PydanticAI

Is anyone using PydanticAI?

799 packages depend on PydanticAI directly (deps.dev, 2026-10-19; niche median 171).

deps.dev weekly direct dependents of the system's own packages. A package counts when it is declared in the system's own tree, published under that name and not attributed by deps.dev to another repository. Partition dates can repeat across snapshots. Package linkage is not uniformly verified: packages with no repository metadata (no_link) are unverified and remain admitted.

Daily package dependents (unscored): 527; captured 2026-11-06; package: pypi/pydantic-ai. deps.dev REST count for one identity-verified pinned package, captured daily and never scored. Its package scope differs from the weekly package union; neither value replaces the other. 21,064 GitHub stars, recorded, not scored.

deps.dev · period 2026-10-19 · n = 29 partitions · method m5 own packages · updated 2026-11-07 · version 868e3c39d9c7-b1 · CSV

How does PydanticAI compare with its niche?

17 systems in Agent Frameworks; niche median 32.6 commits per week. The reader chooses the sort order.

Evidaxis snapshot · period 2026-11-07 · n = 17 systems · method medians of measured values · updated 2026-11-07 · version 868e3c39d9c7-b1 · CSV for this niche

What changed since the last snapshot?

3 published readings changed between snapshots d1eb0cec0f6a and 868e3c39d9c7.

Evidaxis snapshots · period 2026-10-31 to 2026-11-07 · n = 22 partitions · method paired snapshot values · updated 2026-11-07 · 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 2026-11-07 · 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.

• pydantic/pydantic-ai
• Project homepage

What is not measured for PydanticAI, and why

Missing readings describe instrument coverage. A missing value is not a measured 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 2026-11-07 · version 868e3c39d9c7-b1

Measurement detail

Gate, gauges, percentile, derived signals and snapshot receipt

History: 19 weekly observations; minimum 4. Axis coverage: 2 of 3 axes measurable. Gate: computed weekly across the cohort; no convergence event this week

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

PydanticAI

repo

Agent Frameworks · n = 17 · pydantic/pydantic-ai

2 of 3 axes measurable · conf medium

convergence gate

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

position in cohort distribution one of 17 in cohort

momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable

velocity z

log-slope +0.098/wk

citation z

∅no citation axis

Citation source: not measured.

direct-dependents z

Direct-dependents axis: measured.

cohort

17

systems measured

weekly commits

203.6

Development velocity axis: measured.

total citations

no reading

Citation source: not measured.

momentum

69.8

percentile p94

commit heatmap, last 26 weeks203.6/wk

citations by yearCitation source: not measured.

∅Citation source: not measured.

Daily dependents count (unscored) 527 dependents 470 direct, 62 indirect · pypi/pydantic-ai · deps.dev · the scored m5 axis uses weekly partitions

code-leads-citation lag reserved

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

axis alpha vs cohort reserved

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

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 · 2026-11-07 · m5

Direct-dependents momentum (deps.dev)

Direct-dependents axis: measured.

Coverage state

scored

Cohort z

+0.20

OLS slope

+0.024

Theil-Sen slope

+0.024

Latest direct dependents

799

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

Reconstructed history

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

Reconstructed weekly commits

Period	Commits
2025-w39	44
2025-w40	15
2025-w41	19
2025-w42	34
2025-w43	23
2025-w44	25
2025-w45	31
2025-w46	36
2025-w47	27
2025-w48	18
2025-w49	31
2025-w50	33
2025-w51	34
2025-w52	6
2026-w01	22
2026-w02	15
2026-w03	17
2026-w04	24
2026-w05	42
2026-w06	24
2026-w07	25
2026-w08	12
2026-w09	28
2026-w10	3
2026-w11	16
2026-w12	26
2026-w13	37
2026-w14	36
2026-w15	38
2026-w16	19
2026-w17	19
2026-w18	29
2026-w19	42
2026-w20	44
2026-w21	21
2026-w22	12
2026-w23	33
2026-w24	13
2026-w25	42
2026-w26	102
2026-w27	62
2026-w28	60
2026-w29	63
2026-w30	91
2026-w31	74
2026-w32	56
2026-w33	57
2026-w34	72
2026-w35	90
2026-w36	34
2026-w37	88

Peer signals

System	Momentum	Percentile
AgentScope	64.5	81
Agno	41.8	19
AutoGen	43.9	25
CAMEL	35.1	6
CrewAI	53.6	50
DSPy	53.8	56
Google ADK	55.2	69
LangGraph	49.1	38
Letta	45.2	31
Mastra	64.3	75
MetaGPT	65.3	88
Microsoft Agent Framework	72.1	100
OpenAI Agents SDK	50.1	44
PydanticAI	69.8	94
Qwen-Agent	37.6	12
smolagents	32.5	0
Strands Agents	54	62

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