Evidaxis

PydanticAI

repo
Agent Frameworks · n = 17 · pydantic/pydantic-ai
Watch · conf low
momentum
momentum 78.9 of 100 78.9 /100
momentum
78.9/100
pctile
p94
convergence gate
Convergence gate: velocity only, citation axis absent ∅
gate
1 of 2 axes

velocity only, citation axis absent.

one axis passes
position in cohort distribution one of 17 in cohort
percentile 94 within cohort p25 p50 p75 p0 p100
percentile
p94
momentum is the combined velocity and citation signal, percentile within cohort
velocity z
velocity z gaugevelocity z+2.31 within cohort, log-slope +0.057/wk.0+2.31
velocity z
+2.31 σ
slope
+0.057/wk
log-slope +0.057/wk
convergence planefull gate = rising
PydanticAI on the convergence plane PydanticAI at velocity z +2.31 and citation z no axis, against 3 dual-axis cohort peers. single-axis: citation axis absent, excluded from the plane. z>=1 median velocity z → citation z ↑ CAMEL: velocity z -0.97, citation z +0.00 Letta: velocity z -3.04, citation z -0.67 MetaGPT: velocity z +0.48, citation z +1.33
velocity z
+2.31
citation z
no axis
peers
16

single-axis: citation axis absent, excluded from the plane.

citation z no citation axis
cohort
17
systems measured
weekly commits
51.4
rising trend
total citations
n/a
no axis
momentum
78.9
percentile p94
commit heatmap, last 26 weeks51.4/wk
weekly commits, 26 weeks26 weeks of commits, peak 102 in a week, 26 active weeks, 971 total.week 1: 24 commitsweek 2: 25 commitsweek 3: 12 commitsweek 4: 28 commitsweek 5: 3 commitsweek 6: 16 commitsweek 7: 26 commitsweek 8: 37 commitsweek 9: 36 commitsweek 10: 38 commitsweek 11: 19 commitsweek 12: 19 commitsweek 13: 29 commitsweek 14: 42 commitsweek 15: 44 commitsweek 16: 21 commitsweek 17: 12 commitsweek 18: 33 commitsweek 19: 13 commitsweek 20: 42 commitsweek 21: 102 commitsweek 22: 62 commitsweek 23: 60 commitsweek 24: 63 commitsweek 25: 91 commitsweek 26: 74 commits
weeks
26
peak/wk
102
active
26
total
971
citations by yearno axis
adoption 481 dependents 438 direct, 47 indirect · pypi/pydantic-ai · deps.dev · adoption signal, not part of the momentum score

PydanticAI holds an Evidaxis momentum score of 78.9 of 100 on methodology m2, snapshot 2026-08-08, measured within the Agent Frameworks cohort (n = 17). Its development-velocity axis is rising within the cohort while a second independent axis has not converged, so it sits below the two-axis gate.

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 -15.48, regime reversing. prior slope -0.007, recent slope +0.105 per week. -0.007prior 39w+0.105recent 13w-15.48×
swing
-15.48×
regime
reversing
windows
13w vs 39w
snapshot 1 of 1 · · m2
commit-axis Sharpe log-linear slope over residual std, value +0.018 with 95% CI -0.003 to +0.039, 50 degrees of freedom. CI spans zero.0+0.01895% CI -0.003, +0.039-0.003+0.039
sharpe
+0.018
95% ci
-0.003, +0.039
dof
50
snapshot 1 of 1 · · m2
commit changepoint52 weekly commit points. Changepoint at week 43 (2026-06-06), slope change +7.544 commits per week.2026-06-06
date
week
43 of 52
Δslope
+7.544/wk
snapshot 1 of 1 · · m2
code-leads-citation lag reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m2
axis alpha vs cohort reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m2
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m2
methodology gate snapshot 1 of 1 · · m2
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 · · m2

Adoption trend

PydanticAI dependents over time5 points, range 452 to 483 dependents.
min
452 dependents
max
483 dependents
latest
481 dependents
points
5

Downstream packages depending on pypi/pydantic-ai (deps.dev), captured point-in-time each snapshot. An adoption signal, not part of the momentum score.

Verdict

PydanticAI is rising on development velocity, but a second independent axis has not yet converged. It is on watch.

Path to Rising: needs a second measurable axis to exist (no academic paper is currently tracked).

Sources

pydantic/pydantic-ai development-velocity axis

Embed this badge

Evidaxis watch, PydanticAI
[![Evidaxis: PydanticAI](https://evidaxis.org/badge/e_2CS7SM2993J/2026-w32.svg)](https://evidaxis.org/e/e_2CS7SM2993J)

Others in Agent Frameworks

AgentScope Agent Frameworks
Watch
88
p100
vel +3.02 cit no axis
axis dials
+3.02 n/a
Agno Agent Frameworks
Single-axis
48
p44
vel -0.20 cit no axis
axis dials
-0.20 n/a
AutoGen Agent Frameworks
Calibration
51
p50
vel +0.05 cit no axis
axis dials
+0.05 n/a
CAMEL Agent Frameworks
Tracked
44
p25
vel -0.97 cit +0.00
axis dials
-0.97 +0.00
CrewAI Agent Frameworks
Single-axis
55
p62
vel +0.43 cit no axis
axis dials
+0.43 n/a
DSPy Agent Frameworks
Single-axis
47
p38
vel -0.26 cit no axis
axis dials
-0.26 n/a

Full Agent Frameworks cohort →

entity_id e_2CS7SM2993J methodology m2 snapshot 035a72a81e59 period 2026-w32 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m2, never edited by hand. Cite as: “Evidaxis, PydanticAI, entity e_2CS7SM2993J, snapshot 2026-w32.”

Durable reference (format-independent): urn:evidaxis:claim:e_2CS7SM2993J:m2:2026-08-08