Evidaxis

Strands Agents

repo
Agent Frameworks · n = 17 · strands-agents/harness-sdk
2 of 3 axes measurable · conf medium
convergence gate
Convergence gate: Gate: computed weekly across the cohort; no convergence event this week Development velocity: measured × Citation momentum: not measurable ∅ Direct-dependents momentum (deps.dev): measured ×
gate
0 of 3 axes

Gate: computed weekly across the cohort; no convergence event this week

Gate: computed weekly across the cohort; no convergence event this week
position in cohort distribution one of 17 in cohort
percentile 62 within cohort p25 p50 p75 p0 p100
percentile
p62
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z+0.10 within cohort, log-slope +0.022/wk.0+0.10
velocity z
+0.10 σ
slope
+0.022/wk
log-slope +0.022/wk
citation z Citation source: not measured.
direct-dependents z
direct-dependents z gaugedirect-dependents z+0.54 within cohort, log-slope +0.032/point.0+0.54
direct-dependents z
+0.54 σ
slope
+0.032/point
Direct-dependents axis: measured.
cohort
17
systems measured
weekly commits
66.4
Development velocity axis: measured.
total citations
n/a
Citation source: not measured.
momentum
54.0
percentile p62
commit heatmap, last 26 weeks66.4/wk
weekly commits, 26 weeks26 weeks of commits, peak 110 in a week, 26 active weeks, 1552 total.week 1: 46 commitsweek 2: 26 commitsweek 3: 41 commitsweek 4: 36 commitsweek 5: 69 commitsweek 6: 81 commitsweek 7: 83 commitsweek 8: 34 commitsweek 9: 75 commitsweek 10: 43 commitsweek 11: 58 commitsweek 12: 36 commitsweek 13: 58 commitsweek 14: 69 commitsweek 15: 48 commitsweek 16: 63 commitsweek 17: 60 commitsweek 18: 40 commitsweek 19: 35 commitsweek 20: 81 commitsweek 21: 73 commitsweek 22: 64 commitsweek 23: 68 commitsweek 24: 110 commitsweek 25: 89 commitsweek 26: 66 commits
weeks
26
peak/wk
110
active
26
total
1552
citations by yearCitation source: not measured.

Strands Agents holds an Evidaxis momentum score of 54.0 of 100 on methodology m5, snapshot 2026-11-07, measured within the Agent Frameworks cohort (n = 17). Axis coverage: 2 of 3 axes measurable. Gate: computed weekly across the cohort; no convergence event this week

Derived signals

second-order reads, computed from the published series

Three signals ship when the commit series is statistically sufficient; the rest are held in a reserved state until the data supports them. A reserved signal shows its reason, never a fabricated number. How these are computed.

recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio +2.11, regime accelerating. prior slope +0.018, recent slope +0.038 per week. +0.018prior 39w+0.038recent 13w+2.11×
swing
+2.11×
regime
accelerating
windows
13w vs 39w
snapshot 1 of 1 · · m5
commit-axis Sharpe log-linear slope over residual std, value +0.053 with 95% CI +0.032 to +0.074, 50 degrees of freedom. CI excludes zero.0+0.05395% CI +0.032, +0.074+0.032+0.074
sharpe
+0.053
95% ci
+0.032, +0.074
dof
50
snapshot 1 of 1 · · m5
commit changepoint52 weekly commit points. Changepoint at week 50 (2026-10-24), slope change -22.742 commits per week.2026-10-24
date
week
50 of 52
Δslope
-22.742/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
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
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 1 of 1 · · m5

Reconstructed history

Strands Agents reconstructed weekly commits51 points, range 16 to 83 commits/wk.
min
16 commits/wk
max
83 commits/wk
latest
35 commits/wk
points
51

Weekly commits over the past year, reconstructed from git history (GitHub commit_activity). This is reconstructed, not a point-in-time capture. Evidaxis captures the Type-2 signals (watchers, issues, dependents) live and never backfills them; those are the moat.

Measurement states

Strands Agents is under weekly measurement. History: 19 weekly observations; minimum 4. Development velocity axis: measured. Citation source: not measured. Direct-dependents axis: measured. Gate: computed weekly across the cohort; no convergence event this week

Sources

strands-agents/harness-sdk development-velocity axis

Others in Agent Frameworks

AgentScope Agent Frameworks
2 of 3 axes measurable
65
p81
vel +1.46 cit no axis deps +0.86
axis dials
+1.46 n/a +0.86
Agno Agent Frameworks
2 of 3 axes measurable
42
p19
vel -0.64 cit no axis deps -0.67
axis dials
-0.64 n/a -0.67
AutoGen Agent Frameworks
2 of 3 axes measurable
44
p25
vel -0.18 cit no axis deps -0.79
axis dials
-0.18 n/a -0.79
CAMEL Agent Frameworks
3 of 3 axes measurable
35
p6
vel -3.05 cit -0.67 deps +0.15
axis dials
-3.05 -0.67 +0.15
CrewAI Agent Frameworks
2 of 3 axes measurable
54
p50
vel +0.07 cit no axis deps +0.51
axis dials
+0.07 n/a +0.51
DSPy Agent Frameworks
2 of 3 axes measurable
54
p56
vel +1.28 cit no axis deps -0.68
axis dials
+1.28 n/a -0.68

Full Agent Frameworks cohort →

Direct-dependents momentum (deps.dev)

Direct-dependents axis: measured.

Coverage state
scored
Cohort z
+0.54
OLS slope
+0.032
Theil-Sen slope
+0.033
Latest direct dependents
210
Confirmed-clean points
29
Reconstructed history points
15
As-of partition
2026-10-19
Fragility veto
inactive
Rising vote
no

This axis measures the trajectory of a system's own packages: declared in its own tree, published under that name, and not attributed by deps.dev to another repository. A package with no repository link is unverified and stays. The self-name exclusion list is fixed at the v2h.1 panel. Systems with no admitted package are not measured on this axis. Points that cannot be derived exactly are withheld, and the series restarts after a withheld point.

The earliest weekly points of each series were read from deps.dev's BigQuery history on 2026-07-21; later points are weekly captures. m5 does not replay those partitions: each point is the stored system total, one package's unique_direct, or a complete sketch union, and a point that is not exact is withheld. Each record reports how many of its points are reconstructed history.

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

Axis definition · Snapshot axis correlations

entity_id e_3K17NV4B0JF methodology m5 snapshot 868e3c39d9c7 period 2026-w45 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m5, never edited by hand. Cite as: “Evidaxis, Strands Agents, entity e_3K17NV4B0JF, snapshot 2026-w45.”

Durable reference (format-independent): urn:evidaxis:claim:e_3K17NV4B0JF:m5:2026-11-07