Agentic dev tool with long term memory based on a live semantic knowledge graph. Built with SemStreams.
active 2026-01-28 → 2026-07-06 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 160 days from 2026-01-28 to 2026-07-06. Pushes: 301 total, peak 14 in a day. Pull requests: 10 total, peak 2 in a day. Issues: 12 total, peak 4 in a day. Comments: 1 total, peak 1 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| cglusky | 324 | 301 | 10 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#295cglusky2026-06-24 23:39Recovery-triggered R2 re-review wedges at scenarios_reviewed when auto_approve=false (no-LLM testable)
- Issue#263cglusky2026-06-22 03:57Recovery (story_reprepare) returns plan to ready_for_execution but execution never re-dispatches — recovery-redispatch wedge
- Pull request#250cglusky2026-06-19 21:36
- Issue#32cglusky2026-06-19 20:59trajectory.Fetch nil-check misses typed-nil interfaces (class-of-bug magnet)
- Pull request#196cglusky2026-06-16 01:27
- Pull request#183cglusky2026-06-14 01:38
- Pull request#185cglusky2026-06-14 01:02
- Issue#182cglusky2026-06-13 23:09active-poll.sh: implementing-stage wedge-timer false-positives every 30min on hard runs (should be node-aware)
- Issue#180cglusky2026-06-13 23:09scenario-orchestrator: benign idempotency rejections on DAG-unlock logged at level=ERROR (should be Debug)
- Issue#179cglusky2026-06-13 23:09pkg/health: RepeatToolFailure emits false-positive critical alerts (empty evidence_id decode-fail; completed-node worktree-404)
- Issue#179cglusky2026-06-13 23:09pkg/health: RepeatToolFailure emits false-positive critical alerts (empty evidence_id decode-fail; completed-node worktree-404)
- Issue comment#165cglusky2026-06-13 13:13Debug logging volume: DEBUG=1 dumps full LLM payloads → ~2.2GB/run (log-bus volume + grep-poison); secret sweep clean
- Issue#153cglusky2026-06-11 12:24execution-manager: TaskExecution graph entity has two writers using two primitives (dirty-track incoherence)
- Pull request#142cglusky2026-06-09 22:47
- Pull request#133cglusky2026-06-07 23:25
- Issue#128cglusky2026-06-07 12:08feat(skills): add dependency coordinate resolver workflow
- Pull request#124cglusky2026-06-07 11:08
- Pull request#114cglusky2026-06-03 12:35
- Issue#91cglusky2026-06-03 03:06Bump max_requirement_retries to 3 for hard tiers + env-expand e2e-hybrid-gpt5.json timeouts
- Issue#36cglusky2026-05-31 12:53requirement-executor: resumeFromRecoveryLocked preserves RetryCount → recovery + fixable-retry budgets multiply (~$100/req worst case)
- Pull request#20cglusky2026-05-28 14:07
- Pull request#9cglusky2026-05-16 21:58
- Issue#1cglusky2026-02-22 13:51Observability gaps: missing LLM call tracking in trajectory system
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.