Evidaxis
Dated record

Crush

product · Coding Agents, n = 20 · charmbracelet/crush · paper: not linked · as of

36.2 commits/week averaged over the trailing window (niche median 27.8). No paper is linked in OpenAlex. Dependents: no reading captured in the partition. 28,982 GitHub stars, recorded, not scored. Measured for Crush as of 2026-11-07; sources: GitHub, OpenAlex and deps.dev where linked.

commits/wk 36.2 averaged, trailing window niche median 27.8 (n = 20) last commit week 2026-11-01 measured · GitHub ·
citations no paper linked all years, indexed to date niche median 438 (n = 5) no reading · OpenAlex ·
direct dependents not captured this week weekly axis input; partition 2026-11-07 niche median 18 (n = 14) no reading · deps.dev snapshot ·
stars 28,982 recorded, not scored niche median 35,563 (n = 20) measured · GitHub ·

Is Crush still maintained?

Development velocity is the one measurable axis of three: 36.2 commits per week averaged over the trailing window (niche median 27.8/wk, n = 20).

GitHub averaged 36.2 per week over the trailing window; raw weekly counts below are individual weeks.

Last commit week 2026-11-01.

Commits in the latest captured week vs 4 weeks earlier: 19 · vs 26 weeks earlier: -25 · 52-week range: 10 to 131 commits in an individual week.

line chart: Crush, weekly commits, 31 in latest week vs niche median 11.5, 2025-11-09 to 2026-11-01
Crush averaged 36.2 commits a week, 1.3 times the niche median of 27.8. GitHub commit_activity · .
Latest eight weeks
Week startingCommitsNiche P25Niche P75
2026-09-13430108.5
2026-09-2033091.75
2026-09-2726081
2026-10-04120136.5
2026-10-11250100.75
2026-10-18380113.25
2026-10-2572095.75
2026-11-01310106.75
heatmap chart: Crush, weeks with commits, 26 of 26, 2026-05-10 to 2026-11-01
26 of the last 26 captured weeks had commits for Crush. GitHub commit_activity · .
All 52 weeks
Weekly commits
Week startingCommits
2025-11-0922
2025-11-1625
2025-11-2319
2025-11-3032
2025-12-0755
2025-12-14100
2025-12-2110
2025-12-2811
2026-01-0455
2026-01-1165
2026-01-1871
2026-01-2558
2026-02-0164
2026-02-0865
2026-02-1541
2026-02-2238
2026-03-0121
2026-03-0835
2026-03-1539
2026-03-2247
2026-03-2933
2026-04-0555
2026-04-1241
2026-04-1938
2026-04-2661
2026-05-0356
2026-05-1091
2026-05-1744
2026-05-2450
2026-05-3136
2026-06-0725
2026-06-1450
2026-06-2144
2026-06-2825
2026-07-0528
2026-07-12131
2026-07-1950
2026-07-2661
2026-08-0231
2026-08-0917
2026-08-1620
2026-08-2329
2026-08-3039
2026-09-0666
2026-09-1343
2026-09-2033
2026-09-2726
2026-10-0412
2026-10-1125
2026-10-1838
2026-10-2572
2026-11-0131

GitHub commit_activity · period 2025-11-09 to 2026-11-01 · n = 52 weeks · method weekly totals; reconstructed dates · updated · version 868e3c39d9c7-b1 · CSV

Readings

Recorded values and sources
ReadingValueΔ 4 weeksΔ 26 weeks52-week rangeInstrumentDateReproducePrevious reading
Commits per week36.20.6-5.931.6 to 53.4GitHub, trailing 12 weeks2026-11-07Public query31.2
Citing worksno readingno readingno readingno readingOpenAlex, all years2026-11-07Public queryno reading
Weekly direct dependentsno readingno readingno readingno readingWeekly direct dependents2026-11-07Public queryno reading
Daily package dependents (unscored)no readingno readingno readingno readingdeps.dev REST, unscorednot capturedPublic queryno reading
Stars28,982380no reading25,942 to 28,982GitHub stars, unscored2026-11-07Public query28,890

Evidaxis snapshot · period 2026-11-07 · n = 1 system · method source linked readings · updated · version 868e3c39d9c7-b1

How to cite Crush's record?

Evidaxis. Crush measurement record. Snapshot 2026-11-07. urn:evidaxis:claim:e_1TMQEKAN7S6:m5:2026-11-07. CC0-1.0. https://evidaxis.org/e/e_1TMQEKAN7S6/

Evidaxis · period 2026-11-07 · n = 1 system · method claim URN · updated · version 868e3c39d9c7-b1

How does Crush compare with its niche?

20 systems in Coding Agents; niche median 27.8 commits per week. The reader chooses the sort order.

dot plot chart: Crush, averaged commits per week, 36.2 vs niche median 27.8, 2026-11-07
Crush at 36.2 commits a week among 20 systems; niche median 27.8. GitHub, current cohort · .
All 20 systems, alphabetical; choose a heading to sort
Agentless0246no reading2,136
Aider0no reading1949,992
ChatDev0.4493no reading34,700
Cline62.8no reading2171,410
Codex CLI308.6no reading887133,492
Continue0no reading436,426
Crush36.2no readingno reading28,982
Gemini CLI19.4no reading70108,756
Goose48.2no reading256,314
Kilo Code378.1no reading1727,883
mini-swe-agent0.243899,236
Open Interpreter97.5no readingno reading68,821
OpenCode317.5no reading2,310225,077
OpenHands77.3154292,839
Qwen Code458.9no reading2229,057
SWE-agent0438no reading20,746
SWE-bench2.8no reading76,154
Tabby0no readingno reading33,922
Void0no reading73428,714
Zed126no reading1093,673

Evidaxis snapshot · period 2026-11-07 · n = 20 systems · method medians of measured values · updated · version 868e3c39d9c7-b1 · CSV for this niche

What changed since the last snapshot?

2 published readings changed between snapshots d1eb0cec0f6a and 868e3c39d9c7.

slope chart: Crush, changed published values, 2, 2026-10-31 to 2026-11-07
2 published values changed for Crush since 2026-10-31. Evidaxis snapshots · .
Snapshot values
MetricPreviousCurrentDelta
Commits per week31.236.25
Citing worksno readingno readingno reading
Weekly direct dependentsno readingno readingno reading
Stars28,89028,98292

Evidaxis snapshots · period 2026-10-31 to 2026-11-07 · n = 22 partitions · method paired snapshot values · updated · version 868e3c39d9c7-b1 · History CSV

Take the data or follow changes

Values and captured history are available under CC0-1.0. The system feed records changes to published numbers.

Evidaxis · period 2026-11-07 · n = 1 system · method CC0-1.0 open export · updated · version 868e3c39d9c7-b1

For teams tracking many systems

Use the cohort CSV, snapshot archive and membership manifest to reproduce observations across systems.

Cohort CSV · Snapshot archive · Membership manifest

Paper and links

Source records identify the system, repository and linked works; no paper authors are published.

What is not measured for Crush, and why

Missing readings describe instrument coverage. A missing value is not a measured zero.

Unmeasured slots
ReadingReason
Citing worksnot linked
Weekly direct dependentsno partition
Daily package dependents (unscored)no reading captured

Direct dependents: no reading captured in partition not captured; the value is missing, not zero.

Gate ETA: never published; Evidaxis makes no public actionable prediction.

Dependents ecosystem composition: no reading; this field is not present in the snapshot.

Evidaxis · period 2026-11-07 · n = 1 system · method measurement coverage · updated · version 868e3c39d9c7-b1

Measurement detail

Gate, gauges, percentile, derived signals and snapshot receipt

History: 19 weekly observations; minimum 4. Axis coverage: 1 of 3 axes measurable. Gate: not computable - 1 of 3 axes measurable

Gate: not computable - 1 of 3 axes measurable

Crush

product
Coding Agents · n = 20 · charmbracelet/crush
1 of 3 axes measurable · conf low
convergence gate
Convergence gate: Gate: not computable - 1 of 3 axes measurable Development velocity: measured × Citation momentum: not measurable ∅ Direct-dependents momentum (deps.dev): not measurable ∅
gate
0 of 3 axes

Gate: not computable - 1 of 3 axes measurable

· Evidaxis snapshot · 2026-11-07
Gate: not computable - 1 of 3 axes measurable
position in cohort distribution one of 20 in cohort
percentile 42 within cohort p25 p50 p75 p0 p100
percentile
p42
· Evidaxis snapshot · 2026-11-07
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z-0.12 within cohort, log-slope -0.018/wk.0-0.12
velocity z
-0.12 σ
slope
-0.018/wk
· Evidaxis snapshot · 2026-11-07
log-slope -0.018/wk
citation z Citation source: not measured.
direct-dependents z Direct-dependents axis: minimum of 14 usable points of the new quantity and 5 latest dependents not met.
cohort
20
systems measured
weekly commits
36.2
Development velocity axis: measured.
total citations
no reading
Citation source: not measured.
momentum
48.5
percentile p42
commit heatmap, last 26 weeks36.2/wk
weekly commits, 26 weeks26 weeks of commits, peak 131 in a week, 26 active weeks, 1117 total.week 1: 91 commitsweek 2: 44 commitsweek 3: 50 commitsweek 4: 36 commitsweek 5: 25 commitsweek 6: 50 commitsweek 7: 44 commitsweek 8: 25 commitsweek 9: 28 commitsweek 10: 131 commitsweek 11: 50 commitsweek 12: 61 commitsweek 13: 31 commitsweek 14: 17 commitsweek 15: 20 commitsweek 16: 29 commitsweek 17: 39 commitsweek 18: 66 commitsweek 19: 43 commitsweek 20: 33 commitsweek 21: 26 commitsweek 22: 12 commitsweek 23: 25 commitsweek 24: 38 commitsweek 25: 72 commitsweek 26: 31 commits
weeks
26
peak/wk
131
active
26
total
1117
· Evidaxis snapshot · 2026-11-07
citations by yearCitation source: not measured.
recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio +2.88, regime accelerating. prior slope +0.011, recent slope +0.031 per week. +0.011prior 39w+0.031recent 13w+2.88×
swing
+2.88×
regime
accelerating
windows
13w vs 39w
snapshot 1 of 1 · · m5
commit-axis Sharpe log-linear slope over residual std, value -0.002 with 95% CI -0.027 to +0.023, 50 degrees of freedom. CI spans zero.0-0.00295% CI -0.027, +0.023-0.027+0.023
sharpe
-0.002
95% ci
-0.027, +0.023
dof
50
snapshot 1 of 1 · · m5
commit changepoint52 weekly commit points. Changepoint at week 7 (2025-12-27), slope change -14.276 commits per week.2025-12-27
date
week
7 of 52
Δslope
-14.276/wk
snapshot 1 of 1 · · m5
code-leads-citation lag reserved

reserved: citation series too short / axis absent for cross-correlation

status
reserved
value
insufficient data
snapshot 1 of 1 · · m5
axis alpha vs cohort reserved

reserved: cohort N too small for regression (power ~0)

status
reserved
value
insufficient data
snapshot 1 of 1 · · m5
methodology gate snapshot 1 of 1 · · m5
commit weeks
52
citation years
0
shipped
3
reserved
3

shipped

  • recency-swing
  • commit-sharpe
  • commit-changepoint

reserved

  • code-leads-citation-lag
  • axis-alpha
  • gate-eta
snapshot 22 of 22 · · m5

Direct-dependents momentum (deps.dev)

Direct-dependents axis: minimum of 14 usable points of the new quantity and 5 latest dependents not met.

Coverage state
below_floor
Cohort z
no axis
OLS slope
no reading
Theil-Sen slope
no reading
Latest direct dependents
no reading
Confirmed-clean points
0
Reconstructed history points
no reading
As-of partition
no reading
Fragility veto
no reading
Rising vote
no

Source: deps.dev (Google), CC-BY 4.0. Modified: aggregated to system-level counts and momentum scores.

Axis definition · Snapshot axis correlations

Reconstructed history

Reconstructed from git history, not a point-in-time capture. This series is separate from captured observations.

sparkline chart: Crush, reconstructed commits, 2, 2025-w39 to 2026-w38
Crush has 2 reconstructed commits in the latest week; reconstructed niche median not measured. Git history reconstruction · .
Reconstructed weekly commits
PeriodCommits
2025-w3941
2025-w4019
2025-w4129
2025-w4269
2025-w4360
2025-w4443
2025-w4522
2025-w4625
2025-w4719
2025-w4832
2025-w4955
2025-w50100
2025-w5110
2025-w5211
2026-w0155
2026-w0265
2026-w0371
2026-w0458
2026-w0564
2026-w0665
2026-w0741
2026-w0838
2026-w0921
2026-w1035
2026-w1139
2026-w1247
2026-w1330
2026-w1455
2026-w1541
2026-w1638
2026-w1761
2026-w1856
2026-w1991
2026-w2044
2026-w2148
2026-w2236
2026-w2324
2026-w2450
2026-w2544
2026-w2625
2026-w2728
2026-w28130
2026-w2952
2026-w3059
2026-w3129
2026-w3217
2026-w3319
2026-w3428
2026-w3539
2026-w3663
2026-w3725
2026-w382
Peer signals
SystemMomentumPercentile
Agentless61.789
Aider44.237
ChatDev52.158
Cline4432
Codex CLI66.195
Continue38.15
Crush48.542
Gemini CLI49.447
Goose40.816
Kilo Code57.879
mini-swe-agent42.521
Open Interpreter11.40
OpenCode59.784
OpenHands50.353
Qwen Code81.3100
SWE-agent38.911
SWE-bench55.868
Tabby55.974
Void55.263
Zed42.726

Evidaxis · period 2026-11-07 · n = 1 system · method measurement detail · updated · version 868e3c39d9c7-b1 · record JSON · snapshot receipt