The LLM Network feed (/llms-network.txt)
The LLM Network feed offers selected public catalog fields in Markdown, JSON and JSONL. It is available for retrieval, not a guarantee of whole-corpus coverage or delivery to external engines.
What the feed islink
The feed provides listing names, categories, summaries, canonical URLs and tier fields at /llms-network.txt, /llms-network.json and /feeds/catalog.jsonl. Main-directory shards use /llms-network/{software|ai-tools|services}.{txt|json|jsonl}. Enabled cross-host families can also appear, so the network total is not a main-host listing count. These are reader formats, not universal registry or indexing protocols.
How your listing gets inlink
Eligible published software, AI-tool and service partner listings require a Kariant AI or Agentic AI plan stamp. Basic and unstamped partner listings are excluded, and distribution.feedOptOut removes a listing from the feed. Supported platform-authored content and cross-host families use their own eligibility rules. Inclusion is not an independent verification of a price, rating or other field.
Freshness and attributionlink
Catalog and HTTP caches mean updates and withdrawals are not instantly visible to every reader. The feed currently uses a 15-minute corpus cache and a 15-minute public response cache; external copies can persist longer. A generated date is not proof of a fresh source check. Canonical URLs support attribution and fact-checking but do not certify the underlying claims.
Frequently asked questions
Do I have to register my listing for the feed?expand_more
There is no separate external-registry enrollment. Inclusion follows publication, plan and surface eligibility, supported fields and your feed opt-out. Check the served feed after its caches refresh rather than assuming immediate inclusion.
How does plan tier affect feed inclusion?expand_more
For main-directory partner listings, Kariant AI and Agentic AI are eligible; Basic is excluded. The public listing page is a separate channel. Published records still need to pass the feed rules and must not be opted out.
Which engines read the feed?expand_more
The feed is openly consumable by external generative and answer engines. Kariant publishes and maintains the pipe; it does not (and cannot) dictate each engine’s crawl schedule or usage.
Can I opt out?expand_more
Use the per-listing AI syndication feed switch in the Distribution console at kariant.app/partner/distribution. The network feed honors the saved preference on refresh, not instantly across caches or external copies. Other machine formats have separate serving rules; this switch is not a promise of universal removal.