repowiserepowise
Sign in
2233admin/awesome-autoresearchx
OverviewDocsArchitectureKnowledge GraphFilesCode HealthRefactoring

People & History

CommitsContributorsDecisions
ChatPro
Stats
repowiserepowise
ExplorePricingDocs
Sign inIndex repoIndex your repo free
repowise2233admin/awesome-autoresearchx

Commits

Every commit scored for change-risk against this repo's own history, so 'elevated' means elevated here rather than on some global curve.

Needs review

7of 28 scored

7 commits sit in this repo's top risk tercile, which is 25% of the 28scored. The cut is drawn against this codebase's own history rather than a global curve, so a quiet repo still fills its top band, and here it starts at 2.0 out of 10. What pushes a commit up is size and spread together: a large change confined to one area scores below a smaller one scattered across a dozen files.

Fix commits27%Commits whose subject reads as a bug fix rather than new work.Written by an agent1346%Read from commit trailers, so it counts what was declared.Change diffusion0.03bitsShannon entropy of a commit's churn across its files. Zero is a single file, and every extra bit is a doubling of how widely the change spread.Review threshold2.0out of 10Score a commit has to clear to land in this repo's top tercile.

How the work changed shape

Commit categories over time, read off the subject line. Fixes carry the accent because that is the series this chart exists to show.

Consistently feature-driven across its history.

Feature61%
Fix4%
Docs11%
Chore4%
Other21%
46%of indexed commits are agent-attributed(13 of 28)
claude (13)

Review-priority queue

Ranked by change-risk, highest first. Priority is a tercile of this repo's own distribution, so a quiet repo still fills its top band.

Commit review-priority queue
#CommitAuthorWhenLinesRiskTop driver
1
1e10fbdbInitial awesome-autoresearch list
Zhengyao Jiang
5mo ago+165 -0
98%Elevated
more lines added than baseline
2
f48ddb8fStandardize Traces labels by type: progress chart, blog, or PR
Zhengyao Jiangclaudeassisted
4mo ago+11 -11
93%Elevated
more focused than baseline
3
83d8fff2Standardize Traces column to uniform [traces] link text
Zhengyao Jiangclaudeassisted
4mo ago+11 -11
93%Elevated
more focused than baseline
4
d855cb80Add ResearchClawBench benchmark
black-yt
3mo ago+6 -0
88%Elevated
fewer lines added than baseline
5
6b0add67Emphasize optimization traces in About and README intro, fix Nick Oak trace link
Zhengyao Jiangclaudeassisted
4mo ago+3 -3
84%Elevated
fewer lines added than baseline
6
e5906261Add Agon and AutoNumerics
Zenbook
1mo ago+2 -0
79%Elevated
fewer lines added than baseline
7
7b798f95Add peptide AI and Vesuvius Challenge ink detection use cases
Zhengyao Jiang
5mo ago+2 -0
79%Elevated
fewer lines added than baseline
8
f549d12aAdd AutoZyme use case (bioinformatics software speedup)
ElliotXieclaudeassisted
2mo ago+1 -0
63%Typical
fewer lines added than baseline
9
d0fdade3Add vlasenkoalexey/tpu_performance_autoresearch_wiki use case (TPU model performance optimization)
Aleksey Vlasenko
2mo ago+1 -0
63%Typical
fewer lines added than baseline
10
937eea43Add CORAL to Implementations & Forks
BobbyZhouZijian
4mo ago+1 -0
63%Typical
fewer lines added than baseline
11
55a05287Add auto-agent to Implementations & Forks
Alfonso Grazianoclaudeassisted
4mo ago+1 -0
63%Typical
fewer lines added than baseline
12
3e392d26Add digivolve
Mingde (Matthew) Zeng
4mo ago+1 -0
63%Typical
fewer lines added than baseline
13
ae4a7f51Add repo and gamed branch links to tennis XGBoost entry
buildoak
5mo ago+1 -1
63%Typical
fewer lines added than baseline
14
3be76580Add Bitcoin price formula discovery use case
CBaquero
5mo ago+1 -0
63%Typical
fewer lines added than baseline
15
f89e5cfcTrim Agon description to house style
Zhengyao Jiangclaudeassisted
3w ago+1 -1
27%Below typical
fewer lines added than baseline
16
ae514749Add OpenAI Parameter Golf entry: Aiden #1 contributor in hiring challenge
Zhengyao Jiangclaudeassisted
4w ago+1 -0
27%Below typical
fewer lines added than baseline
17
4142c94cAdd Autoresearch on autoresearch entry: AIDE2 self-improvement run
Zhengyao Jiangclaudeassisted
4w ago+1 -0
27%Below typical
fewer lines added than baseline
18
00d3f3e3Add Flappy Bird game AI use case
Zhengyao Jiang
1mo ago+1 -0
27%Below typical
fewer lines added than baseline
19
e9531f49Gloss MaxText as Google's reference repo of SOTA TPU-optimized models
Aleksey Vlasenko
2mo ago+1 -1
27%Below typical
fewer lines added than baseline
20
15f45afcAdd evo to Implementations & Forks
Zhengyao Jiangclaudeassisted
2mo ago+1 -0
27%Below typical
fewer lines added than baseline
21
b6a759d9Add FML-bench benchmark: controlled study of AI research agent search strategies
Zhengyao Jiangclaudeassisted
2mo ago+1 -0
27%Below typical
fewer lines added than baseline
22
ecfa3d14Add SimplexFold entry: Codex /goal autoresearch on AlphaFold2 architecture
Zhengyao Jiangclaudeassisted
3mo ago+1 -0
27%Below typical
fewer lines added than baseline
23
4db49e96Update README.md
Zhengyao Jiang
4mo ago+1 -1
27%Below typical
fewer lines added than baseline
24
55eb1374Fix Peptide AI trace: link to tweet (not progress chart - it's a dashboard screenshot)
Zhengyao Jiangclaudeassisted
4mo ago+1 -1
27%Below typical
fewer lines added than baseline
25
6778fdfdUpdate README.md
Zhengyao Jiang
4mo ago+1 -1
27%Below typical
fewer lines added than baseline
26
c78d85f8Remove retweet link from Vesuvius entry
Zhengyao Jiang
5mo ago+1 -1
27%Below typical
fewer lines added than baseline
27
141ad85dAdd RL post-training optimization use case
Zhengyao Jiang
5mo ago+1 -0
27%Below typical
fewer lines added than baseline
28
be5a07e2Remove Peptide AI entry: no proper optimization traces
Zhengyao Jiangclaudeassisted
4mo ago+0 -1
2%Below typical
fewer lines added than baseline
  • 1e10fbdbInitial awesome-autoresearch list
    Author
    Zhengyao Jiang
    When
    5mo ago
    Lines
    +165 -0
    Risk
    98%Elevated
  • f48ddb8fStandardize Traces labels by type: progress chart, blog, or PR
    Author
    Zhengyao Jiang
    When
    4mo ago
    Lines
    +11 -11
    Risk
    93%Elevated
  • 83d8fff2Standardize Traces column to uniform [traces] link text
    Author
    Zhengyao Jiang
    When
    4mo ago
    Lines
    +11 -11
    Risk
    93%Elevated
  • d855cb80Add ResearchClawBench benchmark
    Author
    black-yt
    When
    3mo ago
    Lines
    +6 -0
    Risk
    88%Elevated
  • 6b0add67Emphasize optimization traces in About and README intro, fix Nick Oak trace link
    Author
    Zhengyao Jiang
    When
    4mo ago
    Lines
    +3 -3
    Risk
    84%Elevated
  • e5906261Add Agon and AutoNumerics
    Author
    Zenbook
    When
    1mo ago
    Lines
    +2 -0
    Risk
    79%Elevated
  • 7b798f95Add peptide AI and Vesuvius Challenge ink detection use cases
    Author
    Zhengyao Jiang
    When
    5mo ago
    Lines
    +2 -0
    Risk
    79%Elevated
  • f549d12aAdd AutoZyme use case (bioinformatics software speedup)
    Author
    ElliotXie
    When
    2mo ago
    Lines
    +1 -0
    Risk
    63%Typical
  • d0fdade3Add vlasenkoalexey/tpu_performance_autoresearch_wiki use case (TPU model performance optimization)
    Author
    Aleksey Vlasenko
    When
    2mo ago
    Lines
    +1 -0
    Risk
    63%Typical
  • 937eea43Add CORAL to Implementations & Forks
    Author
    BobbyZhouZijian
    When
    4mo ago
    Lines
    +1 -0
    Risk
    63%Typical
  • 55a05287Add auto-agent to Implementations & Forks
    Author
    Alfonso Graziano
    When
    4mo ago
    Lines
    +1 -0
    Risk
    63%Typical
  • 3e392d26Add digivolve
    Author
    Mingde (Matthew) Zeng
    When
    4mo ago
    Lines
    +1 -0
    Risk
    63%Typical
  • ae4a7f51Add repo and gamed branch links to tennis XGBoost entry
    Author
    buildoak
    When
    5mo ago
    Lines
    +1 -1
    Risk
    63%Typical
  • 3be76580Add Bitcoin price formula discovery use case
    Author
    CBaquero
    When
    5mo ago
    Lines
    +1 -0
    Risk
    63%Typical
  • f89e5cfcTrim Agon description to house style
    Author
    Zhengyao Jiang
    When
    3w ago
    Lines
    +1 -1
    Risk
    27%Below typical
  • ae514749Add OpenAI Parameter Golf entry: Aiden #1 contributor in hiring challenge
    Author
    Zhengyao Jiang
    When
    4w ago
    Lines
    +1 -0
    Risk
    27%Below typical
  • 4142c94cAdd Autoresearch on autoresearch entry: AIDE2 self-improvement run
    Author
    Zhengyao Jiang
    When
    4w ago
    Lines
    +1 -0
    Risk
    27%Below typical
  • 00d3f3e3Add Flappy Bird game AI use case
    Author
    Zhengyao Jiang
    When
    1mo ago
    Lines
    +1 -0
    Risk
    27%Below typical
  • e9531f49Gloss MaxText as Google's reference repo of SOTA TPU-optimized models
    Author
    Aleksey Vlasenko
    When
    2mo ago
    Lines
    +1 -1
    Risk
    27%Below typical
  • 15f45afcAdd evo to Implementations & Forks
    Author
    Zhengyao Jiang
    When
    2mo ago
    Lines
    +1 -0
    Risk
    27%Below typical
  • b6a759d9Add FML-bench benchmark: controlled study of AI research agent search strategies
    Author
    Zhengyao Jiang
    When
    2mo ago
    Lines
    +1 -0
    Risk
    27%Below typical
  • ecfa3d14Add SimplexFold entry: Codex /goal autoresearch on AlphaFold2 architecture
    Author
    Zhengyao Jiang
    When
    3mo ago
    Lines
    +1 -0
    Risk
    27%Below typical
  • 4db49e96Update README.md
    Author
    Zhengyao Jiang
    When
    4mo ago
    Lines
    +1 -1
    Risk
    27%Below typical
  • 55eb1374Fix Peptide AI trace: link to tweet (not progress chart - it's a dashboard screenshot)
    Author
    Zhengyao Jiang
    When
    4mo ago
    Lines
    +1 -1
    Risk
    27%Below typical
  • 6778fdfdUpdate README.md
    Author
    Zhengyao Jiang
    When
    4mo ago
    Lines
    +1 -1
    Risk
    27%Below typical
  • c78d85f8Remove retweet link from Vesuvius entry
    Author
    Zhengyao Jiang
    When
    5mo ago
    Lines
    +1 -1
    Risk
    27%Below typical
  • 141ad85dAdd RL post-training optimization use case
    Author
    Zhengyao Jiang
    When
    5mo ago
    Lines
    +1 -0
    Risk
    27%Below typical
  • be5a07e2Remove Peptide AI entry: no proper optimization traces
    Author
    Zhengyao Jiang
    When
    4mo ago
    Lines
    +0 -1
    Risk
    2%Below typical
Showing 28 of 28 commits

How the score behaves here

Change risk →

Two views of the same model: where the cuts fall, and what commit shape lands you above them.

Score distribution

Every scored commit, binned on the raw 0 to 10 score rather than the percentile. Percentile ranks are uniform by construction, so that axis has no shape to draw. The dashed lines are the tercile cuts behind each row's priority pill.

020typical ↑elevated ↑0.04.38.5Change-risk score →
Below typical
Typical
Elevated

Size against diffusion

The 28 most recent commits, on their own recency sample rather than the feed above: that defaults to risk-sorted, so reusing it would plot only the top tercile and call it the spread. Big and scattered is what the model penalises. Click a dot to open it.

110100Lines changed (log) →0.01.0Diffusion →
Below typical14
Typical7
Elevated7

Commit history for 2233admin/awesome-autoresearchx

2233admin/awesome-autoresearchx has 37 commits in its history from 10 contributors, the first of them Mar 22, 2026. Every commit is scored for change risk from its size, spread and the history of the files it touches.