𓇳

Building Pantheon
in Public

A transparent record of how we design, build, test, break, and fix our software. From Anubis to a unified platform — no cherry-picking, the mistakes stay in.

819+ Tests Passing
24 Modules
85.7% Avg Coverage
12 Deities
↓ Scroll to see the journey

What is Pantheon

Unified DevOps Intelligence

One Install. All Deities.

Sirsi Pantheon is a unified DevOps intelligence platform. It brings together infrastructure hygiene, QA/QC governance, and persistent AI knowledge into a single, lightweight binary. Install once — get every deity.

𓂀 Anubis is the foundational module — the reason Pantheon exists. Weigh. Judge. Purify. It scans, judges, and purges waste across workstations with 58 rules, ghost app detection, file dedup that's 27× faster than naive hashing, and a policy engine for fleet enforcement.

𓆄 Ma'at governs quality — test coverage thresholds, canon document verification, and CI pipeline monitoring. 57 tests across 3 governance domains.

𓁟 Thoth gives AI assistants persistent memory — 98.7% less code to read per session, $4.08 saved per conversation.

Built in Go. Released under the MIT license. Runs entirely on your device — no data ever leaves your machine.

Our Philosophy

We looked inside the binary and found the truth: all 20 modules compile to 186 KB. That's 1.5% of the binary. The other 98.5% is Go's runtime, paid once. Adding a new deity costs 2–30 KB. Pantheon isn't a rename — it's a recognition that the architecture was already unified.
— Sirsi Engineering

The Data Behind the Decision

Why Pantheon: Binary Size Tells the Story

When we analyzed exactly what's inside the binary, we discovered something remarkable. All 20 deity modules — 13,813 lines of application code — compile to just 186 KB. That's 1.5% of the 12 MB binary.

186 KB
All Sirsi code compiled
20 modules, 18 commands
8.3 MB
Stripped binary size
98.5% is Go runtime
2–30 KB
Cost per new deity
Nearly free to add modules
1
Binary to install
All deities included
12 MB
Full binary (unstripped)
With debug symbols
~10 MB
Go runtime overhead
Paid once, shared by all

The insight: The Go runtime taxes every binary ~10 MB regardless of what's inside. Once you pay that cost, each additional module is nearly free. Doubling the module count would add ~100 KB. The binary already was a unified platform — calling it "Anubis" was limiting what it actually is.

Anubis isn't being demoted. It's the foundational module — the reason Pantheon exists. Every scan rule, every safety protection, every feature started with Anubis. Pantheon is what happens when one deity proves the architecture works and the others join in.

All sizes measured via go tool nm -size and ls -lh on darwin/arm64, March 2026.

The Build Timeline

Every sprint, every problem, every solution — documented as it happened.

March 20, 2026 — Day 0

Genesis

The idea started with a 3-hour manual cleanup of a Mac that recovered 47 GB of wasted space. Virtual machines, old AI models, dead app leftovers — all hiding in plain sight. "Why am I doing this by hand?"

3commits
0tests
~400lines
March 20 — Days 1–2

Core Scanner

Built the scan engine with 58 rules across 7 categories — developer tools, AI models, virtual machines, IDEs, cloud services, storage, and general waste. Added ghost hunting: finding leftovers from apps you already uninstalled.

🐛 CI broke twice. We specified a Go version that doesn't exist and used a deprecated linter plugin. Both fixed same day.
15commits
45tests
~5,000lines
March 21 — Days 5–7

Intelligence Layer

Added the smart features: a neural file classifier that understands what files are (not just their extension), an AI IDE integration so coding assistants can use Anubis, and a policy engine for teams to enforce hygiene standards.

8commits
72tests
~12,000lines
March 21 — Day 8

Duplicate Finder

Built the file deduplication engine — finds duplicate files across your Mac. Started with a simple approach that read every file completely. During testing, the folder picker didn't work at all.

🐛 The visual folder picker returned unusable paths. Browsers can't give apps access to real file locations (it's a security feature). Clicking "Choose Folders" did nothing.
Replaced the browser-based picker with a native macOS Finder dialog. Now it opens the real folder chooser you're familiar with.
5commits
84tests
~14,500lines
March 21–22 — Audit Cycle

Performance & Safety Audit

Deep review of every component. The insight: "measure twice, cut once" — read just the beginning and end of each file instead of the whole thing. This made scanning 27 times faster.

Added trash-first deletion — files always go to your Mac's Trash (you can "Put Back"), with a complete audit log of every action.

🐛 Found a safety bug: the "move to trash" function wasn't verifying file paths correctly. If path resolution failed, it could move the wrong file. Fixed immediately.
7commits
303tests
6bugs fixed
March 22 — Latest

Thoth Knowledge System

Built Thoth — a system that gives AI coding assistants persistent memory. Instead of re-reading thousands of lines of code every conversation (expensive and slow), the AI reads a compact summary. 98% less wasted computation.

Named after the Egyptian god of knowledge. Free and open source — works with any project, any language.

5commits
4projects using it
98%context saved
March 24 — Session 16b

The Coverage Sprint

Hit the "90% weighted average" wall. Realized we couldn't test signal handling or root kills without actually killing real processes. Introduced the Interface Injection Standard (Rule A16) and established the Antigravity IPC Bridge.

Now we can verify Safety Design 100% deterministically. If a root-kill fails, we know exactly how Pantheon reacts, without ever risking the host system.

12commits
768tests
90.1%coverage
Wrote tests for 7 modules in a single session: ignore rules, scan registry, profiles, stealth cleanup, hardware detection, network discovery, and Launch Services.

Found along the way: an ARP parsing edge case where macOS "incomplete" entries could confuse the IP extractor, a comment-count mismatch in the rule registry, and confirmed that every default profile includes the "general" scan category (good product design).

94new tests
15/17modules tested
453total tests
March 22 — Latest

Launch Preparation

Verified all platform builds with GoReleaser snapshot — 12 binaries across macOS, Linux, and Windows (both Intel and ARM). All within size budget. Updated launch copy, investor demo script, and all public-facing stats.

12binaries verified
~8 MBmain binary
6platforms
March 23 — Session 12

Launch Execution + Dogfooding Discovery

Released v0.4.0-alpha with Homebrew tap integration — brew tap SirsiMaster/tools && brew install sirsi-pantheon. GoReleaser auto-publishes the formula to homebrew-tools/Formula/ on every tagged release.

During release execution, discovered that Ma'at's pre-push hook took 55 seconds per push — running full test coverage across all 17 packages even when only 1-2 files changed. After 4 pushes (3 min 40 sec of waiting), implemented diff-based coverage.

🐛 .gitignore pattern pantheon was silently ignoring cmd/pantheon/seba.go (matching any path containing "pantheon"). CI builds were failing since the Seba rebrand. Fix: anchor with /pantheon to match root-level binary only.
Ma'at diff-based coverage: 55s → 36ms (1,500× speedup). Only tests packages with changed files. Unchanged packages use cached coverage.
3,667×Ma'at speedup
18.7×Weigh speedup
8ADRs
81Feather Weight
March 25 — Sessions 18–18c

Performance Optimization

IDE click latency hit 400ms+. Diagnosed to LSP processes (gopls, TypeScript) consuming P-core CPU time. Built Sekhmet renice — deprioritizes LSPs to Background QoS via pantheon guard --renice lsp. Protected language_server_macos_arm from accidental slay. Implemented scoped Horus indexing (856K→50K files).

Click latency eliminated. IDE Renderer regained P-core access. Horus memory reduced by releasing index after use.
8commits
0msclick lag
856K→50Kindexed files
March 25 — Session 19

VS Code Extension

Built the Pantheon VS Code Extension — 5 TypeScript modules replacing the JS scaffold. Always-on Guardian (auto-renice every 60s), Ankh status bar (live RAM/CPU from ps every 5s), 7 Command Palette entries, and Thoth context compression from .thoth/memory.yaml.

5TS modules
7commands
ADR-012accepted
March 25 — Session 20

The Deployment Sprint

Deployed the Deity Registry to Firebase Hosting at sirsi-pantheon.web.app. Wired custom domain pantheon.sirsi.ai via Firebase Hosting API + GoDaddy CNAME. Rebuilt the registry index with click-to-flip 3D cards showing developer info on the back.

15pages deployed
12deity cards
SSLauto-provisioned

Current Status

Real numbers. No inflation.

Reliability

Automated tests819+ passing
Test suites23 of 24
Avg coverage85.7%
Untested modules1 (display-only)
Race conditions0 found
Code warnings0

Safety

Protected locations29 hardcoded
Deletion methodTrash first
Action audit logEvery action
Data sent off-deviceNever
Auto-deleteDisabled

Platform

macOSFull support
Apple SiliconNative
Intel MacSupported
Linux~60%
Windows~40%

Performance

Measured on a real folder with 709 files. Not a synthetic test.

Scan speed (dedup)27.3× faster
Before: 84 ms per batchAfter: 3 ms per batch
Weigh scan (Horus cached)18.7× faster
Before: 15.6 secondsAfter: 833 milliseconds
Ka ghost detection (Horus wired)7.8× faster
Before: 8.5 secondsAfter: 1.08 seconds
Disk reads — less is better for your SSD98.8% less
Before: 97.8 MB readAfter: <2 MB read
Accuracy — duplicates correctly identified100%
25 duplicate groups foundSame result, 27× faster

How it works: instead of reading entire files (which can be gigabytes), we read just the first and last 4 KB. If those 8 KB match, then — and only then — do we read the full file. Most non-duplicates are eliminated instantly.

Case Study · We Eat Our Own Dog Food

𓁟 How Thoth Changed Our Development Process

We built Thoth because our own AI sessions kept failing. Then we measured the difference.

98.7%
less code to read per session
23,177 lines → 300 lines
$4.12
saved per session
274,524 tokens saved per session
136%
more context for actual work
139.0% of window → 1.8%
150
tests in one session
enabled by context preservation
10s
time to productive
vs 3–5 min without Thoth
5
projects using Thoth
deployed across all Sirsi repos
Context window consumed at startup98.7% reduction
Without Thoth: 139.0% (doesn't fit!)With Thoth: 1.8%
Cost per session startup98.8% less
Without Thoth: $4.17With Thoth: $0.05

The problem: Without Thoth, our 23,177-line codebase consumed 139% of the AI's context window just to read at startup. The source code literally didn't fit. The AI had to read selectively, creating blind spots that caused hallucinated function names, duplicated code, and missed safety rules.

The result: Thoth compresses project knowledge into 300 lines of curated facts. The AI starts productive in 10 seconds instead of 3–5 minutes, with 137% more context available for real work. In our best session, we wrote 150 tests and made 11 commits — impossible without context preservation.

All metrics from real development sessions, verified via wc -l and git log. Read the full case study →

Dogfooding · Process Improvement Before Release

🪶 Ma'at: 55 Seconds Was Destroying Productivity

We found a product-killing performance bug by using our own tool. Fixed it in the same session.

36ms
coverage check (diff mode)
was 55 seconds
1,536×
speedup
diff mode vs full scan
~5s
total pre-push gate
was ~65 seconds
Ma'at governance check (diff mode)1,536× faster
Before: 55.3 secondsAfter: 36 milliseconds
Pre-push gate — complete flow~32× faster
Before: ~65 secondsAfter: ~2 seconds

The discovery: During v0.4.0-alpha release execution, every git push triggered Ma'at, which ran go test -cover ./... across all 17+ packages. After 4 pushes (3 min 40 sec of waiting), the insight landed: a governance tool that destroys productivity is worse than no governance at all.

The fix: Diff-based coverage. Ma'at now uses git diff to detect which packages have changed .go files and only tests those. Unchanged packages use cached coverage from ~/.config/pantheon/maat/coverage-cache.json. Same verdicts, same accuracy — 1,500× faster.

The lesson: Most teams discover performance issues after users complain. Pantheon found and fixed this during internal development — a direct benefit of building in public and eating our own dog food.

Measured on Apple M1 Max, macOS Tahoe. All numbers independently verifiable. Read the full case study →

Architecture · Every Deity Wins If One Deity Wins

👁️ Horus: Walk the Filesystem Once, Query Forever

Three deities were independently walking the same directories. Now they share one index.

833ms
Weigh scan (cached)
was 15.6 seconds — 18.7× faster
541ns
per directory query
O(1) hash lookup
1 walk
feeds all deities
was 3 independent walks

The recursive win: Horus indexes the filesystem once with parallel goroutines → Jackal queries the index in 5ms instead of walking for 15s → Ka queries in 1s instead of walking for 8.5s → faster pre-push gate → more pushes per session → more dogfooding → more performance discoveries → better product. The improvements compound. Every deity wins if one deity wins.

Phase 2 coming: macOS FSEvents, Linux fanotify, and Windows USN Journal will make the index incremental — tracking only what changed since the last scan. Target: 200–500ms for any deity.

Read the full Horus case study → | ADR-008 →

Dogfooding · Product Thesis Validated

🐕 The Docker Ghost: 64 GB Hidden in Plain Sight

While analyzing Weigh output, we discovered that 97.6% of all detected waste was one unused application.

64 GB
Docker Desktop (unused)
VM images + cached layers
1.6 GB
actual dev artifacts
after cleanup
833ms
to discover it
pantheon weigh

The recursive insight: Ma'at was slow → fixed it → enabled more pushes → discovered Weigh was slow → fixed Weigh → analyzed output → found 64 GB Docker ghost → removed it. The performance work enabled the disk discovery that validated the entire product.

This is exactly what Pantheon is built to do: surface hidden waste in 833ms, give actionable context (rule name, path, size), and let the user decide. The founder didn't know Docker was consuming 64 GB until Pantheon told him.

Read the full case study →

What We're Still Working On

We'd rather tell you what isn't ready than let you discover it.

Cleaner module needs deeper test coverageIn Progress
Windows support is incompletePlanned
No automatic update mechanism yetPlanned
Visual app still being polishedIn Progress
Structured logging implemented (Go 1.21 slog)Done

Part of the Sirsi Ecosystem

One Platform, All Deities

Pantheon is the unified DevOps intelligence platform from Sirsi Technologies. Every deity maintains its identity while sharing a single runtime and a single install.

Anubis (infrastructure hygiene), Ma'at (QA/QC governance), Thoth (persistent knowledge) — and future deities in any language. The architecture proved itself: adding a module costs 2–30 KB. The platform is ready.

Explore SirsiNexus Anubis→Ra Roadmap →