Public scan — anyone with this URL can view this analysis. Sign up to track your own repos privately, run scheduled re-scans, and get AI fix prompts via your dashboard.
Sign up free Scan another repo
45 of your 144 findings came from Repobility's proprietary detections. ✓ Repobility tags below mark them.

Scan timing: clone 4.81s · analysis 25.43s · 12.5 MB · GitHub API rate-limit (preflight)

jingyaogong/minimind

https://github.com/jingyaogong/minimind · scanned 2026-06-05 11:39 UTC (1 week, 2 days ago) · 10 languages

225 raw signals (129 security + 96 graph) 4th percentile · Python · small (2-20K LoC) System graph score 83 (lower by 41)

File as issue Image
UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 1 week, 2 days ago · v2 · 124 actionable findings from 2 signal sources. 53 repeated signals grouped for readability. Security checks, system graph analysis, and verified AI-agent feedback are merged into one review queue.

JSON
Combined
66.5
/100
Security checks
50
81 findings
System graph
83
88.9% cov · 43 findings
Critical
1
click to filter
Agents
6
0 votes
Crowd
0
reported
Score breakdown â 2026-05-18-v5
Component Sub-score Weight Contribution
structure_score 55.0 0.15 8.25
security_score 52.3 0.25 13.07
testing_score 0.0 0.20 0.00
documentation_score 64.0 0.15 9.60
practices_score 42.0 0.15 6.30
code_quality 46.6 0.10 4.66
Overall 1.00 41.9
Severity distribution — click a segment to filter
Active filters: excluding tests × Reset all
Severity: Critical 1 High 31 Medium 29 Low 40 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Security checks 81 System graph 43 Crowd 0 Layer: Quality 28 Security 21 Software 72 Frontend 1 Cicd 1 Api 1

All 170 nodes from the latest scan, grouped by kind. Each node is a unit the engine identified (file, function, endpoint, table…). Most users won't need this view — it's primarily for debugging the engine's graph extraction or for AI agents that want to enumerate the project structure.

LabelLayerStatusPath
init_model software healthy eval_llm.py:12
main software healthy eval_llm.py:32
convert_torch2transformers_minimind software dead scripts/convert_model.py:16
convert_torch2transformers software healthy scripts/convert_model.py:40
convert_transformers2torch software dead scripts/convert_model.py:99
convert_merge_base_lora software dead scripts/convert_model.py:105
convert_jinja_to_json software dead scripts/convert_model.py:115
convert_json_to_jinja software dead scripts/convert_model.py:121
get_text software healthy scripts/web_demo.py:102
execute_tool software healthy scripts/web_demo.py:124
process_assistant_content software healthy scripts/web_demo.py:149
format_tool_call software dead scripts/web_demo.py:152
format_think software dead scripts/web_demo.py:174
format_think_in_progress software dead scripts/web_demo.py:182
format_think_no_start software dead scripts/web_demo.py:188
load_model_tokenizer software healthy scripts/web_demo.py:199
clear_chat_messages software dead scripts/web_demo.py:212
init_chat_messages software dead scripts/web_demo.py:217
regenerate_answer software dead scripts/web_demo.py:233
setup_seed software healthy scripts/web_demo.py:302
main software healthy scripts/web_demo.py:312
init_model software healthy scripts/serve_openai_api.py:28
get_open_thinking software healthy scripts/serve_openai_api.py:61
__init__ software healthy scripts/serve_openai_api.py:72
on_finalized_text software dead scripts/serve_openai_api.py:77
parse_response software healthy scripts/serve_openai_api.py:83
generate_stream_response software healthy scripts/serve_openai_api.py:105
_generate software healthy scripts/serve_openai_api.py:113
chat_completions software healthy scripts/serve_openai_api.py:172
get_tools software healthy scripts/eval_toolcall.py:42
init_model software healthy scripts/eval_toolcall.py:57
parse_tool_calls software healthy scripts/eval_toolcall.py:70
parse_tool_call_from_text software healthy scripts/eval_toolcall.py:81
execute_tool software healthy scripts/eval_toolcall.py:99
generate software healthy scripts/eval_toolcall.py:115
chat_api software healthy scripts/eval_toolcall.py:133
run_case software healthy scripts/eval_toolcall.py:177
main software healthy scripts/eval_toolcall.py:202
__init__ software healthy model/model_lora.py:7
forward software healthy model/model_lora.py:17
apply_lora software healthy model/model_lora.py:21
forward_with_lora software dead model/model_lora.py:29
load_lora software healthy model/model_lora.py:35
save_lora software healthy model/model_lora.py:45
merge_lora software healthy model/model_lora.py:56
__init__ software healthy model/model_minimind.py:237
norm software healthy model/model_minimind.py:56
forward software healthy model/model_minimind.py:245
precompute_freqs_cis software healthy model/model_minimind.py:62
apply_rotary_pos_emb software healthy model/model_minimind.py:80

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

LabelLayerStatusPath
README.md software healthy README.md
README_en.md software healthy README_en.md
eval_llm.py software healthy eval_llm.py
requirements.txt software healthy requirements.txt
CODE_OF_CONDUCT.md software healthy CODE_OF_CONDUCT.md
convert_model.py software healthy scripts/convert_model.py
web_demo.py software healthy scripts/web_demo.py
serve_openai_api.py software healthy scripts/serve_openai_api.py
chat_api.py software warning scripts/chat_api.py
eval_toolcall.py software healthy scripts/eval_toolcall.py
__init__.py software healthy model/__init__.py
tokenizer_config.json software healthy model/tokenizer_config.json
tokenizer.json software healthy model/tokenizer.json
model_lora.py software healthy model/model_lora.py
model_minimind.py software healthy model/model_minimind.py
__init__.py software healthy dataset/__init__.py
lm_dataset.py software healthy dataset/lm_dataset.py
dataset.md software healthy dataset/dataset.md
train_agent.py software healthy trainer/train_agent.py
rollout_engine.py software healthy trainer/rollout_engine.py
trainer_utils.py software healthy trainer/trainer_utils.py
train_grpo.py software healthy trainer/train_grpo.py
train_lora.py software healthy trainer/train_lora.py
train_tokenizer.py software healthy trainer/train_tokenizer.py
train_ppo.py software healthy trainer/train_ppo.py
train_pretrain.py software healthy trainer/train_pretrain.py
train_dpo.py software healthy trainer/train_dpo.py
train_distillation.py software healthy trainer/train_distillation.py
train_full_sft.py software healthy trainer/train_full_sft.py

LabelLayerStatusPath
ChatRequest software healthy scripts/serve_openai_api.py:50
CustomStreamer software healthy scripts/serve_openai_api.py:71
LoRA software healthy model/model_lora.py:6
MiniMindConfig software healthy model/model_minimind.py:10
RMSNorm software healthy model/model_minimind.py:50
Attention software healthy model/model_minimind.py:91
FeedForward software healthy model/model_minimind.py:136
MOEFeedForward software healthy model/model_minimind.py:148
MiniMindBlock software healthy model/model_minimind.py:178
MiniMindModel software healthy model/model_minimind.py:196
MiniMindForCausalLM software healthy model/model_minimind.py:234
PretrainDataset software healthy dataset/lm_dataset.py:37
SFTDataset software healthy dataset/lm_dataset.py:58
DPODataset software healthy dataset/lm_dataset.py:122
RLAIFDataset software healthy dataset/lm_dataset.py:195
AgentRLDataset software healthy dataset/lm_dataset.py:226
RolloutResult software healthy trainer/rollout_engine.py:41
RolloutEngine software healthy trainer/rollout_engine.py:51
TorchRolloutEngine software healthy trainer/rollout_engine.py:64
SGLangRolloutEngine software healthy trainer/rollout_engine.py:99
SkipBatchSampler software healthy trainer/trainer_utils.py:134
LMForRewardModel software healthy trainer/trainer_utils.py:160
CriticModel software healthy trainer/train_ppo.py:37

LabelLayerStatusPath
scripts software healthy scripts
model software healthy model
dataset software healthy dataset
trainer software healthy trainer

LabelLayerStatusPath
repobility-clone-5e_jvj79 software healthy /tmp/repobility-clone-5e_jvj79

LabelLayerStatusPath
POST /v1/chat/completions api healthy scripts/serve_openai_api.py

LabelLayerStatusPath
port:8998 network healthy scripts/serve_openai_api.py

LabelLayerStatusPath
gpu (detected) hardware healthy eval_llm.py
For AI agents: Voting guide (TP/FP) MCP manifest Stdio wrapper SARIF Integrate Findings queue Vote TP/FP on findings to calibrate the engine.
For AI agents + API integrations
Email me when this repo regresses
Free. We re-scan periodically; new criticals → your inbox. No signup required for the scan itself.
API access

This page is publicly accessible at: https://repobility.com/scan/998a2207-f825-44b2-b8a5-0ec507737cd5/

To check status programmatically (no auth required): 

curl -s https://repobility.com/api/v1/public/scan/998a2207-f825-44b2-b8a5-0ec507737cd5/

Important — please don't re-submit the same URL repeatedly. The submission endpoint is idempotent: re-submitting the same git URL returns this same scan_token, not a new one. To re-scan this repo, sign up free and use the dashboard.