As of 2026-10-10: AutoGen (Agent Frameworks) is under weekly measurement. Axis coverage: 2 of 3 axes measurable. Gate: not computable — reference measurement

AutoGen

Name: Evidaxis measurement: AutoGen
Published: 2026-10-10
License: https://creativecommons.org/publicdomain/zero/1.0/

repo reference measurement

Agent Frameworks · n = 16 · microsoft/autogen

2 of 3 axes measurable · conf medium

convergence gate

gate: 0 of 3 axes

Gate: not computable — reference measurement

position in cohort distribution one of 16 in cohort

percentile: p40

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

velocity z

velocity z: +0.07 σ
slope: +0.000/wk

log-slope +0.000/wk

citation z

∅no citation axis

Citation source: not measured.

direct-dependents z

direct-dependents z: -0.83 σ
slope: +0.011/point

Direct-dependents axis: measured.

cohort

systems measured

weekly commits

Development velocity axis: measured.

total citations

n/a

Citation source: not measured.

momentum

45.2

percentile p40

commit heatmap, last 26 weeks0/wk

weeks: 26
peak/wk: 0
active: 0
total: 0

citations by yearCitation source: not measured.

∅Citation source: not measured.

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.

swing: +0.00×
regime: recent slope below prior window
windows: 13w vs 39w

snapshot 1 of 1 · 2026-10-10 · m4

commit Sharpereserved: <26 non-zero commit weeks

date: 2026-03-28
week: 24 of 52
Δslope: -0.026/wk

snapshot 1 of 1 · 2026-10-10 · m4

code-leads-citation lag reserved

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

status: reserved
value: insufficient data

snapshot 1 of 1 · 2026-10-10 · m4

axis alpha vs cohort reserved

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

status: reserved
value: insufficient data

snapshot 1 of 1 · 2026-10-10 · m4

gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status: reserved
value: insufficient history

snapshot 1 of 1 · 2026-10-10 · m4

methodology gate snapshot 1 of 1 · 2026-10-10 · m4

commit weeks: 52
citation years: 0
shipped: 2
reserved: 4

shipped

recency-swing
commit-changepoint

reserved

commit-sharpe
code-leads-citation-lag
axis-alpha
gate-eta

snapshot 1 of 1 · 2026-10-10 · m4

Reconstructed history

min: 1 commits/wk
max: 8 commits/wk
latest: 1 commits/wk
points: 4

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

AutoGen is under weekly measurement. History: 14 weekly observations; minimum 4. Development velocity axis: measured. Citation source: not measured. Direct-dependents axis: measured. Gate: not computable — reference measurement

Sources

microsoft/autogen development-velocity axis

microsoft.github.io/autogen homepage

Others in Agent Frameworks

AgentScope Agent Frameworks

2 of 3 axes measurable

p100

vel +2.38 cit no axis deps +0.79

axis dials

n/a

CAMEL Agent Frameworks

3 of 3 axes measurable

p27

vel -1.78 cit +0.00 deps -0.05

axis dials

CrewAI Agent Frameworks

2 of 3 axes measurable

p53

vel -0.79 cit no axis deps +0.49

axis dials

n/a

DSPy Agent Frameworks

2 of 3 axes measurable

p33

vel -0.28 cit no axis deps -0.67

axis dials

n/a

Google ADK Agent Frameworks

2 of 3 axes measurable

p67

vel +0.67 cit no axis deps +0.00

axis dials

n/a

LangGraph Agent Frameworks

1 of 3 axes measurable

vel -1.62 cit no axis deps no axis

axis dials

n/a n/a

Full Agent Frameworks cohort →

Direct-dependents momentum (deps.dev)

Direct-dependents axis: measured.

Coverage state: scored
Cohort z: -0.83
OLS slope: +0.011
Theil-Sen slope: +0.010
Latest direct dependents: 151
Confirmed-clean points: 26
Reconstructed history points: 15
As-of partition: 2026-09-28
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. m4 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

Cite this measurement

Plain citation

Evidaxis. AutoGen measurement record. Snapshot 2026-10-10. https://evidaxis.org/e/e_EDX1R1KVT3X/ Concept DOI: 10.5281/zenodo.21076011.

BibTeX

@dataset{evidaxis_e_EDX1R1KVT3X_20261010,
  title = {AutoGen measurement record},
  publisher = {Evidaxis},
  year = {2026},
  url = {https://evidaxis.org/e/e_EDX1R1KVT3X/},
  doi = {10.5281/zenodo.21076011}
}

Download record (JSON)

entity_id e_EDX1R1KVT3X methodology m4 snapshot ad5e404d4f82 period 2026-w41 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m4, never edited by hand. Cite as: “Evidaxis, AutoGen, entity e_EDX1R1KVT3X, snapshot 2026-w41.”

Durable reference (format-independent): urn:evidaxis:claim:e_EDX1R1KVT3X:m4:2026-10-10