_string):CODE
LOWgui_agents/s1/aci/LinuxOSACI.py199 def extract_elements_from_screenshot(self, screenshot) -> Dict:STRING
LOWgui_agents/s1/aci/LinuxOSACI.py301 def linearize_and_annotate_tree(self, obs, show_all=False):CODE
LOWgui_agents/s1/aci/WindowsOSACI.py89 def extract_elements_from_screenshot(self, screenshot: bytes) -> Dict[str, Any]:CODE
LOW⚡gui_agents/s1/aci/WindowsOSACI.py186 def linearize_and_annotate_tree(CODE
LOWgui_agents/s1/aci/ACI.py30 def linearize_and_annotate_tree(CODE
LOWgui_agents/s1/aci/MacOSACI.py110 def extract_elements_from_screenshot(self, screenshot: bytes) -> Dict[str, Any]:CODE
LOWgui_agents/s1/aci/MacOSACI.py207 def linearize_and_annotate_tree(CODE
LOWgui_agents/s1/aci/windowsagentarena/GroundingAgent.py163 def extract_elements_from_screenshot(self, screenshot) -> Dict:STRING
LOWgui_agents/s1/aci/windowsagentarena/GroundingAgent.py263 def linearize_and_annotate_tree(self, obs, show_all=False):CODE
LOWgui_agents/s2_5/memory/procedural_memory.py7 def construct_simple_worker_procedural_memory(agent_class, skipped_actions):CODE
LOWgui_agents/s2_5/utils/common_utils.py44def parse_single_code_from_string(input_string):CODE
LOWgui_agents/s2_5/utils/common_utils.py98def extract_first_agent_function(code_string):CODE
LOWtests/test_providers.py22 def test_ollama_missing_config(self):CODE
LOWtests/test_providers.py28 def test_ollama_valid_config_param(self):CODE
LOWtests/test_providers.py40 def test_ollama_valid_config_env(self):CODE
LOWosworld_setup/s3/bbon/generate_facts.py14async def generate_single_fact_caption(CODE
LOWosworld_setup/s3/bbon/generate_facts.py59async def generate_fact_captions_parallel(CODE
LOWosworld_setup/s3/bbon/utils.py10def image_to_openai_message_format(CODE
LOWosworld_setup/s3/bbon/utils.py107def get_final_screenshot_file(result_dir: str) -> str:CODE
LOW⚡osworld_setup/s3/bbon/utils.py163def get_new_tasks_classification(results_dirs: [str]):CODE
LOWosworld_setup/s3/bbon/utils.py229def check_selected_trajectory(results_dirs: [str], selected_trajectory: str, task: str):CODE
LOWosworld_setup/s3/bbon/utils.py268def evaluate_comparative_results(results_dirs: [str], json_path: str = None):CODE
Structural Annotation Overuse18 hits · 36 pts
SeverityFileLineSnippetContext
LOWosworld_setup/s2/OSWorld.md3# Step 1: Set up Agent S2COMMENT
LOWosworld_setup/s2/OSWorld.md7# Step 2: Copying Over Run FilesCOMMENT
LOWosworld_setup/s3/run.sh1# Step 1: Complete 2 or more rollouts on either AWS or locallyCOMMENT
LOW⚡osworld_setup/s3/run.sh36# Step 2: Generate FactsCOMMENT
LOW⚡osworld_setup/s3/run.sh45# Step 3: Run the Judge. Make sure the order of the results-dirs is the same as the order above.COMMENT
LOW⚡osworld_setup/s3/OSWorld.md3# Step 1: Set up Agent S3COMMENT
LOW⚡osworld_setup/s3/OSWorld.md7# Step 2: Copying Over Run FilesCOMMENT
LOW⚡osworld_setup/s3/OSWorld.md11# Step 3: Switch the AMICOMMENT
LOW⚡osworld_setup/s3/OSWorld.md15# Step 4: Generating FactsCOMMENT
LOWosworld_setup/s3/OSWorld.md31# Step 5: Run the JudgeCOMMENT
LOW⚡osworld_setup/s3/bbon/utils.py164 # Step 1: collect domain/task_ids for each trajectoryCOMMENT
LOW⚡osworld_setup/s3/bbon/utils.py178 # Step 2: find tasks common to all trajectoriesCOMMENT
LOW⚡osworld_setup/s3/bbon/utils.py187 # Step 3: evaluate each common taskCOMMENT
LOW⚡osworld_setup/s1/OSWorld.md3# Step 1: Set up Agent SCOMMENT
LOW⚡osworld_setup/s1/OSWorld.md7# Step 2: Copying Over Run FilesCOMMENT
LOW⚡osworld_setup/s1/OSWorld.md14# Step 3: Best PracticesCOMMENT
LOWosworld_setup/s2_5/OSWorld.md3# Step 1: Set up Agent S2.5COMMENT
LOWosworld_setup/s2_5/OSWorld.md7# Step 2: Copying Over Run FilesCOMMENT
Redundant / Tautological Comments22 hits · 33 pts
SeverityFileLineSnippetContext
LOWgui_agents/s2/cli_app.py160 # Check if we're in paused state and waitCOMMENT
LOWgui_agents/s2/core/mllm.py149 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s2/core/mllm.py200 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s2/core/mllm.py247 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s3/cli_app.py161 # Check if we're in paused state and waitCOMMENT
LOWgui_agents/s3/core/mllm.py212 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s3/core/mllm.py263 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s3/core/mllm.py310 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s3/agents/code_agent.py155 # Check if response is None or emptyCOMMENT
LOWgui_agents/s3/agents/grounding.py450 # Check if text contains Unicode characters that pyautogui.write() can't handleCOMMENT
LOWgui_agents/s1/cli_app.py160 # Check if we're in paused state and waitCOMMENT
LOWgui_agents/s1/utils/common_utils.py254 # Check if the area only contains one colorCOMMENT
LOWgui_agents/s1/aci/MacOSACI.py546 # Iterate through the list and print each application's nameCOMMENT
LOWgui_agents/s1/mllm/MultimodalAgent.py130 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s1/mllm/MultimodalAgent.py175 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s1/mllm/MultimodalAgent.py222 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s2_5/cli_app.py160 # Check if we're in paused state and waitCOMMENT
LOWgui_agents/s2_5/core/mllm.py149 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s2_5/core/mllm.py200 # Check if image_content is a list or a single imageCOMMENT
LOWgui_agents/s2_5/core/mllm.py247 # Check if image_content is a list or a single imageCOMMENT
LOWintegrations/openclaw/agent_s_wrapper.py165 # Output resultCOMMENT
LOWosworld_setup/s3/bbon/utils.py134 # Check if file exists and is validCOMMENT
Modern AI Meta-Vocabulary6 hits · 18 pts
SeverityFileLineSnippetContext
MEDIUMgui_agents/s2/core/knowledge.py55 # All three agents share a generic RAG prompt that asks the agent to provide information for UI automation in CUCOMMENT
MEDIUMgui_agents/s2/agents/worker.py114 # Get RAG knowledge, only update system message at t=0COMMENT
MEDIUMgui_agents/s3/agents/grounding.py573 # This is a full task - use the original task instruction to prevent hallucinationCOMMENT
MEDIUMgui_agents/s1/core/Worker.py125 # Get RAG knowledge, only update system message at t=0COMMENT
MEDIUMgui_agents/s1/core/Worker.py127 # TODO: uncomment and fix for subtask level RAGCOMMENT
MEDIUMgui_agents/s1/core/Knowledge.py56 # All three agent share a generic RAG prompt that ask agent to provide information for UI automation in CURRENT_COMMENT
Unused Imports17 hits · 17 pts
SeverityFileLineSnippetContext
LOWgui_agents/s2/agents/manager.py11CODE
LOWgui_agents/s1/core/Worker.py2CODE
LOWgui_agents/s1/utils/query_perplexica.py2CODE
LOWgui_agents/s1/aci/MacOSACI.py11CODE
LOWgui_agents/s1/aci/windowsagentarena/GroundingAgent.py3CODE
LOWgui_agents/s1/mllm/MultimodalEngine.py6CODE
LOWgui_agents/s1/mllm/MultimodalEngine.py11CODE
LOWgui_agents/s1/mllm/MultimodalAgent.py6CODE
LOWtests/test_providers.py3CODE
LOWosworld_setup/s2/lib_run_single.py6CODE
LOWosworld_setup/s3/lib_run_single.py6CODE
LOWosworld_setup/s3/lib_run_single.py7CODE
LOWosworld_setup/s1/lib_run_single.py6CODE
LOWosworld_setup/s2_5/lib_run_single_local.py6CODE
LOWosworld_setup/s2_5/lib_run_single_local.py7CODE
LOWosworld_setup/s2_5/lib_run_single.py6CODE
LOWosworld_setup/s2_5/lib_run_single.py7CODE
Verbosity Indicators6 hits · 13 pts
SeverityFileLineSnippetContext
LOWosworld_setup/s3/run.sh1# Step 1: Complete 2 or more rollouts on either AWS or locallyCOMMENT
LOW⚡osworld_setup/s3/run.sh36# Step 2: Generate FactsCOMMENT
LOW⚡osworld_setup/s3/run.sh45# Step 3: Run the Judge. Make sure the order of the results-dirs is the same as the order above.COMMENT
LOW⚡osworld_setup/s3/bbon/utils.py164 # Step 1: collect domain/task_ids for each trajectoryCOMMENT
LOW⚡osworld_setup/s3/bbon/utils.py178 # Step 2: find tasks common to all trajectoriesCOMMENT
LOW⚡osworld_setup/s3/bbon/utils.py187 # Step 3: evaluate each common taskCOMMENT
Slop Phrases3 hits · 6 pts
SeverityFileLineSnippetContext
MEDIUMgui_agents/s2/memory/procedural_memory.py88 - If you feel some future subtasks are incorrect or unnecessary, feel free to modify or even remove them.CODE
MEDIUMgui_agents/s1/core/Worker.py159 # Clear older messages - we keep full context. if you want to keep only the last n messages, you can use the fluCOMMENT
LOWgui_agents/s1/core/ProceduralMemory.py60 # MANAGER_PROMPT = """You are a planning agent for solving GUI navigation tasks. You will be provided the initial coSTRING
Modern Structural Boilerplate5 hits · 5 pts
SeverityFileLineSnippetContext
LOWgui_agents/s2/core/knowledge.py322 def update_task_trajectory(self, meta_data: Dict) -> None:CODE
LOWgui_agents/s2/agents/agent_s.py66 def update_narrative_memory(self, trajectory: str) -> None:CODE
LOWgui_agents/s2/agents/agent_s.py339 def update_narrative_memory(self, trajectory: str) -> None:CODE
LOWgui_agents/s1/core/AgentS.py61 def update_narrative_memory(self, trajectory: str) -> None:CODE
LOWgui_agents/s1/core/AgentS.py296 def update_narrative_memory(self, trajectory: str) -> None:CODE
Docstring Block Structure1 hit · 5 pts
SeverityFileLineSnippetContext
HIGHgui_agents/s3/utils/common_utils.py16 Attempts to evaluate the code into a pyautogui code snippet with grounded actions using the observation screenshot.STRING
Self-Referential Comments1 hit · 4 pts
SeverityFileLineSnippetContext
MEDIUM⚡gui_agents/s1/utils/common_utils.py609 # Define a regex pattern to extract the action type and parametersCOMMENT
Over-Commented Block4 hits · 4 pts
SeverityFileLineSnippetContext
LOWgui_agents/s1/aci/windowsagentarena/GroundingAgent.py421 # if overwrite:COMMENT
LOWgui_agents/s1/aci/windowsagentarena/GroundingAgent.py441COMMENT
LOWgui_agents/s1/aci/windowsagentarena/GroundingAgent.py461 # node = self.find_element(0)COMMENT
LOWgui_agents/s1/mllm/MultimodalEngine.py21# tokenizer_image_token,COMMENT
AI Structural Patterns3 hits · 3 pts
SeverityFileLineSnippetContext
LOWgui_agents/s2/agents/agent_s.py90CODE
LOWgui_agents/s3/bbon/behavior_narrator.py271CODE
LOWgui_agents/s1/mllm/MultimodalEngine.py40CODE
AI Slop Vocabulary1 hit · 3 pts
SeverityFileLineSnippetContext
MEDIUMgui_agents/s1/core/ProceduralMemory.py66 # MANAGER_PROMPT = """You are an expert planning agent for GUI tasks. You will be provided with an initial state of COMMENT