Update to Rhizome AI
Snapshot Nov 21, 2026 · 06:10 UTC · version 3.2.0
Package or technical metadata updated
Package or technical metadata updated
Observed in package metadata. These changes alone do not establish a new customer-facing feature.
Up to 3 plugins free · no card required.
All fields and original values.
These are saved file metadata. Open a changed file to read its text edits.
Package file
Oct 24, 2026 · 13:02 UTC
29fe31fa3dacc66c722982a22ea235171e37af2bea56181e3726aa37c3fc2388
Nov 21, 2026 · 06:10 UTC
338c63598b9bbe1be1d715765136f14d2e98ff532f8353fbd7c7286cab32e9f8
Package file
Oct 24, 2026 · 13:02 UTC
3999
Nov 21, 2026 · 06:10 UTC
5724
Compare saved observations
Download comparison JSONChanged files
Choose a file to see its text changes. Binary or large files show metadata only.
.codex-plugin/plugin.json
− removed · + added
--- before +++ after @@ -2,7 +2,7 @@ "author": { "name": "Rhizome AI" }, - "description": "Rhizome's built an AI regulatory coworker that helps life sciences know what their regulator thinks.\n\nWe're backed by the same investors as Benchling and have gone from 0 -> >25 customers in the last 18 months. \n\nWe've indexed >3 TB worth of data put out by the FDA, EMA, MHRA, PMDA, etc., and built an agent that helps you:\n - automate precedents research \n - research FDA expectations around clinical endpoints, trial design, labeling, etc. \n - review briefing booklets, write pre-IND meeting packages, create white papers on almost any topic \n\nWhat you get:\n - each fact is backed by a citation, each citation is backed by the page of a health authority document \n - comprehensive answers that draw on up to 1,000 sources \n - we've had no hallucinations reported last 18 months \n\nFor more info, read rhizomeai.com/llms.txt\n\nFor support, reach out to support@rhizomeai.com", + "description": "Rhizome is an AI Regulatory Coworker that researches comprehensively to answer based on facts it can directly tie to >130 indexed health authority databases.\n\nOur customers are leveraging it to:\n\n- Build regulatory strategies\n- Understand clinical expectations\n- Keep an eye on competitive intel\n- Write and review HA-facing documents\n\nOur datasets cover:\n\n- FDA: drug, biologic and device approvals (Drugs@FDA, Purple Book, Orange Book, 510(k)/De Novo, PMA), DailyMed labels, guidance (including product-specific guidance), advisory committees, CRLs, warning and untitled letters, 483s and inspections, recalls, orphan designations, clinical trials, the CFR and the Federal Register\n- EMA and EU: EPARs, guidelines, committee documents, orphan and PIP decisions, CTIS and EU CTR trials, EudraLex, MDCG guidance, EUDAMED devices and certificates\n- UK MHRA, Health Canada, Swissmedic, TGA (Australia) and BfArM/PEI (Germany): approvals and assessment reports, guidance, regulations and clinical trials\n- International standards: ICH, IMDRF, PIC/S, ISO and GHWP\n- US market access: CMS coverage decisions, HCPCS codes and Part B drug pricing\n- Competitive context: SEC filings, patents and PTAB decisions, PubMed, and RAPS/DIA regulatory news\n\nEnterprise accounts can also search 50+ more databases, all translated to English:\n\n- Japan PMDA: review reports, guidance, the Japanese Pharmacopoeia, and jRCT/UMIN clinical trials\n- China NMPA/CDE: product reviews, CDE acceptances, guidance, regulations, announcements and consultations, clinical trials (including ChiCTR), and human genetic resources rules\n- South Korea MFDS: review reports, drug, biologic and device regulations, guidance, notifications and clinical trials\n- Brazil ANVISA: guidance, legislation, clinical research guidance and CONEP resolutions\n- Taiwan TFDA/CDE: guidance, announcements, drug safety communications, regulatory notices and drug/device laws\n- More jurisdictions: Argentina ANMAT, India CDSCO, South Africa SAHPRA, Saudi SFDA, T\u00fcrkiye T\u0130TCK, Israel MoH and UAE EDE\n- FDA adverse events: FAERS (drugs) and MAUDE (devices)\n- Health Canada: clinical study reports through PRCI\n\nSupport: support@rhizomeai.com", "interface": { "capabilities": [], "category": "Healthcare", @@ -13,9 +13,9 @@ ], "developerName": "Rhizome AI", "displayName": "Rhizome AI", - "longDescription": "Rhizome's built an AI regulatory coworker that helps life sciences know what their regulator thinks.\n\nWe're backed by the same investors as Benchling and have gone from 0 -> >25 customers in the last 18 months. \n\nWe've indexed >3 TB worth of data put out by the FDA, EMA, MHRA, PMDA, etc., and built an agent that helps you:\n - automate precedents research \n - research FDA expectations around clinical endpoints, trial design, labeling, etc. \n - review briefing booklets, write pre-IND meeting packages, create white papers on almost any topic \n\nWhat you get:\n - each fact is backed by a citation, each citation is backed by the page of a health authority document \n - comprehensive answers that draw on up to 1,000 sources \n - we've had no hallucinations reported last 18 months \n\nFor more info, read rhizomeai.com/llms.txt\n\nFor support, reach out to support@rhizomeai.com", + "longDescription": "Rhizome is an AI Regulatory Coworker that researches comprehensively to answer based on facts it can directly tie to >130 indexed health authority databases.\n\nOur customers are leveraging it to:\n\n- Build regulatory strategies\n- Understand clinical expectations\n- Keep an eye on competitive intel\n- Write and review HA-facing documents\n\nOur datasets cover:\n\n- FDA: drug, biologic and device approvals (Drugs@FDA, Purple Book, Orange Book, 510(k)/De Novo, PMA), DailyMed labels, guidance (including product-specific guidance), advisory committees, CRLs, warning and untitled letters, 483s and inspections, recalls, orphan designations, clinical trials, the CFR and the Federal Register\n- EMA and EU: EPARs, guidelines, committee documents, orphan and PIP decisions, CTIS and EU CTR trials, EudraLex, MDCG guidance, EUDAMED devices and certificates\n- UK MHRA, Health Canada, Swissmedic, TGA (Australia) and BfArM/PEI (Germany): approvals and assessment reports, guidance, regulations and clinical trials\n- International standards: ICH, IMDRF, PIC/S, ISO and GHWP\n- US market access: CMS coverage decisions, HCPCS codes and Part B drug pricing\n- Competitive context: SEC filings, patents and PTAB decisions, PubMed, and RAPS/DIA regulatory news\n\nEnterprise accounts can also search 50+ more databases, all translated to English:\n\n- Japan PMDA: review reports, guidance, the Japanese Pharmacopoeia, and jRCT/UMIN clinical trials\n- China NMPA/CDE: product reviews, CDE acceptances, guidance, regulations, announcements and consultations, clinical trials (including ChiCTR), and human genetic resources rules\n- South Korea MFDS: review reports, drug, biologic and device regulations, guidance, notifications and clinical trials\n- Brazil ANVISA: guidance, legislation, clinical research guidance and CONEP resolutions\n- Taiwan TFDA/CDE: guidance, announcements, drug safety communications, regulatory notices and drug/device laws\n- More jurisdictions: Argentina ANMAT, India CDSCO, South Africa SAHPRA, Saudi SFDA, T\u00fcrkiye T\u0130TCK, Israel MoH and UAE EDE\n- FDA adverse events: FAERS (drugs) and MAUDE (devices)\n- Health Canada: clinical study reports through PRCI\n\nSupport: support@rhizomeai.com", "privacyPolicyURL": "https://rhizomeai.com/privacypolicy", - "shortDescription": "Know what the FDA thinks", + "shortDescription": "Cited FDA & EMA Answers", "supportURL": "https://rhizomeai.com", "termsOfServiceURL": "https://rhizomeai.com/termsofservice", "websiteURL": "https://rhizomeai.com", @@ -25,12 +25,12 @@ "composerIconDark": "./assets/icon-dark.png" }, "name": "app-6a63bad25528819187bf1eeabd8a9af3", - "version": "3.1.0", + "version": "3.2.0", "mcpServers": "./.mcp.json", "extensions": { "com.openai": { "publication": { - "release_notes": "New tools: rhizome_search finds a specific document the user names (a warning letter, 483, label, guidance, 510(k), recall) and returns its best-matching pages; rhizome_document_read reads the pages of one document found with rhizome_search; rhizome_dataset_list lists the searchable datasets and their filters. All three are read-only. Regulatory and clinical questions still go to rhizome_conversation_message, which researches across sources and returns a cited answer.\n\nUpdated: rhizome_conversation_message is no longer marked read-only, since it starts a research run and saves a conversation to the user's account. rhizome_conversation_message and rhizome_conversation_wait have clearer descriptions and output field docs, and a used-up free-plan allowance now returns as a normal result with an upgrade link instead of an error. Server instructions are shorter and cover when to use search and read versus research, answering a clarifying question from the research agent, and stopping a run in progress." + "release_notes": "Listing update: new subtitle and description. No tool or server changes." } } },
Full technical diff · 2 changed fields
changed /files/.codex-plugin~1plugin.json/sha256
"29fe31fa3dacc66c722982a22ea235171e37af2bea56181e3726aa37c3fc2388"
"338c63598b9bbe1be1d715765136f14d2e98ff532f8353fbd7c7286cab32e9f8"
changed /files/.codex-plugin~1plugin.json/size
3999
5724
Full snapshot data
{
"files": {
".app.json": {
"sha256": "0dd04711584a3c52fafbc855ed4ee43e95b71db5cdd0c0f216a5c9472bc29f0e",
"size": 99
},
".codex-plugin/plugin.json": {
"sha256": "338c63598b9bbe1be1d715765136f14d2e98ff532f8353fbd7c7286cab32e9f8",
"size": 5724
},
".mcp.json": {
"sha256": "f935ff3c231b46e38cc4bf06202dd511885e85ccd62f6bfee5e979485cdd51a5",
"size": 94
},
"assets/icon-dark.png": {
"sha256": "c0bfc452a7014208ee6b5dd2ff5fb2c04c5ee3dc8bda308e2afdfeb6ce222b11",
"size": 10495
},
"assets/icon.png": {
"sha256": "19589982da256aad72ea697076ce7ff27ddf9417a89277e1347a451cfa3b98f4",
"size": 10288
},
"assets/logo-dark.png": {
"sha256": "9a38cc3e48b1d78711d95d7d7af6dfc78a7062bf49449ce16eec81f3d3b77d03",
"size": 18018
},
"assets/logo.png": {
"sha256": "d1b9cb623fc1e68acea1d601f6b466f654c495549aee48cdefafb3e3be85f547",
"size": 14706
}
}
}SHA-256 of public snapshot: a1cf316115a565bea53813499d09b6c29e1416dda931afe9c62e71bd440d0e6b