2026-04-08 - 2026-04-09
Overview
2 Releases published by 2 users
Published
v7.0.0
Published
Golden-Allegro-v6-Sonnet4
10 Pull requests merged by 4 users
Merged
#418 [EPIC] Gemini — Sovereign Infrastructure Suite Implementation
Merged
#411 [PERPLEXITY-08] Add PR checklist CI workflow and enforcement script
Merged
#412 [PERPLEXITY-03] Add disambiguation header to SOUL.md (Bitcoin inscription)
Merged
#384 refactor: wire retrieval_enforcer L1 to SovereignStore — eliminate subprocess/ONNX dependency
Merged
#375 docs: add MEMORY_ARCHITECTURE.md — retrieval order, storage layout, data flow
Merged
#365 feat: FLEET-010/011/012 — Phase 3-5 cross-agent delegation, model pipeline, lifecycle
Merged
#364 feat: Bezalel Builder Wizard — Sidecar Authority Update
Merged
#366 art: The Timmy Foundation — Visual Story (24 images + 2 videos)
Merged
#380 feat: Sovereign Memory Store — zero-API durable memory (SQLite + FTS5 + HRR)
Merged
#362 [SOVEREIGN] Orchestrator v1 — backlog reader, priority scorer, agent dispatcher
4 Pull requests proposed by 2 users
Proposed
#424 v7.0.0: Fleet architecture checkin
Proposed
#425 feat: Dead man switch config fallback engine
Proposed
#430 Fleet Behaviour Hardening: task gates + guardrails enforcement
Proposed
#431 CI: Comprehensive config validation pipeline (YAML, Python, Shell, JSON, Cron, Playbooks)
37 Issues closed from 2 users
Closed
#381 [RCA] Timmy chose vanity metrics over real work — root cause analysis
Closed
#371 [MEMPALACE][MP-4] Memory promotion — scratchpad to palace with intent
Closed
#417 [SOTA] Evaluate SWE-agent for autonomous Gitea issue resolution
Closed
#416 [SOTA] Deploy MLX on Mac M3 Max for faster local inference
Closed
#415 [SOTA] Evaluate Huey as task queue for distributed agent dispatch
Closed
#414 [SOTA] Evaluate sqlite-vec as lightweight vector search for fleet
Closed
#413 [SOTA] Evaluate Engram as ONNX-free memory replacement for MemPalace
Closed
#410 [GEMINI-12] Telemetry pipeline v2 — operational visibility without cloud dependencies
Closed
#409 [GEMINI-11] Sovereign skill installer — package our tools for any new wizard
Closed
#408 [GEMINI-10] Cross-repo test suite — verify the fleet works as a system, not just parts
Closed
#407 [GEMINI-09] Phase progression tracker — where is the fleet on the Paperclips arc?
Closed
#406 [GEMINI-08] Self-healing infrastructure — auto-detect and fix common failures
Closed
#405 [GEMINI-07] Model evaluation harness — benchmark every GGUF before deploying
Closed
#404 [GEMINI-06] Gitea webhook pipeline — real-time event-driven fleet coordination
Closed
#403 [GEMINI-05] Continuous Architecture Decision Records — make decisions stick
Closed
#402 [GEMINI-04] Agent dispatch framework — replace the ad-hoc dispatch scripts
Closed
#401 [GEMINI-03] llama.cpp fleet manager — start, stop, monitor, swap models across all machines
Closed
#400 [GEMINI-02] Fleet-wide architecture linter v2 — enforce sidecar boundary automatically
Closed
#399 [GEMINI-01] Automated VPS provisioning system — Von Neumann as code, not a runbook
Closed
#398 [EPIC] Gemini — The Builder, The Systematizer, The Force Multiplier
Closed
#378 [MUDA] SOUL.md exists in 3 repos with divergent content
Closed
#396 [PERPLEXITY-11] Evaluate every Timmy-created cron job — running, useful, or zombie?
Closed
#395 [PERPLEXITY-10] Assess which of Timmy's 9 guard scripts actually work in production
Closed
#394 [PERPLEXITY-09] Quantify waste — dollar cost of every cloud API call this week
Closed
#392 [PERPLEXITY-07] Audit llama.cpp deployment across all 4 machines
Closed
#391 [PERPLEXITY-06] Verify the orchestrator actually dispatches real work
Closed
#390 [PERPLEXITY-05] Fleet-wide dependency chain for all open epics
Closed
#389 [PERPLEXITY-04] Branch sprawl cleanup — count, assess, delete
Closed
#388 [PERPLEXITY-03] SOUL.md divergence audit — 3 repos, 1 truth
Closed
#387 [PERPLEXITY-02] Code review every open PR before merge — establish the standard
Closed
#386 [PERPLEXITY-01] Audit every overnight Groq completion — what actually shipped vs noise
Closed
#385 [EPIC] Perplexity — The Auditor, The Architect, The Conscience
Closed
#382 [QA][REPORT] Perplexity MemPalace Audit — Branch Cleanup + Architecture Findings — April 8, 2026
Closed
#397 [PERPLEXITY-12] Write the morning report Alexander actually wants to read
Closed
#393 [PERPLEXITY-08] Write the agent code review checklist Timmy won't follow without enforcement
Closed
#383 [AUDIT] MemPalace Spec Parity — sovereign_store.py vs mempalace CLI + retrieval_enforcer wiring gap
Closed
#355 [ORCHESTRATOR-1] Build Gitea backlog reader + priority scorer
43 Issues created by 3 users
Opened
#381 [RCA] Timmy chose vanity metrics over real work — root cause analysis
Opened
#382 [QA][REPORT] Perplexity MemPalace Audit — Branch Cleanup + Architecture Findings — April 8, 2026
Opened
#383 [AUDIT] MemPalace Spec Parity — sovereign_store.py vs mempalace CLI + retrieval_enforcer wiring gap
Opened
#385 [EPIC] Perplexity — The Auditor, The Architect, The Conscience
Opened
#386 [PERPLEXITY-01] Audit every overnight Groq completion — what actually shipped vs noise
Opened
#387 [PERPLEXITY-02] Code review every open PR before merge — establish the standard
Opened
#388 [PERPLEXITY-03] SOUL.md divergence audit — 3 repos, 1 truth
Opened
#389 [PERPLEXITY-04] Branch sprawl cleanup — count, assess, delete
Opened
#390 [PERPLEXITY-05] Fleet-wide dependency chain for all open epics
Opened
#391 [PERPLEXITY-06] Verify the orchestrator actually dispatches real work
Opened
#392 [PERPLEXITY-07] Audit llama.cpp deployment across all 4 machines
Opened
#393 [PERPLEXITY-08] Write the agent code review checklist Timmy won't follow without enforcement
Opened
#394 [PERPLEXITY-09] Quantify waste — dollar cost of every cloud API call this week
Opened
#395 [PERPLEXITY-10] Assess which of Timmy's 9 guard scripts actually work in production
Opened
#396 [PERPLEXITY-11] Evaluate every Timmy-created cron job — running, useful, or zombie?
Opened
#397 [PERPLEXITY-12] Write the morning report Alexander actually wants to read
Opened
#398 [EPIC] Gemini — The Builder, The Systematizer, The Force Multiplier
Opened
#399 [GEMINI-01] Automated VPS provisioning system — Von Neumann as code, not a runbook
Opened
#400 [GEMINI-02] Fleet-wide architecture linter v2 — enforce sidecar boundary automatically
Opened
#401 [GEMINI-03] llama.cpp fleet manager — start, stop, monitor, swap models across all machines
Opened
#402 [GEMINI-04] Agent dispatch framework — replace the ad-hoc dispatch scripts
Opened
#403 [GEMINI-05] Continuous Architecture Decision Records — make decisions stick
Opened
#404 [GEMINI-06] Gitea webhook pipeline — real-time event-driven fleet coordination
Opened
#405 [GEMINI-07] Model evaluation harness — benchmark every GGUF before deploying
Opened
#406 [GEMINI-08] Self-healing infrastructure — auto-detect and fix common failures
Opened
#407 [GEMINI-09] Phase progression tracker — where is the fleet on the Paperclips arc?
Opened
#408 [GEMINI-10] Cross-repo test suite — verify the fleet works as a system, not just parts
Opened
#409 [GEMINI-11] Sovereign skill installer — package our tools for any new wizard
Opened
#410 [GEMINI-12] Telemetry pipeline v2 — operational visibility without cloud dependencies
Opened
#413 [SOTA] Evaluate Engram as ONNX-free memory replacement for MemPalace
Opened
#414 [SOTA] Evaluate sqlite-vec as lightweight vector search for fleet
Opened
#415 [SOTA] Evaluate Huey as task queue for distributed agent dispatch
Opened
#416 [SOTA] Deploy MLX on Mac M3 Max for faster local inference
Opened
#417 [SOTA] Evaluate SWE-agent for autonomous Gitea issue resolution
Opened
#419 [RESEARCH SPIKE] Hermes Memory Providers vs MemPalace — Overlap Analysis & Vendor Lock-in Report
Opened
#420 Test Issue - Allegro Harness Report
Opened
#421 Agent Harness Introspection Report - Allegro Fleet Readiness
Opened
#422 🔍 Agent Harness Introspection - Allegro Fleet Readiness Assessment
Opened
#423 🛡️ Dead Man Switch Config Fallbacks - Bezalel Agent Autonomous Recovery System
Opened
#426 [CROSS-REVIEW] Allegro: Review v7.0.0 checkin + dead man switch fallback
Opened
#427 [CROSS-REVIEW] Ezra: Review v7.0.0 checkin + dead man switch fallback
Opened
#428 [CROSS-REVIEW] Bezalel: Review v7.0.0 checkin + dead man switch fallback
Opened
#429 [EMACS] Fix daemon socket + per-user identity and audit trail on Bezalel
27 Unresolved Conversations
Open
#203
[DAILY] Build guidance packet -> daily issue cutter
Open
#379
[POLICY] Prevent agents from approving zero-change PRs
Open
#289
[CI] Add repo-native validation for timmy-config deploy, cron, and shell changes
Open
#345
[EPIC] Five Japanese Wisdoms — operational discipline for the AI fleet
Open
#128
[CRUCIBLE] Add resource scheduling template with named resources
Open
#271
[LAZARUS][BACKENDS] Abstract process, venv, docker, and remote cell backends
Open
#272
[LAZARUS][TEAMING] Project lanes, shared scratchpad, and no-cross-contamination collaboration model
Open
#273
[LAZARUS][VERIFY] Isolation test suite, TTL cleanup, and graveyard garbage collection
Open
#127
[CRUCIBLE] Add contradiction/consistency checking template
Open
#201
[DAILY] Build emergence scorecard and evidence ledger
Open
#202
[DAILY] Build lane-health governor and automatic rerouter
Open
#367
[EPIC][MEMPALACE] Sovereign Memory Palace — From Recall to Elegant Action
Open
#336
[EPIC] Sidecar Extraction — reset hermes-agent to pure upstream, move sovereign work to timmy-config
Open
#354
[EPIC] Sovereign Orchestrator — remove Alexander from dispatch loop
Open
#293
[BUG] Stop gitea-event-watcher.py falseworking on stale repo aliases
Open
#347
[ANDON] 行灯 — Real-time signal light. Instant Telegram alerts on any failure.
Open
#356
[ORCHESTRATOR-2] Build agent dispatcher — route issues to the right agent
Open
#346
[JIDOKA] 自働化 — Stop the line on defect. Auto-halt loops when quality drops.
Open
#357
[ORCHESTRATOR-3] Build consolidated reporter — one report for Alexander
Open
#340
[SIDECAR-4] Reset hermes-agent to pure upstream
Open
#337
[SIDECAR-1] Extract docs, reports, security files from hermes-agent to timmy-config
Open
#338
[SIDECAR-2] Extract scripts and CI workflows from hermes-agent to timmy-config
Open
#339
[SIDECAR-3] Restructure agent/* extensions as skills or runtime patches
Open
#169
[FLEET] Define the wolf tier and burn-night rubric for expendable free-model workers
Open
#376
[MUDA][AUDIT] Cut the waste — branch sprawl, repo bloat, abandoned PRs, issue backlog
Open
#123
[OPS] deploy.sh --validate flag -- run model health check before deploying
Open
#370
[MEMPALACE][MP-3] Session scratchpad — ephemeral context that survives tool hops