chore: daily update 2026-07-31
This commit is contained in:
OpenWiki Bot
+1
-1
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"updatedAt": "2026-07-29T18:13:32.946Z",
|
||||
"updatedAt": "2026-07-30T18:21:11.269Z",
|
||||
"command": "update",
|
||||
"model": "MiniMax-M3"
|
||||
}
|
||||
|
||||
@@ -39,6 +39,20 @@ Concrete work tasks, follow-ups, approvals, and scheduled items extracted from G
|
||||
- Status: open
|
||||
- Notes: Material new development in the China regulatory lane — sits **on top of** the existing `china-cde-cell-gene-therapy-rules-2026` and `china-order-no-818-clinical-translation` items, not replacing them. Two positive signals (Merck–Bio-Techne acquisition; CARsgen satri-cel solid-tumor CAR-T approval) show the China CGT manufacturing environment is consolidating around advanced therapeutics. One negative signal (gene-editing trial death + published regulatory backlash) could foreshadow stricter CDE / NMPA / hospital-level oversight and tighter qualification criteria for "qualified hospitals" under Order No. 818. Together these affect: (a) qualification timelines for the CellShot-TriArm and ClinoReactor-class deals Robin has in flight, (b) which "qualified hospitals" remain eligible to host first-in-human studies, (c) whether CelVivo / 3Brain / Cellink vendor positioning for Chinese pharma R&D / CDMO accounts needs to change tone (e.g. emphasize safety documentation, IRB-grade workflows). Pull NMPA / hospital-IRB statements on the gene-editing trial case before next Chinese customer conversation.
|
||||
|
||||
### 3brain-coreplate-2026-conference-positioning: verify current CorePlate campaign and retrieve application material on next 3Brain check
|
||||
- Owner: me
|
||||
- Source: web-search — 3Brain official website plus 3Brain organization material captured through LinkedIn in Tavily pull 7 (2026-07-30); the dated result is 2026-07-25 and names ISSCR 2026 booth 412, while the company page also names ELRIG Drug Discovery booth 4
|
||||
- Due: unscheduled
|
||||
- Status: open
|
||||
- Notes: First credible direct 3Brain evidence after five Tavily pulls dominated by an unrelated EEG-paper mis-attribution. Vendor material positions CorePlate-enabled HD-MEA for high-resolution, scalable functional readouts from iPSC neuronal/cardiac models, brain organoids, assembloids, and 3D spheroids. Confirm which conference posts are current, obtain the named posters/application notes, and map them to Chinese neural-organoid and pharma-screening prospects. This pull does not establish CorePlate 1W/6W load force or Sample Holder Set details.
|
||||
|
||||
### celvivo-clinostar-2-nams-demo-2026: verify product naming and campaign provenance on next CelVivo check
|
||||
- Owner: me
|
||||
- Source: web-search — Instagram snippets surfaced in Tavily pull 7 (2026-07-30): ClinoStar webinar copy (`DbaUZjIjMgK`), NexUs Locus on-site demo copy dated 2026-07-24 (`DbKYC4NBtrN`), and ClinoStar 2 NAMs positioning (`DbSl7nkoFjK`)
|
||||
- Due: unscheduled
|
||||
- Status: open
|
||||
- Notes: Watchlist lead, not a confirmed launch or customer win. Verify that the posts come from CelVivo or an authorized distributor, whether `ClinoStar 2` is current official product naming, and whether the NexUs Locus live demo produced reusable data or contacts. The result set does not support Tavily's “installed base” language; one malformed duplicate URL was discarded.
|
||||
|
||||
<!--
|
||||
Structure for new entries:
|
||||
|
||||
|
||||
+1
-1
@@ -23,7 +23,7 @@
|
||||
|
||||
- **Wiki state:** initialized — Hacker News, the local Obsidian vault, and Tavily web search are active and feeding `/sources/hackernews.md`, `/sources/git-repo.md`, `/sources/web-search.md`, and `/themes.md`.
|
||||
- **Connectors:** Hacker News, git-repo, and web search active. Gmail, Slack, Notion, and X are not yet configured — see "Adding sources" below.
|
||||
- **Last update:** see [/.last-update.json](/.last-update.json) — this run was a `git-repo` vault-fresh refresh (`obsidian-robin-1` pulled 2026-07-29 18:07 UTC). HEAD advanced from `21491578` → `1a81e485` (+2 commits dated 2026-07-29: `81671c69` feat Organoids 2026 综述 deep-read + `1a81e485` SOP-rewrite of the same file — both land in `04-Literature/Deep-Reads/Organoid/`). No new themes, commitments, or open-questions rows; HN + web-search lanes were unchanged from the prior pull so `/sources/hackernews.md` and `/sources/web-search.md` carry over without edit. Previous material-evidence run (web-search refresh `web-search-1` pulled 2026-07-29 18:03 UTC) — Three lanes produced material new evidence: (a) **first vendor-anchored Cellink BIO X Gen 3 / BIO X6 signal** (Nuclear Mechano-Oncology install LinkedIn, CELLINK official LinkedIn promoting BIO X6 at U. Miami, third-party market report noting Cellink revenue uptick, appellaser selection guide) — promoted to `/commitments.md` as `cellink-bio-x-gen3-customer-evidence`; (b) **China CGT regulatory landscape material updates** (Roots Analysis: Merck–Bio-Techne $11.3B June 2026 + CARsgen satri-cel CAR-T solid-tumor approval June 2026; SCMP/LiveScience/Straits Times: gene-editing trial death in 6-year-old + published regulatory backlash 2026-07-24 → 2026-07-29) — promoted to `/commitments.md` as `china-cgt-2026-july-developments`; (c) **Hermes Agent v0.19 docs continue** (NousResearch/hermes-agent `configuration.md` 2026-07-26 documents iteration-budget behavior change; `features/api-server.md` 2026-07-27 documents new `/v1/runs/{run_id}/stop` + `/approval` endpoints with MiniMax-M3 as the documented default) — refreshes `hermes-agent-v0-19-quicksilver` Last seen → 2026-07-29. Also: `agent-memory-architecture` cluster grows to 12+ distinct sources (Hackernoon Moorcheh.ai "Agent Memory Has a Lock-In Problem. Open Formats Are How We Fix It." is the strongest OpenWiki-aligning source yet — pull-request review of agent memory); `MiniMax-m3` refresh (MyClaw.ai 2026-07-29 confirms M3 + M2.7 as operational models for both OpenClaw and Hermes); `class-organoid-3d-bioprinting` refresh (GEN "Large Bioprinted Tissues Get a Precision Boost" 2026-07-29; MDPI Cells volumetric bioprinting + hepatic organoid 2026-07-27; CN Bio + Ligand Pharmaceuticals + Sequel Med Tech deal; NASA AVATAR with Emulate OOC). Tavily answer-text mis-attribution persists on Q2 3Brain (5th pull in a row) — flagged in `/sources/web-search.md`. Detailed evidence on `/sources/web-search.md` pull 6.
|
||||
- **Last update:** see [/.last-update.json](/.last-update.json) — the current run covers 3 connectors (`hackernews-1` 2026-07-30 18:00, `web-search-1` 2026-07-30 18:04, `git-repo` 2026-07-30 18:13). The HN pull returned the same vendor-empty pattern as the prior run (no theme refresh, no commitment row from that lane). The Tavily pull 7 (`2026-07-30 18:04`) was the material one — **first clean 3Brain Tavily evidence in any pull** (LinkedIn 3Brain organization material naming ISSCR 2026 booth 412 + 3Brain Japan company page covering ELRIG Drug Discovery booth 4 + RECI 2026 + INTERPHEX Japan 2026 + 3brain.com confirming CorePlate 3D / Accura-3D / BrainWave 6) — promoted to `/commitments.md` as `3brain-coreplate-2026-conference-positioning`; **CelVivo ClinoStar 2 / NAMs Instagram snippets** (ClinoStar webinar copy, NexUs Locus live-demo copy 2026-07-24, ClinoStar 2 NAMs positioning) — promoted to `/commitments.md` as `celvivo-clinostar-2-nams-demo-2026`. Three theme rows refreshed Last seen → 2026-07-30: `class-organoid-3d-bioprinting` (FDA NAMs framework 2026-07-27 + Molecular Cancer 3D-bioprinted liver cancer Peking Union 2026-07-28 + npj Biomedical Innovations microvasculature 2026-07-29 + CN Bio + NASA AVATAR re-anchored); `hermes-agent-v0-19-quicksilver` (api-server.md now exposes a per-profile `API_SERVER_KEY` breaking-change warning + Hermes Atlas state-of-Hermes-July-2026 third-party report); `agent-memory-architecture` adds arXiv 2607.24759v1 + rohitg00 LLM Wiki v2 (2026-07-30) + Pi `@zosmaai/pi-llm-wiki` + MinIO AIStor Memory (HPCwire 2026-07-29 + SiliconANGLE 2026-07-30) — cluster is now 14+ sources. Tavily answer-text was **honest on the 3Brain lane this pull** (vs the 5-prior-run Nature EEG mis-attribution pattern) — the new 3Brain hits are real, vendor-anchored. Tavily answer-text mis-attribution persists on Q1 (CelVivo) and Q6 (installed-base) — the latter hallucinated again "A-Level (H2) science labs, Eclat @ Henderson" with no underlying URL support. Git-repo pull at 18:13 is **identical state** to the 18:07 pull (HEAD still `1a81e485`, same 5 untracked files: 3Brain Sample Holder Set, Raji 2026 hMOs + 3Brain MEA, Tasevska 2025 HCTZ BIO X, Bosnjakovic 2025 PAH ClinoStar, OpenWiki速查手册) — no new commits, no new evidence. Detailed evidence on `/sources/web-search.md` pull 7.
|
||||
|
||||
## How to use this wiki
|
||||
|
||||
|
||||
+19
-3
@@ -8,10 +8,26 @@ Compact evidence trail for the Hacker News connector (`hackernews-1`, Robin-cura
|
||||
- **Backend:** public HN feeds (`top`, `new`) + Algolia HN search queries
|
||||
- **Auth:** none — public feeds
|
||||
- **Window:** last 24 hours
|
||||
- **Latest fetch:** `2026-07-29T18:00:02Z` (latest 18:00 pull on 2026-07-29; prior 2026-07-28 18:00, 2026-07-27 18:00, 2026-07-26 18:16 and 18:00 pulls also documented below)
|
||||
- **Raw dumps:** `~/.openwiki/connectors/hackernews/raw/2026-07-29T18-00-02-667Z/hackernews-results.json` (current) · `~/.openwiki/connectors/hackernews/raw/2026-07-28T18-00-02-178Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-27T18-00-02-615Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-26T18-16-06-805Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-26T18-00-02-441Z/hackernews-results.json`
|
||||
- **Latest fetch:** `2026-07-30T18:00:42Z` (latest 18:00 pull on 2026-07-30; prior 2026-07-29 18:00, 2026-07-28 18:00, 2026-07-27 18:00, 2026-07-26 18:16 and 18:00 pulls also documented below)
|
||||
- **Raw dumps:** `~/.openwiki/connectors/hackernews/raw/2026-07-30T18-00-02-784Z/hackernews-results.json` (current) · `~/.openwiki/connectors/hackernews/raw/2026-07-29T18-00-02-667Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-28T18-00-02-178Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-27T18-00-02-615Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-26T18-16-06-805Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-26T18-00-02-441Z/hackernews-results.json`
|
||||
|
||||
## Latest update — 2026-07-29 18:00 UTC
|
||||
## Latest update — 2026-07-30 18:00 UTC
|
||||
|
||||
- **Coverage:** 2 feeds (`top`, `new`), 24 search queries (the same life-science + workflow set the 2026-07-29 18:00 pull used), 26 + 30 = 56 unique resolved feed stories, and the life-science / vendor / workflow lane hit table below.
|
||||
- **Life-science lane:** **zero vendor-anchored hits** across all 14 life-science / vendor queries — `3D bioprinting`, `3D bioprinter`, `bioprinting clinical`, `spheroid bioreactor`, `microgravity cell culture`, `CELVIVO`, `MEA neuroscience`, `organ-on-chip`, `brain organoid`, `spheroid drug screening` returned `nbHits=0`. `organoid` returned 5 hits, all string collisions (Carolina Cloud pays SOFR on unused prepaid credits 55 pts; "Is the bottleneck on AI at your company technical or organizational?" 2 pts; "The cost of memory: How organisms balance thinking and sensing" 3 pts — a cognitive-biology essay on memory in living organisms, off-scope to 3D cell culture; "Built a household organizer in Flutter – what would you improve?" 1 pt; "AI policies that don't suck" 1 pt). `3Brain` returned 7 hits, all string collisions (Show HN: Burnless context-protocol 1 pt; "Reproducing Split Brain on CloudNativePG" 3 pts; "Mentally tiring work causes glutamate to build up in the brain (2022)" 2 pts; "The Computer and the Brain: John von Neumann" 5 pts; "The Strain in Your Brain" 3 pts; "My Brain-Breaking Trick to Quit Using Facebook" 4 pts; Show HN one-click-install "company brain" Chrome extension 2 pts). `Cellink` returned 3 hits, all string collisions ("Selling to Carol" 2 pts; "The 73,000-server market reselling Western frontier AI into China" 2 pts; "Go LLM SDK for streaming, tool-calling AI backends (plus frontend React lib)" 49 pts). `liver organoid` returned 1 hit = the same "AI policies that don't suck" false positive. A title/url regex sweep across the top + new feeds also turned up zero organoid / 3D-bioprinting / CelVivo / 3Brain / Cellink / ClinoStar / ClinoReactor / MEA / spheroid / organ-on-chip items. The prior "no material HN footprint for the 4 vendor lines" finding still holds.
|
||||
- **Workflow lane:** **zero search-query hits** that translate to direct changes on Robin's named daily-driver stack. `Codex CLI` returned 28 hits (capped at 20 returned) — surface-level cluster of generic agent wrappers / TUIs / context-engineering pieces (`49107749` "Agent-Manager: A Tmux TUI for Running Claude Code, Codex and OpenCode" 80 pts; `49111019` "Show HN: Claude-account – switch Claude Code accounts without logging in again" 20 pts; `49110007` "I aggregated 32 Claude Code sessions: 96.8% of tokens went to re-reading history" 1 pt; `49107982` "AI Automation Without the Hype" 4 pts; `49112195` "Show HN: Tuneloop – a local CLI for analyzing coding agent session transcripts" 4 pts; `49109106` "Show HN: Memsprout – share AI context with your teammates" 2 pts; `49105673` Rust coding agent compatible with Claude Code plugins/skills 3 pts). None is a direct change to Hermes / MiniMax / OpenWiki / RAGFlow / NocoDB / SeaFile, so they stay adjacent-not-promoted per the brief's "Workflow tooling (priority LOW)" rule. `Hermes Agent` returned 3 hits, all false positives / off-scope ("OpenAI's rogue agent didn't stop at Hugging Face" 2 pts; "Show HN: Let your agents create custom pods" 2 pts; "Launch HN: Prized (YC S26) – Let non-engineer staff build secure internal tools" 50 pts). `MCP connector agent` returned 2 hits — `49102632` "Transfer context from one agent to another agent mid task" (3 pts, new on 2026-07-30) is **adjacent** to the existing `agent-memory-architecture` watchlist (same lane as Worklog SQLite + OKF v0.2) but at 3 pts it does **not** push Last seen; `49102100` "Show HN: Nurb – Agentic CAD for 3D printing" (2 pts) is generic agentic CAD for plastic 3D printing, not bioprinting, so off-scope. `Claude Code agent workflow` returned 1 hit (`49105673`, same Rust-agent item). `MiniMax` returned 7 string-noise hits (Show HN: OpenMetaHarness long-horizon execution 3 pts; Minimus Hardened Images 2 pts; SDL_GPU 2D graphics library 42 pts; Show HN minimalist proxy for LLM cluster 2 pts; "A Dark Cave" minimalist survival game 3 pts; "How to get more coding productivity with LLMs" 8 pts; Ask HN: testers for RAM-based Linux distribution 3 pts). `OpenWiki`, `OpenWiki personal brain`, `RAGFlow`, `agent memory wiki`, `agent personal brain` all returned `nbHits=0`.
|
||||
- **High-engagement top-feed items not promoted:** `49111237` "Gemini Robotics 2 brings whole body intelligence to robots" (245 pts, top feed) — robotics, off-scope; `49112867` "Advancing the price-performance frontier with GPT-5.6" (133 pts, top feed, OpenAI blog) — GPT-5.6 model launch, off-scope; `49109193` "Why is everyone trying to build a solid-state battery?" (112 pts, top feed) — battery tech, off-scope; `49108048` "Gpiozero Flow" (111 pts, top feed) — Python GPIO library, off-scope; `49111176` "The Economic Benefit of Refactoring" (99 pts, top feed) — software dev, off-scope; `49109616` "Upper stage impacting the moon on 2026 August 5" (93 pts, top feed) — space, off-scope; `49108678` "Are We Stuck with Lean?" (89 pts, top feed) — manufacturing, off-scope; `49111305` "Physicists Solve a Muon Mystery. Now, Old Results Don't Add Up" (84 pts, top feed) — physics, off-scope; `49110547` "Hacker Public Radio" (80 pts, top feed) — community podcast, off-scope; `49108485` "3D Pinball for Windows (1995)" (73 pts, top feed) — retrocomputing, off-scope; `49108571` "Show HN: I made a game where you build a CPU from logic gates" (55 pts, top feed) — Show HN, off-scope; `49109721` "Launch HN: Prized (YC S26) – Let non-engineer staff build secure internal tools" (50 pts, top feed — same item returned by `Hermes Agent` query) — YC S26 launch, off-scope; `49108971` "How old is Ann?" (49 pts, top feed) — math puzzle, off-scope; `49113059` "We Gave GPT 5.6 Sol a Real Business. It Lied, Spammed, and Lost $447" (29 pts, top feed) — GPT-5.6 critique, off-scope; `49111019` "Show HN: Claude-account – switch Claude Code accounts without logging in again" (20 pts, top feed) — Claude Code wrapper, off-scope; `49113279` "Show HN: ZeroShot: Agent session monitoring to make your team go faster" (6 pts, new feed) — generic agent monitoring, off-scope; `49113099` / `49113287` "Inkling-Small" (4 pts each, new feed) — open-weight adjacent (Inkling-Small model card), off-scope; `49113348` "OpenAI cuts GPT 5.6 Luna prices by 80%" (1 pt, new feed) — GPT-5.6 pricing, off-scope.
|
||||
- **New-feed items not promoted:** all 30 items were either ≤ 6 pts, off-scope news (Russia charges Telegram founder Pavel Durov with aiding terrorism; South Korea stock market plunges as AI-driven boom fades; WNBA deletes wager post; Russia news; "Alan Turing's biggest AI assumption may have been wrong"), or already off-scope adjacent clusters (`49113120` "AI Agent Authentication and Authorization (IETF Internet-Draft)" 1 pt — adjacent to agent tooling but not Robin's named stack; `49113119` "Can AI agents conduct open-ended AI research?" 1 pt — generic agent research, off-scope). None matches a Robin in-scope keyword.
|
||||
- **Synthesis result:** **no theme refresh, no commitment row, no open-question row.** `class-organoid-3d-bioprinting` last-seen stays at 2026-07-29 (this 24h window is empty of organoid signal); `agent-memory-architecture` last-seen also stays at 2026-07-29 (`49102632` "Transfer context from one agent to another agent mid task" is adjacent at 3 pts but does not qualify for a refresh — engagement threshold not met). The Codex-CLI wrapper/TUI cluster continues to be the densest workflow signal at moderate engagement, but stays adjacent-not-promoted per the brief.
|
||||
|
||||
| Query lane | Queries run | Qualifying results |
|
||||
| --- | --- | --- |
|
||||
| Life sciences / vendors | `organoid`, `3D bioprinting`, `3D bioprinter`, `bioprinting clinical`, `spheroid bioreactor`, `microgravity cell culture`, `CELVIVO`, `3Brain`, `Cellink`, `MEA neuroscience`, `organ-on-chip`, `liver organoid`, `brain organoid`, `spheroid drug screening` | 0 |
|
||||
| AI workflow | `OpenWiki`, `OpenWiki personal brain`, `Hermes Agent`, `Claude Code agent workflow`, `Codex CLI`, `RAGFlow`, `agent memory wiki`, `agent personal brain`, `MCP connector agent`, `MiniMax` | 0 |
|
||||
|
||||
Raw dump: `~/.openwiki/connectors/hackernews/raw/2026-07-30T18-00-02-784Z/hackernews-results.json`.
|
||||
|
||||
## Update — 2026-07-29 18:00 UTC
|
||||
|
||||
- **Coverage:** 2 feeds (`top`, `new`), 24 search queries (the same life-science + workflow set the 2026-07-28 18:00 pull used), 27 + 30 = 57 unique resolved feed stories, and the life-science / vendor / workflow lane hit table below.
|
||||
- **Life-science lane:** **zero search-query hits** across all 14 life-science / vendor queries — `organoid`, `3D bioprinting`, `3D bioprinter`, `bioprinting clinical`, `spheroid bioreactor`, `microgravity cell culture`, `CELVIVO`, `3Brain`, `Cellink`, `MEA neuroscience`, `organ-on-chip`, `liver organoid`, `brain organoid`, `spheroid drug screening` all returned no results. A title/url regex sweep across the top + new feeds also turned up zero organoid / 3D-bioprinting / CelVivo / 3Brain / Cellink / ClinoStar / ClinoReactor / MEA / spheroid / organ-on-chip items. The prior "no material HN footprint for the 4 vendor lines" finding still holds.
|
||||
|
||||
+44
-2
@@ -1,6 +1,6 @@
|
||||
# Web Search Evidence
|
||||
|
||||
> Connector: `web-search-1` (Tavily). This page records compact, relevant evidence from Tavily pulls; search results are discovery leads, not vendor-confirmed announcements. Latest pull: 2026-07-27 18:04 UTC.
|
||||
> Connector: `web-search-1` (Tavily). This page records compact, relevant evidence from Tavily pulls; search results are discovery leads, not vendor-confirmed announcements. Latest pull: 2026-07-30 18:04 UTC.
|
||||
|
||||
## 2026-07-26 pull
|
||||
|
||||
@@ -317,5 +317,47 @@ Q10 returned four new sources that further corroborate the existing `agent-memor
|
||||
- Pull 4: fetched 2026-07-27T18:04:46Z — raw `~/.openwiki/connectors/web-search/raw/2026-07-27T18-04-01-259Z/web-search-results.json`
|
||||
- Pull 5: fetched 2026-07-28T18:04:26Z — raw `~/.openwiki/connectors/web-search/raw/2026-07-28T18-03-43-560Z/web-search-results.json`
|
||||
- Pull 6: fetched 2026-07-29T18:03:26Z — raw `~/.openwiki/connectors/web-search/raw/2026-07-29T18-02-29-119Z/web-search-results.json`
|
||||
- Queries: pulls 1, 2, 4, 5, 6 = 10 queries each; pull 3 = 6 queries (vendor-anchored only)
|
||||
- Pull 7: fetched 2026-07-30T18:04:41Z — raw `~/.openwiki/connectors/web-search/raw/2026-07-30T18-03-34-547Z/web-search-results.json`
|
||||
- Queries: pulls 1, 2, 4, 5, 6, 7 = 10 queries each; pull 3 = 6 queries (vendor-anchored only)
|
||||
- Instance: `web-search-1`
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-30 18:04 pull
|
||||
|
||||
Seventh stand-alone Tavily pull; all 10 queries re-ran. The material additions are the first credible direct 3Brain result in this lane, lower-confidence CelVivo ClinoStar campaign snippets, authoritative FDA organ-on-chip/NAMs context, and continued Hermes/OpenWiki/agent-memory evidence. Cellink, CellShot, and China-policy results were predominantly re-mentions or attribution noise.
|
||||
|
||||
### 3Brain CorePlate conference and application positioning — confirmed vendor signal
|
||||
|
||||
- **3Brain organization material via LinkedIn, surfaced with a 2026-07-25 result:** [ISSCR 2026 / CorePlate-enabled HD-MEA campaign](https://www.linkedin.com/posts/lucyschmidt_neuroscience-cellbiology-brain-activity-7486837823321292800-F8Rk) (score 0.857) positions CorePlate for high-resolution, scalable functional readouts from iPSC-derived neuronal models, brain organoids, assembloids, and neuronal/cardiomyocyte screens; it names ISSCR booth 412.
|
||||
- **3Brain company LinkedIn:** [3Brain AG](https://jp.linkedin.com/company/3brain) (score 0.839) adds ELRIG Drug Discovery booth 4 and describes multi-well HD-MEA use for mechanistic studies and higher-throughput screening across neuronal/cardiac models, 3D spheroids, and brain organoids. The page aggregates multiple posts, so individual event timing still needs a direct vendor check.
|
||||
- **3Brain official site:** [High-Density Microelectrode Array](https://www.3brain.com) (score 0.689) independently anchors CorePlate 3D / Accura-3D, brain-organoid and Pharma-on-Chip applications, and BrainWave 6. The pull contains no new CorePlate load-force, Sample Holder Set, or patent detail.
|
||||
- **Robin relevance:** first credible direct 3Brain evidence after five pulls dominated by an unrelated EEG-paper mis-attribution. Added `/commitments.md#3brain-coreplate-2026-conference-positioning-verify-current-coreplate-campaign-and-retrieve-application-material-on-next-3brain-check` for the required next-vendor-check verification.
|
||||
|
||||
### CelVivo ClinoStar / ClinoStar 2 campaign snippets — watchlist
|
||||
|
||||
- **Instagram snippets:** [ClinoStar webinar copy](https://www.instagram.com/p/DbaUZjIjMgK) (score 0.335) describes clinostat-based simulated microgravity; [NexUs Locus live-demo copy](https://www.instagram.com/reel/DbKYC4NBtrN) (published 2026-07-24; score 0.291) promises on-site growth of larger, more physiologically relevant organoids; a separate [ClinoStar 2 post](https://www.instagram.com/p/DbSl7nkoFjK) (score 0.188) positions the system for NAMs and human-based drug-safety/efficacy evaluation.
|
||||
- Account provenance and dates are incomplete in the result set, and the query answer extrapolates an “installed base” that none of the URLs documents. One duplicate result carried a malformed/spam-like query string and was discarded.
|
||||
- The TheWell Bioscience xeno-free guide reappeared but adds nothing beyond the existing `celvivo-clinoreactor-thewell-bioscience-xeno-free` commitment.
|
||||
- **Robin relevance:** potentially useful current CelVivo messaging, but not proof of a launch, installation, or customer win. Added `/commitments.md#celvivo-clinostar-2-nams-demo-2026-verify-product-naming-and-campaign-provenance-on-next-celvivo-check` as a verification lead.
|
||||
|
||||
### Organ-on-chip, bioprinting, and regulatory context
|
||||
|
||||
- **FDA, content current 2026-07-27:** [Accelerating and Modernizing Early and Late-Stage Clinical Development](https://www.fda.gov/industry/fda-actions-accelerate-and-modernize-early-and-late-stage-clinical-development) (score 0.566) explicitly includes human organ-on-chip systems among NAMs, alongside June 2026 cell/gene-therapy draft guidance and May 2026 streamlined nonclinical-safety guidance. This is authoritative US regulatory context, not a China-policy update.
|
||||
- **Molecular Cancer, published 2026-07-28:** [patient-derived 3D-bioprinted primary liver-cancer models](https://link.springer.com/article/10.1186/s12943-026-02751-1) (score 0.347), from Peking Union Medical College Hospital, adds China-based translational application evidence.
|
||||
- **npj Biomedical Innovations, published 2026-07-29:** [Challenges and opportunities in generating microvasculature using bioprinting techniques](https://www.nature.com/articles/s44385-026-00100-x) (score 0.177) adds application-domain context. The prior MDPI hepatic-organoid volumetric-bioprinting paper also reappeared.
|
||||
- China Order No. 818, CDE classification, CARsgen, CN Bio, NASA AVATAR, and Emulate results are re-mentions already captured in pull 5 or pull 6; no NMPA/CDE-direct corroboration appeared.
|
||||
|
||||
### Workflow tooling and agent memory — source-backed, low priority
|
||||
|
||||
- **NousResearch Hermes Agent docs:** [api-server.md](https://github.com/NousResearch/hermes-agent/blob/main/website/docs/user-guide/features/api-server.md) (score 0.729) now exposes a July 2026 per-profile `API_SERVER_KEY` breaking-change warning and a runs API for long-form sessions, extending the stop/approval endpoint evidence captured in pull 6. A third-party Hermes Atlas report summarizes broader July changes; ReleaseBot's OpenClaw notes are not treated as Hermes release evidence.
|
||||
- **OpenWiki official repository:** [langchain-ai/openwiki](https://github.com/langchain-ai/openwiki) (score 0.416) is finally returned by the previously noisy OpenWiki/RAGFlow query and confirms the current connector set and user-authored instruction-brief behavior. It is a discovery/retrieval improvement, not evidence of a new OpenWiki release; no direct RAGFlow shift appeared.
|
||||
- **LLM-wiki pattern:** [arXiv 2607.24759v1](https://arxiv.org/html/2607.24759v1) (score 0.792) explicitly describes an LLM-maintained interlinked Markdown wiki between raw sources and agents; [LLM Wiki v2](https://gist.github.com/rohitg00/2067ab416f7bbe447c1977edaaa681e2) surfaced on 2026-07-30 (score 0.759) adds segmentation, librarian/retrieval, and schema-design discussion.
|
||||
- **Enterprise agent memory:** MinIO's [AIStor Memory announcement](https://www.hpcwire.com/bigdatawire/this-just-in/minio-launches-aistor-memory-the-enterprise-memory-foundation-for-agentic-ai) (2026-07-29; score 0.576) and [SiliconANGLE coverage](https://siliconangle.com/2026/07/29/miniio-debuts-aistor-memory-long-term-memory-ai-agents-need-scale-safely) (2026-07-30; score 0.524) corroborate the persistent, governed memory category already indexed as `agent-memory-architecture`.
|
||||
|
||||
### Exclusions and synthesis result
|
||||
|
||||
- **Cellink:** Tavily's answer attributes the MDPI volumetric-bioprinting paper to BIO X, but the underlying result excerpt does not name CELLINK. Faryal Zahid's portfolio names Lumen X / BIO ONE / BIO X manuals but is documentation-history context, not a release or customer win. The existing Cellink commitment is unchanged.
|
||||
- **Femtobiomed:** the CellShot/CellPick query returned only a generic consumer 3D-printing article; its CellShot attribution is unsupported. No CellShot, CellPick, or TriArm evidence was promoted.
|
||||
- **Promoted:** two vendor-verification commitments (3Brain and CelVivo). **Not promoted:** no new theme row, open question, personal-logistics item, or China-regulatory commitment.
|
||||
- **Coverage:** fetched `2026-07-30T18:04:41.115Z`; 10 queries; raw `~/.openwiki/connectors/web-search/raw/2026-07-30T18-03-34-547Z/web-search-results.json`; instance `web-search-1`.
|
||||
|
||||
@@ -6,13 +6,13 @@ Index kept narrow by design: only themes that map to Robin's actual work (life-s
|
||||
|
||||
| Topic key | Theme / Signal | First seen | Last seen | Confidence | Sources | Evidence count | Status | Evidence |
|
||||
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
||||
| `class-organoid-3d-bioprinting` | Recurring organoid, 3D bioprinting, and 3D-cell-culture automation coverage; this window adds a 2026-07-28 HN drug-discovery essay (owlposting "Why haven't organoids solved all of drug discovery?", 9 pts), a 2026-07-27 Oxford Academic review on 3D-bioprinted organoids, a 2026-07-22 Sage review on bioprinting-enabled organoids, a 2026-07-27 Pluristyx iPSC + aerospace clinical-grade hepatocyte manufacturing partnership, the first vendor-anchored CelVivo ClinoReactor co-marketing signal (TheWell Bioscience xeno-free workflow pages), and the first vendor-anchored Cellink BIO X Gen 3 / BIO X6 signal (Nuclear Mechano-Oncology install + CELLINK LinkedIn U. Miami reference + third-party market report) plus GEN "Large Bioprinted Tissues Get a Precision Boost" (2026-07-29) and MDPI Cells "Rapid Volumetric Bioprinting Coupled with Dynamic Perfusion Enhances Human Hepatic Organoid Toxicity Testing" (2026-07-27) on top of the prior Nature / HN evidence; still mostly application-domain plus two vendor-channel signals | 2026-07-16 | 2026-07-29 | source-backed | hackernews, web-search | 20+ | active | [HN: 49083799 drug-discovery essay 2026-07-28](/sources/hackernews.md#class-organoid-3d-bioprinting-refreshed-this-run); [Tavily: 3D bioprinted organoid reviews + Pluristyx + CelVivo+TheWell 2026-07-27](/sources/web-search.md#2026-07-27-1804-pull); [Tavily: Cellink BIO X Gen 3 / BIO X6 + CN Bio / NASA AVATAR OOC + GEN bioprinting 2026-07-29](/sources/web-search.md#2026-07-29-1803-pull) |
|
||||
| `class-organoid-3d-bioprinting` | Recurring organoid, 3D bioprinting, and 3D-cell-culture automation coverage; this window adds a 2026-07-28 HN drug-discovery essay (owlposting "Why haven't organoids solved all of drug discovery?", 9 pts), a 2026-07-27 Oxford Academic review on 3D-bioprinted organoids, a 2026-07-22 Sage review on bioprinting-enabled organoids, a 2026-07-27 Pluristyx iPSC + aerospace clinical-grade hepatocyte manufacturing partnership, the first vendor-anchored CelVivo ClinoReactor co-marketing signal (TheWell Bioscience xeno-free workflow pages), and the first vendor-anchored Cellink BIO X Gen 3 / BIO X6 signal (Nuclear Mechano-Oncology install + CELLINK LinkedIn U. Miami reference + third-party market report) plus GEN "Large Bioprinted Tissues Get a Precision Boost" (2026-07-29) and MDPI Cells "Rapid Volumetric Bioprinting Coupled with Dynamic Perfusion Enhances Human Hepatic Organoid Toxicity Testing" (2026-07-27) on top of the prior Nature / HN evidence; pull 7 (2026-07-30) adds FDA NAMs framework (2026-07-27, organ-on-chip included among New Approach Methodologies alongside June 2026 cell/gene-therapy draft guidance), Molecular Cancer patient-derived 3D-bioprinted primary liver cancer (Peking Union Medical College Hospital, 2026-07-28), and npj Biomedical Innovations microvasculature bioprinting review (2026-07-29); still mostly application-domain plus two vendor-channel signals | 2026-07-16 | 2026-07-30 | source-backed | hackernews, web-search | 22+ | active | [HN: 49083799 drug-discovery essay 2026-07-28](/sources/hackernews.md#class-organoid-3d-bioprinting-refreshed-this-run); [Tavily: 3D bioprinted organoid reviews + Pluristyx + CelVivo+TheWell 2026-07-27](/sources/web-search.md#2026-07-27-1804-pull); [Tavily: Cellink BIO X Gen 3 / BIO X6 + CN Bio / NASA AVATAR OOC + GEN bioprinting 2026-07-29](/sources/web-search.md#2026-07-29-1803-pull); [Tavily: FDA NAMs + Peking Union 3D-bioprinted liver cancer + npj microvasculature 2026-07-30](/sources/web-search.md#2026-07-30-1804-pull) |
|
||||
| `china-cde-cell-gene-therapy-rules-2026` | China CDE (under NMPA) published technical guidelines defining scope & classification of cell and gene therapy drugs; standardizes CMC planning for Chinese pharma/CDMO/biotech customers | 2026-07-24 | 2026-07-24 | source-backed | web-search | 1 | watchlist | [Tavily: cisema.com 2026-07-24](/sources/web-search.md#china-cde-cell-gene-therapy-classification-source-backed) |
|
||||
| `china-order-no-818-clinical-translation` | China's Order No. 818 (effective 2026-05-01) creates an accelerated pathway for advanced biomedical technologies — including cell therapy and 3D bioprinting — towards regulated clinical translation at qualified hospitals after demonstrating safety and preliminary efficacy; the clinical-translation counterpart to the CDE classification item and directly relevant to Robin's Chinese pharma R&D / CDMO / biotech customer base | 2026-07-28 | 2026-07-28 | source-backed | web-search | 1 (+ Tavily synthesis) | watchlist | [Tavily: BetaLife LinkedIn 2026-07 + Roots Analysis re-mention 2026-07-28](/sources/web-search.md#china-order-no-818--accelerated-clinical-translation-pathway--source-backed) |
|
||||
| `MiniMax-m3` | MiniMax-M3 (1M context multimodal) HuggingFace model card + Twitter launch; the daily-driver inference provider behind every OpenWiki run and most of Robin's agent work; haimaker.ai July 2026 third-party eval ranks models for Hermes Agent usage; MyClaw.ai 2026-07-29 confirms M3 + M2.7 are the operational models for both OpenClaw and Hermes, with M3 supporting multimodal (image, video, music, speech, web search) | 2026-07-16 | 2026-07-29 | watchlist | hackernews, web-search | 5 | watchlist | [HN: M3 model cluster (huggingface + twitter)](/sources/hackernews.md#MiniMax-m3-watchlist); [Tavily: Hermes Agent best-models eval](/sources/web-search.md#hermes-agent-best-models-eval-source-backed-workflow-tooling-low-priority); [Tavily: MyClaw OpenClaw vs MiniMax Agent 2026-07-29](/sources/web-search.md#2026-07-29-1803-pull) |
|
||||
| `hermes-agent-v0-19-quicksilver` | Hermes Agent v0.19 "Quicksilver" release (2026-07-25): first-token delay 4.3s → 0.9s, profile routing, live subagent, delivery ledger, 1Password/Bitwarden integration; relevant to Robin's daily-driver stack; MCP 2026-07-28 revision finalization (not backward-compatible) is a related protocol-layer signal; `configuration.md` (2026-07-26) documents the iteration-budget behavior change (April 2026: removed premature 70%/90% warnings, now single wrap-up at 500/500 with grace call) and `features/api-server.md` (2026-07-27) documents new `/v1/runs/{run_id}/stop` + `/approval` endpoints with MiniMax-M3 as the documented default model | 2026-07-25 | 2026-07-29 | source-backed | web-search | 6 | active | [Tavily: Hermes v0.19 Quicksilver + MCP revision 2026-07-27](/sources/web-search.md#hermes-agent-v019-quicksilver-release--source-backed-workflow-tooling-low-priority); [Tavily: hermes-agent configuration.md + api-server.md + MyClaw 2026-07-29](/sources/web-search.md#2026-07-29-1803-pull) |
|
||||
| `hermes-agent-v0-19-quicksilver` | Hermes Agent v0.19 "Quicksilver" release (2026-07-25): first-token delay 4.3s → 0.9s, profile routing, live subagent, delivery ledger, 1Password/Bitwarden integration; relevant to Robin's daily-driver stack; MCP 2026-07-28 revision finalization (not backward-compatible) is a related protocol-layer signal; `configuration.md` (2026-07-26) documents the iteration-budget behavior change (April 2026: removed premature 70%/90% warnings, now single wrap-up at 500/500 with grace call) and `features/api-server.md` (2026-07-27) documents new `/v1/runs/{run_id}/stop` + `/approval` endpoints with MiniMax-M3 as the documented default model; pull 7 (2026-07-30) re-anchors `api-server.md` with a new per-profile `API_SERVER_KEY` breaking-change warning and a runs API for long-form sessions, and adds a third-party Hermes Atlas "State of Hermes Agent — July 2026" report | 2026-07-25 | 2026-07-30 | source-backed | web-search | 8 | active | [Tavily: Hermes v0.19 Quicksilver + MCP revision 2026-07-27](/sources/web-search.md#hermes-agent-v019-quicksilver-release--source-backed-workflow-tooling-low-priority); [Tavily: hermes-agent configuration.md + api-server.md + MyClaw 2026-07-29](/sources/web-search.md#2026-07-29-1803-pull); [Tavily: api-server.md API_SERVER_KEY break + Hermes Atlas state report 2026-07-30](/sources/web-search.md#2026-07-30-1804-pull) |
|
||||
| `openwiki-brand` | `langchain-ai/openwiki` (96 pts) — same product family as Robin's OpenWiki; high-engagement on HN | 2026-07-16 | 2026-07-16 | source-backed | hackernews | 1 (+ 2 adjacent wrappers) | watchlist | [HN: openwiki cluster](/sources/hackernews.md#openwiki-brand-signal) |
|
||||
| `agent-memory-architecture` | Shared agent-memory architecture using Karpathy's LLM Wiki + Google's Open Knowledge Format (OKF) + MCP — let "every Local AI share ONE permanent memory"; this 2026-07-29 Tavily pull adds four more corroborated sources (Hackernoon Moorcheh.ai "Agent Memory Has a Lock-In Problem. Open Formats Are How We Fix It." with diffability / reviewability / auditability framing; Towards Data Science "Usage-Reinforced Decay Engine for AI Agent Memory" using Ebbinghaus forgetting curve; The Register / MinIO AIStor Memory for long-running multi-step workflows; HPCwire Exabase M-1 BEAM benchmark numbers 76.9% / 75.0% / 68.0% at 100K/1M/10M tokens) on top of the prior HN + Tavily sources; the Hackernoon piece is the strongest OpenWiki-aligning source yet | 2026-07-26 | 2026-07-29 | source-backed | hackernews, web-search | 12+ | active | [HN: 49059959, 49059889, 49060215](/sources/hackernews.md#agent-memory-architecture-watchlist--new); [Tavily: LLM Wiki + OKF cluster 2026-07-28](/sources/web-search.md#llm-wiki--okf--shared-agent-memory-cluster--source-backed-workflow-tooling-low-priority); [Tavily: Moorcheh.ai + TDS + MinIO + Exabase cluster 2026-07-29](/sources/web-search.md#2026-07-29-1803-pull) |
|
||||
| `agent-memory-architecture` | Shared agent-memory architecture using Karpathy's LLM Wiki + Google's Open Knowledge Format (OKF) + MCP — let "every Local AI share ONE permanent memory"; this 2026-07-29 Tavily pull adds four more corroborated sources (Hackernoon Moorcheh.ai "Agent Memory Has a Lock-In Problem. Open Formats Are How We Fix It." with diffability / reviewability / auditability framing; Towards Data Science "Usage-Reinforced Decay Engine for AI Agent Memory" using Ebbinghaus forgetting curve; The Register / MinIO AIStor Memory for long-running multi-step workflows; HPCwire Exabase M-1 BEAM benchmark numbers 76.9% / 75.0% / 68.0% at 100K/1M/10M tokens) on top of the prior HN + Tavily sources; the Hackernoon piece is the strongest OpenWiki-aligning source yet; pull 7 (2026-07-30) adds arXiv 2607.24759v1 "A Templated Substrate for Heterogeneous Collaborative" + rohitg00 LLM Wiki v2 (extending Karpathy's LLM Wiki pattern with lessons from building agentmemory) + Pi `@zosmaai/pi-llm-wiki` package + MinIO AIStor Memory (HPCwire 2026-07-29 + SiliconANGLE 2026-07-30) — cluster is now 14+ distinct sources | 2026-07-26 | 2026-07-30 | source-backed | hackernews, web-search | 14+ | active | [HN: 49059959, 49059889, 49060215](/sources/hackernews.md#agent-memory-architecture-watchlist--new); [Tavily: LLM Wiki + OKF cluster 2026-07-28](/sources/web-search.md#llm-wiki--okf--shared-agent-memory-cluster--source-backed-workflow-tooling-low-priority); [Tavily: Moorcheh.ai + TDS + MinIO + Exabase cluster 2026-07-29](/sources/web-search.md#2026-07-29-1803-pull); [Tavily: arXiv 2607.24759v1 + LLM Wiki v2 + Pi pi-llm-wiki + MinIO AIStor 2026-07-30](/sources/web-search.md#2026-07-30-1804-pull) |
|
||||
|
||||
## Notes
|
||||
|
||||
|
||||
Reference in New Issue
Block a user