Skip to content

active 2026-05-162026-07-06 (UTC)

Complete coverage26,449 / 26,449 hourly files (100%) · 2 absent upstream2023-08-152026-08-21 (UTC)
Events
107
Pushes
48
Pull requests
1
Issues
38
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 52 days from 2026-05-16 to 2026-07-06. Pushes: 48 total, peak 9 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 38 total, peak 17 in a day. Comments: 9 total, peak 3 in a day. Stars: 0 total, peak 0 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
sbeardsley954818
gemini-code-assist[bot]2001

Recent activity

Latest issues, pull requests and releases

  • Issue#144sbeardsley2026-06-24 23:43
    Cross-language parity: port PlanExecute budget-resume fix (cfffa40) to TS/Python/Go
  • Issue#162sbeardsley2026-06-24 20:13
    Cross-language parity: relax plan phase to free-text/markdown plans (SC-28) (TS/Python/Go)
  • Issue#156sbeardsley2026-06-24 19:19
    Port SC-BUG-1 (HITL resume re-enters composed SelfVerifying/PlanExecute frames) to TypeScript / Python / Go
  • Issue#142sbeardsley2026-06-12 22:58
    Project-scoped durable storage: stable project_id so task_list survives Ralph window resets and process restarts
  • Issue#124sbeardsley2026-06-07 11:09
    feat(harness): per-variant RunStrategy::run implementations — recursive executor (Composable Execution A.1/A.6, largest unit)
  • Issue#120sbeardsley2026-06-07 01:55
    feat(harness): ExecutionRegistry replaces single-collaborator HarnessConfig fields + custom-strategy registry (Composable Execution A.3)
  • Issue#120sbeardsley2026-06-07 01:55
    feat(harness): ExecutionRegistry replaces single-collaborator HarnessConfig fields + custom-strategy registry (Composable Execution A.3)
  • Issue comment#118sbeardsley2026-06-06 23:34
    feat(tasklist): Task.blockers field + task_list add_task blockers param (Composable Execution Part C schema)
  • Issue comment#117sbeardsley2026-06-06 20:25
    feat(harness): BudgetPolicy + BudgetExhaustedBehavior serializable types (Composable Execution Part B)
  • Issue#122sbeardsley2026-06-06 18:58
    feat(harness): max_steps() advisory worst-case turn bound (Composable Execution B.8)
  • Issue#122sbeardsley2026-06-06 18:58
    feat(harness): max_steps() advisory worst-case turn bound (Composable Execution B.8)
  • Issue#120sbeardsley2026-06-06 18:58
    feat(harness): ExecutionRegistry replaces single-collaborator HarnessConfig fields + custom-strategy registry (Composable Execution A.3)
  • Issue#120sbeardsley2026-06-06 18:58
    feat(harness): ExecutionRegistry replaces single-collaborator HarnessConfig fields + custom-strategy registry (Composable Execution A.3)
  • Issue comment#101sbeardsley2026-06-06 08:46
    example: 12-cordyceps — fully autonomous task-completion agent (capstone)
  • Issue#98sbeardsley2026-06-03 23:25
    example: 09-self-verifying — quality loop as harness strategy
  • Issue#82sbeardsley2026-05-30 01:27
    MemoryTool — scope-aware memory tool (deferred from #81)
  • Issue comment#82sbeardsley2026-05-30 01:27
    MemoryTool — scope-aware memory tool (deferred from #81)
  • Issue comment#72sbeardsley2026-05-29 02:59
    Parse an accepted plan artifact into the task list across all four languages
  • Issue#70sbeardsley2026-05-28 21:26
    Plan phase: generate a plan artifact (one-shot planning turn) across all four languages
  • Issue#26sbeardsley2026-05-28 18:04
    Discussion: Evaluation Harness and Tight Feedback Loop
  • Issue#60sbeardsley2026-05-27 13:28
    Implement HillClimbing loop strategy (iterative optimization) across all four languages
  • Issue#55sbeardsley2026-05-27 12:42
    Wire StandardContextManager into the harness compaction seam (production adapter)
  • Pull request#56sbeardsley2026-05-27 12:42
  • Issue comment#33sbeardsley2026-05-27 01:54
    Fix: ObservabilityProvider needs local outbox for durable trace buffering
  • Issue#34sbeardsley2026-05-27 01:51
    Fix: Mode::Yolo and SandboxProvider::None require a dangerous feature flag

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.