Skip to content

AI-native-Systems-Research/agentic-strategy-evolution

View on GitHub ↗Related repositories →

active 2026-04-012026-06-16 (UTC)

Complete coverage26,753 / 26,753 hourly files (100%) · 2 absent upstream2023-08-152026-09-02 (UTC)
Events
96
Pushes
43
Pull requests
2
Issues
26
Stars
1
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 77 days from 2026-04-01 to 2026-06-16. Pushes: 43 total, peak 8 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 26 total, peak 6 in a day. Comments: 10 total, peak 5 in a day. Stars: 1 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
sriumcp391214
mtoslalibu372804
Naima20023300
jgchn2011
claude[bot]1001

Recent activity

Latest issues, pull requests and releases

  • Issue#247sriumcp2026-06-01 13:06
    [F2] Methodology prompt: when target-repo docs conflict with campaign.yaml, campaign wins
  • Issue#236sriumcp2026-05-28 21:43
    `state.json` `phase` field lags artifact writes during execution
  • Issue#225sriumcp2026-05-27 12:47
    Tracking: methodology improvements (living tracker)
  • Issue#225sriumcp2026-05-27 12:47
    Tracking: methodology improvements (living tracker)
  • Issue#225sriumcp2026-05-27 12:47
    Tracking: methodology improvements (living tracker)
  • Issue#222sriumcp2026-05-27 12:45
    Bundle.experiment_spec.rehearsal_subset — structured rehearsal scope
  • Issue#213sriumcp2026-05-26 23:16
    Tracking: paper-burst friction-test rerun findings (post-#204)
  • Issue#215sriumcp2026-05-26 23:15
    meta_findings.json reports empty nous_asks despite retry_log signals on iteration failure
  • Issue#215sriumcp2026-05-26 23:15
    meta_findings.json reports empty nous_asks despite retry_log signals on iteration failure
  • Issue#203sriumcp2026-05-26 17:35
    Tracking: paper-burst friction-test findings (post-#189)
  • Issue comment#176sriumcp2026-05-26 00:56
    Tracking: integration gaps surfaced by sort_bench dry-run (3 children)
  • Issue#177sriumcp2026-05-26 00:56
    bug: best_found.json never written during real iteration — update_best_found not wired in
  • Issue#178sriumcp2026-05-26 00:56
    bug: deployment_recommendation silently falls back when best_found.json is missing
  • Pull request#180sriumcp2026-05-26 00:52
  • Issue#169sriumcp2026-05-25 14:24
    feat: engine no longer hard-stops on REFUTE — refutations become search constraints
  • Issue#159sriumcp2026-05-25 03:24
    feat: graded-complexity methodology — iter 1 simplest tier, escalate only on refutation
  • Issue comment#160sriumcp2026-05-25 03:24
    Tracking: Self-improving Nous — repo memory, parsimony, richer arms, meta-findings
  • Issue comment#157sriumcp2026-05-25 03:24
    feat: add H-dose-response arm — vary knob continuously to test response shape
  • Issue comment#143sriumcp2026-05-24 23:44
    feat: orphan-worktree GC at run start (#133, Phase A)
  • Issue#132sriumcp2026-05-22 12:54
    feat: explore-then-synthesize design phase via Explore subagents
  • Issue#125sriumcp2026-05-22 12:54
    feat: package Nous as a Claude Code plugin with skills and slash commands
  • Issue#125sriumcp2026-05-22 12:54
    feat: package Nous as a Claude Code plugin with skills and slash commands
  • Issue#125sriumcp2026-05-22 12:54
    feat: package Nous as a Claude Code plugin with skills and slash commands
  • Issue#120sriumcp2026-05-22 12:54
    Tracking: Claude-Code-native uplift for Nous (UX, quality, speed, token budget)
  • Issue#109mtoslalibu2026-05-20 21:18
    Context-aware retry: preserve intermediate work and continue on failure

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.