Logbook

Decisions, lessons, blockers and open questions

The record behind the numbers: what was decided and why, what went wrong and what it taught, what's blocked, and what's still undecided. Every entry traces to Falkor's own records.

The featured story

The rewrite that rebuilt Falkor

In July I had two AI models design a replacement for Falkor from scratch. It never shipped. Its best parts rebuilt Falkor instead.

  1. Decision

    Commission a clean-sheet rival

    The question was whether a clean start would beat Falkor. Two frontier AI models each designed a complete successor from scratch, and I judged them head to head. The winner, AURYN, came as a build-ready package of 20 documents and 35 screens: a Rust core, a “morning paper” interface, and three hard rules aimed at Falkor's worst defects. Stale data can't show green, one referee owns the GPU, and an action isn't done until a check proves it.

    Competition records

  2. Decision

    Stalled, audited, frozen

    Coding ran in phases through July. When I authorized the next phase on 1 August, it stalled within a day in a resource wait loop behind a safety lock. On 9 August an independent audit of the demo found every screen a shell: 0 of 13 user journeys worked, none of 6,303 acceptance checks had been worked through, the source no longer built, and the only runnable binary carried a false release identity. Falkor, checked the same day, was all green. The migration goal was deleted, and AURYN was frozen.

    Build records and independent audit · 9 Aug 2026

  3. Decision

    Audited again, for parts

    Then AURYN was audited a second time, for what was worth keeping: the best parts that had actually been coded, and the ideas that never were. Both were refactored into a new package for reimagining Falkor. Among the ideas: one registry of everything the system can do, status that can't show green on stale data, and actions that aren't done until a check proves them.

    Audit and reimagining package · Aug 2026

  4. Decision

    Rebuilt in layers

    The rebuild took groups of pages one at a time, focused each group and layered it onto the new foundation. It was a large rebuild. Early on, an audit found 184 page routes, more than half of the registered ones retired but still alive, because every cleanup had added a hub and deleted nothing. In two days, 19 and 20 August, that became 98 with no capability lost. AURYN itself was left behind, adopted by the Falkor it was built to replace.

    Route audit · 19–20 Aug 2026

The lesson. A demo that shows shells is a finding, not a delay. Freeze early, audit for what's worth keeping, and rebuild the product people already use, one layer at a time.

Read the full case study

Every entry

  1. Decision

    Documentation holds current facts only

    Falkor's working documentation was rewritten to hold current facts only: a fact that changes is replaced in place, and finished work leaves the roadmap. The 17 core documents went from about 7 MB to 171 KB: eight working documents, plus nine short pointers kept where code names a path. Every earlier word is archived byte for byte with a checksum manifest. The rewrite took 46 minutes, with no code change.

    Docs cleanup closeout · 4 Nov 2026

  2. Decision

    A memory that learns, and shows its sources

    Falkor now learns from my chats and my own records, entirely on the home PC, in a memory kept apart from the notes I approve. Every fact it recalls is labelled with where it came from and when, each answer lists the facts it used, and anything can be forgotten. In a 26-question check, the facts came back for all 23 questions that had an answer, all 3 without one were declined rather than invented, and recall took about 0.8 seconds, down from 3 to 6.5. All 70 source labels checked were right.

    Memory quality check · 3 Nov 2026

  3. Decision

    Opening the dashboard changes nothing

    Falkor's new home screen follows one rule: opening it saves nothing and starts no AI job. Each tile shows what it last read, with its age, while it updates, and one “Needs you” count is shared across the header and every page, with “unknown” never shown as zero. Three agent lanes and an integrator built it in a day; on real data it is 41% shorter on a desktop and 55% shorter on a phone.

    Home surfaces closeout · 3 Nov 2026

  4. Decision

    Fold a page, keep every feature

    The Experiment Studio was folded into Visual Hub, the creative hub, under one rule: nothing that works is removed or hidden. Every feature moved, the old address points to its new home, and three tools that had never run were deleted outright, freeing 15 GB.

    Experiment fold closeout · 3 Nov 2026

  5. Lesson

    Unanswered is unknown, not down

    Status checks now tell unknown from down. Under the Linux subsystem's mirrored networking, a connection to an unused port can hang instead of being refused, so an unanswered probe is reported as unknown and then settled from the system's own list of listening ports, never guessed.

    Certification · 30 Oct 2026

  6. Decision

    A timing race fails certification

    Timing races are now held to the same standard as hard-coded models: from 29 October, any test whose result depends on timing fails certification. A gate now checks every test before it counts, and the certification run on 1 November passed every test on its first try.

    Operator rule · 29 Oct 2026

  7. Decision

    Certified means a full run

    Certification now means a full run of everything, with every test passing and nothing timed out, skipped or left unrun, and no caveats, before I sign it.

    Certification · 28 Oct 2026

  8. Lesson

    Every outbound flow, mapped

    A read-only audit mapped all 125 outbound flows: anything carrying a key, an account, a question I asked, the home location or a personal detail. Every fallback to cloud search is now visible and logged, keys stay out of logs, outbound traffic is checked in every certification, and chat runs on local models only.

    Outbound audit · 27 Oct 2026

  9. Decision

    Every pending update, applied safely

    Every pending update was applied in one pass: 66 Linux packages including Node, 13 web packages including Next.js and React, and the browser-testing tools, each checked live before certification. Falkor's own update button applies routine updates and, by design, leaves the riskiest tier for me to approve.

    Software inventory · 25 Oct 2026

  10. Decision

    Switch a new reader on only where it wins

    Firecrawl, a stronger web reader, went head to head with the ordinary reader on 53 news and venue sources, in two rounds, with robots.txt enforced. It won on 22 and was switched on for 19: only where it rescued a source the ordinary reader couldn't open, or did strictly better in both rounds. One arena's calendar went from 34 listings to 65.

    Reader trial · 25 Oct 2026

  11. Decision

    Split a phase to ship what's ready

    Phase 3 was split so each part could ship on its own merits: what the household could see went first, the redesign of the daily reading became Phase 4, and the 241 behind-the-scenes items became their own sub-phase, worked through by priority. By 30 October, 141 of them were delivered.

    Roadmap · 14 Oct 2026

  12. Lesson

    Report k of n, never a bare percentage

    After an agent's notes were compacted, a baseline survived only as “7.1%”, which was the failure rate. It nearly reported a 69-of-70 re-run as a jump from 7.1% to 98.6%. The real comparison was 65 of 70 against 69 of 70, with overlapping intervals: consistent with improvement, not proof of it.

    Behaviour suites · 28 Sep 2026

  13. Blocker

    The calendar went quiet, so Falkor says so

    From 21 Aug the calendar's sign-in could no longer be renewed, but a wrapper still returned “ok” with zero events, which let the assistant say there was nothing on tomorrow. Now Falkor says it can't reach the calendar: no web fallback, no invented events. Re-authorizing was mine to do; on 28 Sep it was reconnected, and a live check read all 7 calendars.

    Local-truth routing · Aug–Sep 2026

  14. Decision

    Red tests don't get longer timeouts

    The 22 Sep certification ran for 183 minutes with retries off and ended with 4 of 56 gates red. Raising timeouts or adding retries was rejected: it would have turned those gates into decoration and erased a real observation about behaviour under load. The same day, every failing check was fixed at its cause. No timeout was raised, no retry added, no assertion weakened.

    Certification · 22 Sep 2026

  15. Lesson

    Most reds were the test battery's own load

    The 22 Sep certification ended with 52 of 56 gates green. Behind the 4 red gates were 5 failing checks, and only one was a product defect; the others passed on a quiet machine. One took 15.6 seconds inside the battery and 672 milliseconds on its own. Now every red gets a quiet re-run before anyone repairs it.

    Certification · 22 Sep 2026

  16. Open questionOpen

    Fine-tune the chat model?

    On 17 Sep I chose a behaviour lab first, with fine-tuning only for the gaps it measures. Research on 21 Sep found that training the 12B chat model needs about 20 GB of GPU memory, against a 16 GB card. The question now is which measured gap, if any, is worth that.

    Roadmap · Sep 2026

  17. BlockerOpen

    Certification needs a person

    Falkor's certification matrix has 43 mandatory requirements. Two can't be met by any process: physically rebooting and logging in, and judging the cockpit on the real screen. Four more need evidence from a genuine reboot of the same build, so every fix deployed after a reboot costs another one. The formal stamp waits on me, on purpose.

    Certification matrix · Sep 2026

  18. Open questionOpen

    Keep n8n, or park it?

    n8n 3.0, due in October 2026, removes nodes. The options are to stay pinned on 2.x and prove that at least one approval-gated workflow earns its keep, or to park it.

    Roadmap · 17 Sep 2026

  19. Decision

    Keep a century-old archive out of the news

    The Library of Congress's Chronicling America was the last keyless news source on the list. But it serves digitised newspapers from before 1963, and mixing them into the current-news corpus would have damaged it. No adapter was written; the entry keeps its reasoning and a working endpoint until history has a proper home.

    Source registry · 4 Sep 2026

  20. Lesson

    A green gate that couldn't see

    The rule against hard-coded model names passed while 1,592 of them sat in 371 files, because it checked only two patterns. Its replacement brought them to zero, then turned out to exempt its own file, where it was carrying exactly what it bans. It now scans itself, and a missing self-scan fails the run.

    Model platform · Aug–Sep 2026

  21. Open questionOpen

    Where does history belong?

    Keeping pre-1963 newspapers out of the news was the easy half. The open half: does an archive deserve its own surface, with its own rules for ranking and freshness?

    Source registry · Sep 2026

  22. Decision

    Chat gets no permanent claim on the GPU

    A scheduled job loaded its own model and pushed the chat model off the 16 GB GPU. My first call was to give chat priority. That evening I reversed it: workloads run on schedule, and whichever model happens to be loaded is not the model chat uses. Removing the priority code (8 files) let the job run, and that exposed three hidden defects, including an 81.3-second cold load against a 25 to 45 second limit.

    Model scheduling · 3 Sep 2026

  23. Lesson

    Find the mechanism; don't tolerate the symptom

    A React hydration error (#418) appeared under load and was first tolerated as a framework bug. Instrumenting React's error path in the test browser showed the real mechanism: React 19.2 replayed a page element after a lazily loaded chunk paused hydration. A structural fix took it from 6 errors in 18 runs to 0 in 36.

    Front end · 2 Sep 2026

  24. Lesson

    An outlier is a question, not a finding

    An AI agent filed a disabled watchdog task as a high-priority recovery gap: it was the only one of four siblings switched off. It was a finished migration. The service had moved to the process manager in July, and re-enabling the task would have given one process two owners. The finding was withdrawn, tests now pin the migration, and the rule is to ask what replaced something before asking why it's off.

    Operability · 30 Aug 2026

  25. Lesson

    An estimate isn't a measurement

    When the full browser battery first ran, 889 tests failed. A 15-file sample was extrapolated to “about 83% are stale tests pinned to retired pages”. Measured across every failure the same day, only 26 of 890 (2.9%) carried the retired-page signature, and 391 (43.9%) failed on live pages. The work went where the measurement pointed: by 22 Sep, 7,215 of 7,218 passed.

    Test census · 26 Aug 2026

  26. Lesson

    A 400-character window hid 889 failures

    The certification script trimmed each red gate's evidence to its last four lines, 400 characters at most, so a shard with 120 failures showed one or two. Three full runs read as “a handful left”, and an agent's “24 → 10 → 0” progress story was an artifact of that window. Once red gates printed every failure, the real debt was 889 tests across 337 files.

    Certification tooling · Aug 2026

  27. Decision

    n8n: superseded, removed, restored behind approvals

    Falkor's own scheduler became the system of record (17 of 17 jobs healthy), so n8n was declared superseded, and the next lane removed the integration. That removal had no recorded authorization, while the instance and its 11 workflows were intact, so it was reversed. n8n came back as a lean bridge: it can list and describe workflows, but nothing runs without a plan-bound approval. Retiring a tool is a decision, not a side effect of someone's cleanup.

    Lane records · Aug 2026

  28. Lesson

    A time limit that could never pass

    Every certification gate had the same 900-second cap, including a browser tier of 6,949 tests run one at a time; a 260-test slice alone took 20 minutes. The cap could never cover the suite it claimed to gate. It became a fast collection check plus eight shards with two hours each, and full runs now take about three to four hours.

    Certification tooling · 24 Aug 2026

  29. Lesson

    Two dead signals before a kill

    During a certification run, the watchdog that recovers the Linux subsystem killed a healthy instance: one failed probe was enough, and that probe fails briefly under load. Recovery now needs two independent dead signals, 20 seconds apart. It has since absorbed about 25 real blips with no false kills and no missed failures.

    Supervisor · 24 Aug 2026

  30. Decision

    More memory for the Linux VM? Measured, and no

    The proposal was to raise the Linux subsystem's memory cap from 13 to 16 GB so the model runtime could memory-map its model. Measurement said it wouldn't be enough: the runtime would still have been about 8 GiB short, while Windows would have lost most of its last 2 GB. Instead, a held session cut cold starts to 2 in 8 hours, a larger swap file took chat turns over 10 seconds from 12% to 0%, and on 26 Aug the machine's RAM was doubled to 64 GB.

    Runbook and handoff · Aug 2026

  31. Lesson

    One word disabled every tool

    Chat tools had been silently off. The model service dropped its tool instructions whenever the system prompt contained “Falkor”, and Falkor's identity prompt always did. On the same question, the prompt shrank from 5,068 tokens to 502 and the tool call vanished.

    Audit · 21 Aug 2026Read the case study

  32. Lesson

    A feature that never worked, with a passing test

    The unified Inbox had never completed an inline action since it shipped: it sent display IDs where every backend expected exact IDs, and sent approvals to the wrong broker. Its only test checked that two URL strings appeared in the source code. After the fix, all 1,433 actionable rows resolve.

    Consolidation · 20 Aug 2026

  33. Lesson

    A build loop quietly ate 404 GiB

    The rewrite's build harness created a fresh 10.7 GiB build folder roughly every 25 minutes for two days, 40 of them, and never cleaned one up. A storage root-cause sweep found it among 480 GiB of reclaimable space. Falkor now keeps a permanent collector that names the owner of leftover files from their path, never guessing from their size.

    Storage sweep · 19 Aug 2026

  34. Lesson

    One setting reloaded the model every turn

    Falkor sent a per-request batch size that disagreed with the one the model runner was started with. The runtime quietly reloaded the model on every chat turn while still reporting it as loaded: 0.3 seconds of load time became 8 to 17. Removing one key cut time to first byte from 4.4 seconds to 0.4.

    Chat performance · 3 Aug 2026

  35. Lesson

    Agreement isn't truth

    Every document agreed that the rewrite's coding was frozen, so the contradiction checker found nothing stale. I had authorized coding that day; they were all wrong together. Status is now re-derived from the live source, never from documents agreeing with each other.

    Docs truth · 1 Aug 2026

  36. BlockerOpen

    The payout model broke the rules

    For the classroom fundraising app, policy research found that paying donations straight to teachers conflicts with school-district policy and state gift limits. I documented three compliant alternatives, and the real-money pilot waits until the payout model changes. Better found in research than in production.

    Policy memo · 17 May 2026

Timeline and commit history

From early March to late September 2026. This history comes from Falkor's own records (git history, roadmaps and audits), not from memory.

Commits per day

Falkor and its stack, 1 Mar 2026 to 16 Nov 2026

Git · 16 Nov 2026
Commits per day5,724 commits across 207 active days.MarAprMayJunJulAugSepOctNovMonWedFri1 Mar 2026: 0 commits2 Mar 2026: 0 commits3 Mar 2026: 0 commits4 Mar 2026: 0 commits5 Mar 2026: 0 commits6 Mar 2026: 0 commits7 Mar 2026: 0 commits8 Mar 2026: 0 commits9 Mar 2026: 0 commits10 Mar 2026: 0 commits11 Mar 2026: 0 commits12 Mar 2026: 0 commits13 Mar 2026: 0 commits14 Mar 2026: 0 commits15 Mar 2026: 0 commits16 Mar 2026: 0 commits17 Mar 2026: 9 commits18 Mar 2026: 7 commits19 Mar 2026: 16 commits20 Mar 2026: 12 commits21 Mar 2026: 14 commits22 Mar 2026: 13 commits23 Mar 2026: 0 commits24 Mar 2026: 0 commits25 Mar 2026: 12 commits26 Mar 2026: 5 commits27 Mar 2026: 2 commits28 Mar 2026: 9 commits29 Mar 2026: 11 commits30 Mar 2026: 7 commits31 Mar 2026: 0 commits1 Apr 2026: 0 commits2 Apr 2026: 0 commits3 Apr 2026: 0 commits4 Apr 2026: 30 commits5 Apr 2026: 7 commits6 Apr 2026: 0 commits7 Apr 2026: 3 commits8 Apr 2026: 0 commits9 Apr 2026: 0 commits10 Apr 2026: 0 commits11 Apr 2026: 0 commits12 Apr 2026: 0 commits13 Apr 2026: 0 commits14 Apr 2026: 0 commits15 Apr 2026: 0 commits16 Apr 2026: 0 commits17 Apr 2026: 0 commits18 Apr 2026: 0 commits19 Apr 2026: 0 commits20 Apr 2026: 0 commits21 Apr 2026: 0 commits22 Apr 2026: 0 commits23 Apr 2026: 0 commits24 Apr 2026: 10 commits25 Apr 2026: 25 commits26 Apr 2026: 25 commits27 Apr 2026: 22 commits28 Apr 2026: 42 commits29 Apr 2026: 37 commits30 Apr 2026: 21 commits1 May 2026: 22 commits2 May 2026: 7 commits3 May 2026: 7 commits4 May 2026: 53 commits5 May 2026: 51 commits6 May 2026: 45 commits7 May 2026: 39 commits8 May 2026: 31 commits9 May 2026: 28 commits10 May 2026: 27 commits11 May 2026: 31 commits12 May 2026: 27 commits13 May 2026: 38 commits14 May 2026: 34 commits15 May 2026: 40 commits16 May 2026: 33 commits17 May 2026: 43 commits18 May 2026: 31 commits19 May 2026: 23 commits20 May 2026: 22 commits21 May 2026: 6 commits22 May 2026: 19 commits23 May 2026: 56 commits24 May 2026: 55 commits25 May 2026: 14 commits26 May 2026: 35 commits27 May 2026: 15 commits28 May 2026: 30 commits29 May 2026: 25 commits30 May 2026: 0 commits31 May 2026: 5 commits1 Jun 2026: 28 commits2 Jun 2026: 40 commits3 Jun 2026: 9 commits4 Jun 2026: 12 commits5 Jun 2026: 10 commits6 Jun 2026: 8 commits7 Jun 2026: 4 commits8 Jun 2026: 20 commits9 Jun 2026: 12 commits10 Jun 2026: 18 commits11 Jun 2026: 8 commits12 Jun 2026: 12 commits13 Jun 2026: 6 commits14 Jun 2026: 4 commits15 Jun 2026: 8 commits16 Jun 2026: 22 commits17 Jun 2026: 17 commits18 Jun 2026: 13 commits19 Jun 2026: 7 commits20 Jun 2026: 9 commits21 Jun 2026: 10 commits22 Jun 2026: 12 commits23 Jun 2026: 7 commits24 Jun 2026: 1 commit25 Jun 2026: 6 commits26 Jun 2026: 7 commits27 Jun 2026: 0 commits28 Jun 2026: 13 commits29 Jun 2026: 8 commits30 Jun 2026: 24 commits1 Jul 2026: 14 commits2 Jul 2026: 27 commits3 Jul 2026: 1 commit4 Jul 2026: 25 commits5 Jul 2026: 13 commits6 Jul 2026: 30 commits7 Jul 2026: 17 commits8 Jul 2026: 0 commits9 Jul 2026: 0 commits10 Jul 2026: 19 commits11 Jul 2026: 12 commits12 Jul 2026: 3 commits13 Jul 2026: 23 commits14 Jul 2026: 6 commits15 Jul 2026: 9 commits16 Jul 2026: 1 commit17 Jul 2026: 0 commits18 Jul 2026: 33 commits19 Jul 2026: 16 commits20 Jul 2026: 21 commits21 Jul 2026: 2 commits22 Jul 2026: 3 commits23 Jul 2026: 1 commit24 Jul 2026: 5 commits25 Jul 2026: 1 commit26 Jul 2026: 18 commits27 Jul 2026: 6 commits28 Jul 2026: 15 commits29 Jul 2026: 18 commits30 Jul 2026: 6 commits31 Jul 2026: 23 commits1 Aug 2026: 0 commits2 Aug 2026: 0 commits3 Aug 2026: 11 commits4 Aug 2026: 1 commit5 Aug 2026: 0 commits6 Aug 2026: 15 commits7 Aug 2026: 0 commits8 Aug 2026: 4 commits9 Aug 2026: 11 commits10 Aug 2026: 32 commits11 Aug 2026: 12 commits12 Aug 2026: 10 commits13 Aug 2026: 15 commits14 Aug 2026: 6 commits15 Aug 2026: 14 commits16 Aug 2026: 4 commits17 Aug 2026: 27 commits18 Aug 2026: 7 commits19 Aug 2026: 10 commits20 Aug 2026: 22 commits21 Aug 2026: 36 commits22 Aug 2026: 18 commits23 Aug 2026: 9 commits24 Aug 2026: 23 commits25 Aug 2026: 5 commits26 Aug 2026: 18 commits27 Aug 2026: 25 commits28 Aug 2026: 15 commits29 Aug 2026: 3 commits30 Aug 2026: 12 commits31 Aug 2026: 67 commits1 Sep 2026: 67 commits2 Sep 2026: 36 commits3 Sep 2026: 12 commits4 Sep 2026: 18 commits5 Sep 2026: 8 commits6 Sep 2026: 13 commits7 Sep 2026: 9 commits8 Sep 2026: 5 commits9 Sep 2026: 3 commits10 Sep 2026: 19 commits11 Sep 2026: 8 commits12 Sep 2026: 0 commits13 Sep 2026: 1 commit14 Sep 2026: 8 commits15 Sep 2026: 17 commits16 Sep 2026: 74 commits17 Sep 2026: 24 commits18 Sep 2026: 7 commits19 Sep 2026: 1 commit20 Sep 2026: 4 commits21 Sep 2026: 7 commits22 Sep 2026: 9 commits23 Sep 2026: 14 commits24 Sep 2026: 3 commits25 Sep 2026: 5 commits26 Sep 2026: 73 commits27 Sep 2026: 11 commits28 Sep 2026: 203 commits29 Sep 2026: 76 commits30 Sep 2026: 0 commits1 Oct 2026: 3 commits2 Oct 2026: 25 commits3 Oct 2026: 191 commits4 Oct 2026: 18 commits5 Oct 2026: 3 commits6 Oct 2026: 0 commits7 Oct 2026: 0 commits8 Oct 2026: 6 commits9 Oct 2026: 105 commits10 Oct 2026: 112 commits11 Oct 2026: 102 commits12 Oct 2026: 35 commits13 Oct 2026: 0 commits14 Oct 2026: 11 commits15 Oct 2026: 61 commits16 Oct 2026: 51 commits17 Oct 2026: 12 commits18 Oct 2026: 3 commits19 Oct 2026: 50 commits20 Oct 2026: 13 commits21 Oct 2026: 44 commits22 Oct 2026: 54 commits23 Oct 2026: 119 commits24 Oct 2026: 56 commits25 Oct 2026: 83 commits26 Oct 2026: 96 commits27 Oct 2026: 113 commits28 Oct 2026: 190 commits29 Oct 2026: 68 commits30 Oct 2026: 62 commits31 Oct 2026: 3 commits1 Nov 2026: 2 commits2 Nov 2026: 0 commits3 Nov 2026: 117 commits4 Nov 2026: 39 commits5 Nov 2026: 23 commits6 Nov 2026: 227 commits7 Nov 2026: 126 commits8 Nov 2026: 33 commits9 Nov 2026: 11 commits10 Nov 2026: 14 commits11 Nov 2026: 148 commits12 Nov 2026: 111 commits13 Nov 2026: 31 commits14 Nov 2026: 24 commits15 Nov 2026: 7 commits16 Nov 2026: 1 commit

Commits per day01–78–1516–3132+

5,724 commits across 207 active days. About 7 in 10 commits to Falkor's main repository carry an AI coding agent's signature.

Monthly totals (table view)
MonthCommits
March 2026117
April 2026222
May 2026892
June 2026355
July 2026368
August 2026432
September 2026735
October 20261,689
November 2026914
  1. Early Mar 2026

    A local AI stack

    The DGo stack begins: local models, memory and services on one home PC.

    Project records

  2. 17 Mar 2026

    Falkor gets a face

    Falkor's clean-source repository starts: one cockpit over everything the stack can do.

    Git history

  3. Mar to Apr 2026

    Ten build phases

    Memory, agent orchestration, source quality and integrations, built phase by phase through the end of April.

    Roadmap

  4. May 2026

    The expansion

    826 Falkor commits in one month: a media studio, a pixel-display companion, personal tools and screen understanding.

    Git history

  5. 15 Jun 2026

    Falkor 3.0

    The shift from a pile of features to one product: one navigation, one model authority, production baselines.

    Project records

  6. 13 Jul 2026

    A clean-sheet rival

    Two AI models each designed a from-scratch successor to Falkor, and I judged them head to head. The winner, AURYN, was a Rust core with three hard rules aimed at Falkor's worst defects.

    Competition recordsThe whole story

  7. 9 Aug 2026

    Freezing the rewrite

    The rewrite's demo was all shells: 0 of 13 user journeys worked and the source no longer built. Falkor, checked the same day, was all green. I froze the rewrite, then had it audited for the parts worth keeping.

    Independent auditThe whole story

  8. Aug to Sep 2026

    Rebuilt in layers

    AURYN's best coded parts and unbuilt ideas became a package for reimagining Falkor, which was then rebuilt one group of pages at a time. In the first two days, 184 page routes became 98 with no capability lost.

    Route auditThe whole story

  9. Aug to Sep 2026

    Proving it

    Recovery programs, a 7,000-test browser battery made runnable, and certification gates that refuse to pass without evidence.

    Certification records

  10. 25 Sep 2026

    The full audit

    649 capabilities, 1,051 API operations and 7,331 dependencies mapped. It's the snapshot this site is built from.

    Capability audit

  11. Oct to Nov 2026

    Phases 3 to 7

    One drawer for chat, actions, capture and links; searchable documents; a redesigned daily reading, built by Codex; notes, documents and family features; a calm new home screen; and a personal memory that learns on the home PC and shows its sources. Utilities upgraded, every pending update applied, and the documentation cut to current facts.

    Roadmap · Lane closeouts

  12. 16 Nov 2026

    Certified

    Falkor's certification run passed all 8,724 browser tests, and I signed it off.

    Certification records

Esc