Evidaxis
Dated record

OpenAI Agents SDK

repo · Agent Frameworks, n = 17 · openai/openai-agents-python · paper: not linked · as of

59.6 commits/week averaged over the trailing window (niche median 21.5). No paper is linked in OpenAlex. deps.dev: 352 direct dependents. 29,709 GitHub stars, recorded, not scored. Measured for OpenAI Agents SDK as of 2026-09-26; sources: GitHub, OpenAlex and deps.dev where linked.

commits/wk 59.6 averaged, trailing window niche median 21.5 (n = 17) last commit week 2026-09-20 measured · GitHub ·
citations no paper linked all years, indexed to date niche median 60 (n = 5) no reading · OpenAlex ·
direct dependents 352 partition 2026-09-07 niche median 151 (n = 17) measured · deps.dev snapshot ·
stars 29,709 recorded, not scored niche median 29,503 (n = 17) measured · GitHub ·

Is OpenAI Agents SDK still maintained?

59.6 commits per week averaged over the trailing window (niche median 21.5/wk, n = 17).

GitHub averaged 59.6 per week over the trailing window; raw weekly counts below are individual weeks.

Last commit week 2026-09-20.

Commits in the latest captured week vs 4 weeks earlier: 52 · vs 26 weeks earlier: 59 · 52-week range: 0 to 143 commits in an individual week.

line chart: OpenAI Agents SDK, weekly commits, 91 in latest week vs niche median 12, 2025-09-28 to 2026-09-20
OpenAI Agents SDK averaged 59.6 commits a week, 2.8 times the niche median of 21.5. GitHub commit_activity · .
Latest eight weeks
Week startingCommitsNiche P25Niche P75
2026-08-02143058
2026-08-0991166
2026-08-1671271
2026-08-2339139
2026-08-3012060
2026-09-0636240
2026-09-1331037
2026-09-2091186
heatmap chart: OpenAI Agents SDK, weeks with commits, 26 of 26, 2026-03-29 to 2026-09-20
26 of the last 26 captured weeks had commits for OpenAI Agents SDK. GitHub commit_activity · .
All 52 weeks
Weekly commits
Week startingCommits
2025-09-2810
2025-10-057
2025-10-1220
2025-10-1925
2025-10-267
2025-11-0210
2025-11-094
2025-11-1616
2025-11-231
2025-11-3012
2025-12-076
2025-12-1417
2025-12-216
2025-12-280
2026-01-0421
2026-01-1136
2026-01-1841
2026-01-2513
2026-02-0138
2026-02-0842
2026-02-1515
2026-02-2222
2026-03-0155
2026-03-0828
2026-03-1540
2026-03-2232
2026-03-2912
2026-04-0511
2026-04-1229
2026-04-1934
2026-04-2632
2026-05-03105
2026-05-1050
2026-05-1714
2026-05-247
2026-05-318
2026-06-078
2026-06-149
2026-06-2127
2026-06-2819
2026-07-0555
2026-07-1228
2026-07-1943
2026-07-2675
2026-08-02143
2026-08-0991
2026-08-1671
2026-08-2339
2026-08-3012
2026-09-0636
2026-09-1331
2026-09-2091

GitHub commit_activity · period 2025-09-28 to 2026-09-20 · n = 52 weeks · method weekly totals; reconstructed dates · updated · version 9d2fe956adbc-b1 · CSV

Readings

Recorded values and sources
ReadingValueΔ 4 weeksΔ 26 weeks52-week rangeInstrumentDateReproducePrevious reading
Commits per week59.68.927.710.3 to 59.6GitHub, trailing 12 weeks2026-09-26Public query53.5
Citing worksno readingno readingno readingno readingOpenAlex, all years2026-09-26Public queryno reading
Direct dependents352no readingno reading347 to 352Direct dependents2026-09-07Public query347
Daily dependents (unscored)no readingno readingno readingno readingdeps.dev REST, unscored2026-09-26Public queryno reading
Stars29,709656no reading27,554 to 29,709GitHub stars, unscored2026-09-26Public query29,558

Evidaxis snapshot · period 2026-09-26 · n = 1 system · method source linked readings · updated · version 9d2fe956adbc-b1

How to cite OpenAI Agents SDK's record?

Evidaxis. OpenAI Agents SDK measurement record. Snapshot 2026-09-26. urn:evidaxis:claim:e_3HZS2JPM2CR:m3:2026-09-26. CC0-1.0. https://evidaxis.org/e/e_3HZS2JPM2CR/

Evidaxis · period 2026-09-26 · n = 1 system · method claim URN · updated · version 9d2fe956adbc-b1

Is anyone using OpenAI Agents SDK?

352 packages depend on OpenAI Agents SDK directly (deps.dev, 2026-09-07; niche median 151).

sparkline chart: OpenAI Agents SDK, direct dependents, 352 vs niche median 151, 2026-08-31 to 2026-09-07
352 direct dependents on deps.dev for OpenAI Agents SDK; niche median 151. deps.dev weekly package union · .
Weekly dependents
PartitionDirect dependentsWeekly pointsMethod
2026-09-0735223m3 package union

Daily dependents (unscored): no reading. 29,709 GitHub stars, recorded, not scored.

deps.dev · period 2026-09-07 · n = 23 partitions · method m3 package union · updated · version 9d2fe956adbc-b1 · CSV

How does OpenAI Agents SDK compare with its niche?

17 systems in Agent Frameworks; niche median 21.5 commits per week. The reader chooses the sort order.

dot plot chart: OpenAI Agents SDK, averaged commits per week, 59.6 vs niche median 21.5, 2026-09-26
OpenAI Agents SDK at 59.6 commits a week among 17 systems; niche median 21.5. GitHub, current cohort · .
All 17 systems, alphabetical; choose a heading to sort
AgentScope21.593032,410
Agno28no reading11142,351
AutoGen0no reading15161,178
CAMEL5.21021417,776
CrewAI24.2no reading34259,063
DSPy13.56016638,344
Google ADK106.2no reading21821,651
LangGraph8.2no reading1,73942,326
Letta0.6581324,896
Mastra422.2no reading41628,346
MetaGPT01531170,633
Microsoft Agent Framework68.8no reading2113,814
OpenAI Agents SDK59.6no reading35229,709
PydanticAI98no reading72420,195
Qwen-Agent0no reading817,128
smolagents0.7no reading9529,503
Strands Agents55.5no reading2068,453

Evidaxis snapshot · period 2026-09-26 · n = 17 systems · method medians of measured values · updated · version 9d2fe956adbc-b1 · CSV for this niche

What changed since the last snapshot?

3 published readings changed between snapshots fcfd3a7ccdcb and 9d2fe956adbc.

slope chart: OpenAI Agents SDK, changed published values, 3, 2026-09-19 to 2026-09-26
3 published values changed for OpenAI Agents SDK since 2026-09-19. Evidaxis snapshots · .
Snapshot values
MetricPreviousCurrentDelta
Commits per week53.559.66.1
Citing worksno readingno readingno reading
Direct dependents3473525
Stars29,55829,709151

Evidaxis snapshots · period 2026-09-19 to 2026-09-26 · n = 14 partitions · method paired snapshot values · updated · version 9d2fe956adbc-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 2026-09-26 · n = 1 system · method CC0-1.0 open export · updated · version 9d2fe956adbc-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 OpenAI Agents SDK, and why

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

Unmeasured slots
ReadingReason
Citing worksnot linked
Daily dependents (unscored)no reading captured

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 2026-09-26 · n = 1 system · method measurement coverage · updated · version 9d2fe956adbc-b1

Measurement detail

Gate, gauges, percentile, derived signals and snapshot receipt

History: 11 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

OpenAI Agents SDK

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

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

· Evidaxis snapshot · 2026-09-26
Gate: computed weekly across the cohort; no convergence event this week
position in cohort distribution one of 17 in cohort
percentile 69 within cohort p25 p50 p75 p0 p100
percentile
p69
· Evidaxis snapshot · 2026-09-26
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z+1.34 within cohort, log-slope +0.044/wk.0+1.34
velocity z
+1.34 σ
slope
+0.044/wk
· Evidaxis snapshot · 2026-09-26
log-slope +0.044/wk
citation z Citation source: not measured.
direct-dependents z
direct-dependents z gaugedirect-dependents z-0.23 within cohort, log-slope +0.019/point.0-0.23
direct-dependents z
-0.23 σ
slope
+0.019/point
· Evidaxis snapshot · 2026-09-26
Direct-dependents axis: measured.
cohort
17
systems measured
weekly commits
59.6
Development velocity axis: measured.
total citations
no reading
Citation source: not measured.
momentum
57.0
percentile p69
commit heatmap, last 26 weeks59.6/wk
weekly commits, 26 weeks26 weeks of commits, peak 143 in a week, 26 active weeks, 1080 total.week 1: 12 commitsweek 2: 11 commitsweek 3: 29 commitsweek 4: 34 commitsweek 5: 32 commitsweek 6: 105 commitsweek 7: 50 commitsweek 8: 14 commitsweek 9: 7 commitsweek 10: 8 commitsweek 11: 8 commitsweek 12: 9 commitsweek 13: 27 commitsweek 14: 19 commitsweek 15: 55 commitsweek 16: 28 commitsweek 17: 43 commitsweek 18: 75 commitsweek 19: 143 commitsweek 20: 91 commitsweek 21: 71 commitsweek 22: 39 commitsweek 23: 12 commitsweek 24: 36 commitsweek 25: 31 commitsweek 26: 91 commits
weeks
26
peak/wk
143
active
26
total
1080
· Evidaxis snapshot · 2026-09-26
citations by yearCitation source: not measured.
recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio +0.37, regime recent slope below prior window. prior slope +0.025, recent slope +0.009 per week. +0.025prior 39w+0.009recent 13w+0.37×
swing
+0.37×
regime
recent slope below prior window
windows
13w vs 39w
snapshot 1 of 1 · · m3
commit-axis Sharpe log-linear slope over residual std, value +0.040 with 95% CI +0.015 to +0.066, 50 degrees of freedom. CI excludes zero.0+0.04095% CI +0.015, +0.066+0.015+0.066
sharpe
+0.040
95% ci
+0.015, +0.066
dof
50
snapshot 1 of 1 · · m3
commit changepoint52 weekly commit points. No significant changepoint detected (|delta slope| within the noise floor).no significant changepoint
changepoint
none detected
snapshot 1 of 1 · · m3
code-leads-citation lag reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m3
axis alpha vs cohort reserved

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

status
reserved
value
insufficient data
snapshot 1 of 1 · · m3
methodology gate snapshot 1 of 1 · · m3
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 14 of 14 · · m3

Direct-dependents momentum (deps.dev)

Direct-dependents axis: measured.

Coverage state
scored
Cohort z
-0.23
OLS slope
+0.019
Theil-Sen slope
+0.019
Latest direct dependents
352
Confirmed-clean points
23
Reconstructed history points
15
As-of partition
2026-09-07
Fragility veto
inactive
Rising vote
no

This axis measures the frozen-panel trajectory of the package set selected and linkage-verified as of 2026-07-21. Systems outside that panel are not measured on this axis. Residual survivorship beyond the frozen universe is disclosed, not denied.

The earliest weekly points of each series were read from deps.dev's BigQuery history on 2026-07-21; later points are weekly captures. 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.

sparkline chart: OpenAI Agents SDK, reconstructed commits, 19, 2025-w39 to 2026-w38
OpenAI Agents SDK has 19 reconstructed commits in the latest week; reconstructed niche median not measured. Git history reconstruction · .
Reconstructed weekly commits
PeriodCommits
2025-w3910
2025-w407
2025-w4120
2025-w4225
2025-w437
2025-w4410
2025-w454
2025-w4616
2025-w471
2025-w4812
2025-w496
2025-w5017
2025-w516
2026-w0121
2026-w0236
2026-w0341
2026-w0413
2026-w0538
2026-w0642
2026-w0715
2026-w0822
2026-w0955
2026-w1028
2026-w1140
2026-w1232
2026-w1312
2026-w1411
2026-w1529
2026-w1634
2026-w1732
2026-w18105
2026-w1950
2026-w2014
2026-w217
2026-w228
2026-w238
2026-w249
2026-w2527
2026-w2619
2026-w2755
2026-w2828
2026-w2943
2026-w3075
2026-w31143
2026-w3291
2026-w3371
2026-w3439
2026-w3512
2026-w3636
2026-w3731
2026-w3819
Peer signals
SystemMomentumPercentile
AgentScope79.8100
Agno45.625
AutoGen47.931
CAMEL50.638
CrewAI54.350
DSPy54.962
Google ADK61.781
LangGraph40.812
Letta40.50
Mastra57.375
MetaGPT53.844
Microsoft Agent Framework70.594
OpenAI Agents SDK5769
PydanticAI62.188
Qwen-Agent43.919
smolagents40.76
Strands Agents54.656

Evidaxis · period 2026-09-26 · n = 1 system · method measurement detail · updated · version 9d2fe956adbc-b1 · record JSON · snapshot receipt