Evidaxis

hermes-agent

repo
Unassigned (AI-v1 census) · n = 10 · NousResearch/hermes-agent
Watch · conf low
momentum
momentum 96.5 of 100 96.5 /100
momentum
96.5/100
pctile
p100
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 10 in cohort
percentile 100 within cohort p25 p50 p75 p0 p100
percentile
p100
momentum is the combined velocity and citation signal, percentile within cohort
velocity z
velocity z gaugevelocity z+3.72 within cohort, log-slope +0.080/wk.0+3.72
velocity z
+3.72 σ
slope
+0.080/wk
log-slope +0.080/wk
convergence planefull gate = rising
hermes-agent on the convergence plane hermes-agent at velocity z +3.72 and citation z no axis, against 0 dual-axis cohort peers. single-axis: citation axis absent, excluded from the plane. z>=1 median velocity z → citation z ↑
velocity z
+3.72
citation z
no axis
peers
9

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

citation z no citation axis
cohort
10
systems measured
weekly commits
1066.8
rising trend
total citations
n/a
no axis
momentum
96.5
percentile p100
commit heatmap, last 26 weeks1066.8/wk
weekly commits, 26 weeks26 weeks of commits, peak 1837 in a week, 26 active weeks, 21784 total.week 1: 20 commitsweek 2: 112 commitsweek 3: 266 commitsweek 4: 434 commitsweek 5: 920 commitsweek 6: 664 commitsweek 7: 456 commitsweek 8: 490 commitsweek 9: 863 commitsweek 10: 983 commitsweek 11: 1075 commitsweek 12: 1071 commitsweek 13: 795 commitsweek 14: 834 commitsweek 15: 799 commitsweek 16: 768 commitsweek 17: 949 commitsweek 18: 908 commitsweek 19: 792 commitsweek 20: 1066 commitsweek 21: 1248 commitsweek 22: 867 commitsweek 23: 1163 commitsweek 24: 1628 commitsweek 25: 1837 commitsweek 26: 776 commits
weeks
26
peak/wk
1837
active
26
total
21784
citations by yearno axis

hermes-agent holds an Evidaxis momentum score of 96.5 of 100 on methodology m2, snapshot 2026-08-08, measured within the Unassigned (AI-v1 census) cohort (n = 10). 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 +0.21, regime decelerating. prior slope +0.202, recent slope +0.042 per week. +0.202prior 39w+0.042recent 13w+0.21×
swing
+0.21×
regime
decelerating
windows
13w vs 39w
snapshot 1 of 1 · · m2
commit-axis Sharpe log-linear slope over residual std, value +0.125 with 95% CI +0.074 to +0.176, 50 degrees of freedom. CI excludes zero.0+0.12595% CI +0.074, +0.176+0.074+0.176
sharpe
+0.125
95% ci
+0.074, +0.176
dof
50
snapshot 1 of 1 · · m2
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 · · 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

Verdict

hermes-agent 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

NousResearch/hermes-agent development-velocity axis

Embed this badge

Evidaxis watch, hermes-agent
[![Evidaxis: hermes-agent](https://evidaxis.org/badge/e_TEXN6TK2CRK/2026-w32.svg)](https://evidaxis.org/e/e_TEXN6TK2CRK)

Others in Unassigned (AI-v1 census)

ECC Unassigned (AI-v1 census)
Single-axis
23
p0
vel -2.14 cit no axis
axis dials
-2.14 n/a
firecrawl Unassigned (AI-v1 census)
Single-axis
57
p67
vel +0.53 cit no axis
axis dials
+0.53 n/a
graphify Unassigned (AI-v1 census)
Watch
69
p89
vel +1.51 cit no axis
axis dials
+1.51 n/a
langchain Unassigned (AI-v1 census)
Single-axis
40
p11
vel -0.83 cit no axis
axis dials
-0.83 n/a
langflow Unassigned (AI-v1 census)
Single-axis
44
p33
vel -0.49 cit no axis
axis dials
-0.49 n/a
stable-diffusion-webui Unassigned (AI-v1 census)
Single-axis
49
p44
vel -0.11 cit no axis
axis dials
-0.11 n/a

Full Unassigned (AI-v1 census) cohort →

entity_id e_TEXN6TK2CRK 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, hermes-agent, entity e_TEXN6TK2CRK, snapshot 2026-w32.”

Durable reference (format-independent): urn:evidaxis:claim:e_TEXN6TK2CRK:m2:2026-08-08