Meta tags:
description=AI agents are only as smart as the context you give them. OKF is a new open specification that... Tagged with ai, mlops, opensource, architecture.;
keywords=ai, mlops, opensource, architecture, software, coding, development, engineering, inclusive, community;

Headings (most frequently used words):

okf, example, knowledge, the, what, bundle, vs, team, open, format, markdown, standard, your, ai, agents, have, been, waiting, for, dev, community, actually, is, structure, real, world, examples, rag, mcp, getting, started, in, minutes, to, know, before, adopting, early, mover, case, top, comments, data, base, platform, runbook, api, documentation, more, from, suhas, mallesh,

Text of the page (most frequently used words):
the (58), and (30), for (24), knowledge (23), okf (23), #bundle (21), that (16), your (16), agent (15), fullscreen (14), mode (14), orders (13), dev (12), rag (10), pipeline (10), you (10), agents (10), data (10), api (10), with (9), this (9), team (9), tables (9), can (9), files (9), what (9), directory (9), markdown (9), not (9), from (8), are (8), concept (8), format (8), any (8), concepts (8), revenue (8), share (7), time (7), exit (7), enter (7), file (7), mcp (7), query (7), create (6), log (6), open (6), source (6), terraform (6), context (6), every (6), path (6), type (6), table (6), title (6), tags (6), customers (6), status (6), model (5), comment (5), like (5), link (5), one (5), runbook (5), them (5), see (5), before (5), tool (5), runbooks (5), all (5), pci (5), community (4), 2026 (4), use (4), real (4), internal (4), post (4), spec (4), metrics (4), same (4), schema (4), optional (4), means (4), without (4), index (4), description (4), resource (4), joins (4), metric (4), live (4), charge (4), key (4), auth (4), payments (4), call (4), churn_score (4), their (3), software (3), code (3), free (3), about (3), docs (3), agnostic (3), more (3), suhas (3), mallesh (3), follow (3), abuse (3), hide (3), comments (3), want (3), but (3), via (3), make (3), copy (3), hari (3), haran (3), always (3), get (3), three (3), point (3), changes (3), minutes (3), early (3), read (3), semantics (3), calls (3), standard (3), know (3), join (3), into (3), bundle_path (3), validate (3), per (3), order (3), prod (3), core (3), customer_id (3), schemas (3), apis (3), reads (3), charges (3), platform (3), example (3), monthly (3), building (3), order_items (3), account (2), where (2), date (2), other (2), policy (2), conduct (2), database (2), organization (2), accounts (2), help (2), aws (2), azure (2), may (2), joined (2), location (2), actions (2), reporting (2), will (2), hidden (2), report (2), common (2), across (2), tools (2), menu (2), jul (2), save (2), answer (2), store (2), architecture (2), bundles (2), github (2), catalog (2), defined (2), find (2), write (2), learn (2), case (2), adopting (2), starting (2), has (2), level (2), base (2), audit (2), ready (2), default (2), how (2), body (2), parse (2), content (2), vendor (2), two (2), teams (2), yet (2), shared (2), does (2), give (2), critical (2), tooling (2), field (2), names (2), experimental (2), load_okf_bundle (2), text (2), concept_id (2), str (2), pathlib (2), run (2), validator (2), returns (2), eof (2), row (2), customer (2), postgresql (2), ecommerce (2), truth (2), first (2), getting (2), stable (2), large (2), document (2), runtime (2), chunks (2), curated (2), cross (2), yes (2), server (2), requires (2), when (2), processing (2), new (2), scope (2), rate (2), limits (2), refunds (2), service (2), patterns (2), links (2), related (2), diagnose (2), escalate (2), human (2), cloudwatch (2), check (2), drift (2), root (2), failure (2), response (2), mlops (2), annual (2), mrr (2), sum (2), active (2), count (2), trial (2), subscriptions (2), sla (2), value (2), monthly_recurring_revenue (2), documents (2), known (2), issues (2), column (2), records (2), entries (2), required (2), each (2), graph (2), relationship (2), complete (2), order_id (2), timestamp (2), anything (2), specification (2), solves (2), custom (2), doesn (2), have (2), been (2), waiting (2), search (2), place, coders, stay, grow, careers, made, love, 2016, ruby, rails, built, powers, inclusive, communities, forem, terms, privacy, mlh, shop, postgres, contact, showcase, advertise, education, tracks, videos, challenges, home, space, discuss, keep, development, manage, career, gcp, googlecloud, 2024, san, francisco, california, further, consider, blocking, person, confirm, child, well, sure, become, still, visible, permalink, reply, button, likes, interesting, could, much, easier, reduce, duplicated, effort, dropdown, jun, chennai, india, finding, features, smarter, workflows, solutions, creators, developers, expand, collapse, dismiss, preview, submit, templates, let, quickly, faqs, snippets, template, trusted, user, personal, subscribe, top, found, helpful, deep, dives, reference, implementations, sample, com, googlecloudplatform, start, most, pain, prone, misused, mis, nobody, 2am, apache, takes, five, honest, now, markup, decade, ago, cheap, ship, makes, legible, questions, movers, matters, mover, tracked, iso, 8601, regulated, industries, those, convention, tell, behave, repo, describes, they, solve, different, layers, problem, complements, claude, lives, git, repository, filesystem, readable, switch, consumers, migrating, lock, design, using, exchange, whether, interpret, identically, depends, conventions, aren, standardized, already, gives, way, structural, interoperability, semantic, expect, evolve, don, build, mission, assumes, won, change, google, finished, explicitly, items, load, inject, return, removesuffix, relative_to, read_text, continue, name, rglob, dict, def, import, over, pass, fail, rule, tripped, exits, gate, node, mjs, npx, conformance, cat, mkdir, started, practical, pattern, definitions, archives, governs, connect, sources, plumbing, replace, derives, raw, stores, linked, updates, directly, vector, embeddings, just, infrastructure, unstructured, corpora, org, best, request, derived, ahead, authored, prepared, connection, protocol, retrieval, these, complementary, competing, rest, payment, operations, bearer, token, tokens, expire, after, hour, retrieve, issue, refund, 100, req, min, burst, 200, seconds, 429, breach, fields, tagged, must, logged, policies, true, endpoints, services, https, ships, alongside, integrating, endpoint, needing, openapi, specs, documentation, follows, uses, alarm, sagemaker, execution, verify, sync, completed, cause, update, manually, eventbridge, unresolved, ml_platform, components, preprocess, preprocessing, component, resolution, training_data, training, systems, feature_store, feature, pipeline_logs, logs, diagnosis, steps, failed, 5xx, errors, symptoms, sre, writes, navigate, respond, incidents, reading, writing, dashboard, avoids, plan, division, error, junior, analysts, constantly, subscription_amount, billing_period_months, plans, divide, 12x, excluded, attrition, caveats, recurring, finance, subscription, normalized, quality, sql, generating, understanding, gotchas, world, examples, reserved, filenames, carry, meaning, enumerates, contents, support, progressive, disclosure, letting, available, opening, individual, grouped, newest, listing, changelog, pipeline_failure, incident_response, payments_api, structure, authentication, sdk, system, linking, turns, navigable, asserts, specific, kind, conveyed, surrounding, prose, itself, identifier, registry, generation, identity, things, powerful, purchase, event, queries, filter, unless, specifically, exclude, flight, uuid, primary, total, usd, enum, pending, refunded, utc, displays, pst, conversion, convert, created_at, amount_usd, columns, 15t10, 00z, looks, entire, yaml, frontmatter, deliberately, minimal, metadata, form, representing, capture, including, datasets, playbooks, actually, published, june, neutral, simplest, possible, approach, exists, scattered, confluence, pages, notion, wikis, slack, threads, heads, senior, engineers, integration, scratch, hits, wall, capable, framework, set, formula, says, breaks, only, smart, packages, organizational, plain, integrations, proprietary, sdks, opensource, posted, mastodon, facebook, linkedin, copied, clipboard, pick, gem, boost, jump, fire, raised, hands, exploding, head, unicorn, add, reaction, close, powered, algolia, navigation, skip,

Text of the page (random words):
open knowledge format okf the markdown standard your ai agents have been waiting for dev community skip to content navigation menu search powered by algolia search log in create account dev community close add reaction like unicorn exploding head raised hands fire jump to comments save boost pick as gem more copy link copy link copied to clipboard share to x share to linkedin share to facebook share to mastodon share post via report abuse suhas mallesh posted on jul 3 open knowledge format okf the markdown standard your ai agents have been waiting for ai mlops opensource architecture ai agents are only as smart as the context you give them okf is a new open specification that packages your organizational knowledge as plain markdown files so any agent can read it without custom integrations or proprietary sdks every team building ai agents hits the same wall the model is capable the agent framework is set up but the agent doesn t know anything about your organization it doesn t know what your orders table means what the churn_score metric formula is or what the on call runbook says to do when the pipeline breaks that knowledge exists it s scattered across confluence pages notion wikis data catalog entries slack threads and the heads of senior engineers getting it into an agent means building a custom integration for every source every team solves this from scratch published on june 12 2026 the open knowledge format okf is a vendor neutral specification that solves this with the simplest possible approach a directory of markdown files ️ what okf actually is an okf bundle is a directory of markdown files representing concepts anything you want to capture including tables datasets metrics playbooks runbooks and apis each concept is one file that s the entire model a directory of md files with yaml frontmatter the format is deliberately minimal one required field type optional metadata title description resource tags timestamp and a free form markdown body a concept document looks like this type table title orders description one row per customer order source of truth for revenue reporting resource postgresql prod db ecommerce orders tags revenue core sla timestamp 2026 06 15t10 00 00z orders the orders table records every purchase event it is the join root for all revenue queries do not filter on status complete unless you specifically want to exclude in flight orders from the count key columns order_id uuid primary key customer_id fk to customers customers md amount_usd total order value in usd status enum pending processing complete refunded common joins joins to customers customers md on customer_id joins to order_items order_items md on order_id known issues the created_at column is utc but the bi tool displays it in pst without conversion always convert at query time enter fullscreen mode exit fullscreen mode three things make this powerful 1 file path is identity the file tables orders md has the concept identifier tables orders no registry no id generation no database 2 markdown links are the knowledge graph a link from concept a to concept b asserts a relationship the specific kind of relationship is conveyed by the surrounding prose not by the link itself concepts linking to each other turns the directory into a navigable graph 3 no tooling required no api no authentication no sdk the file system is the api bundle structure knowledge bundle index md optional directory listing log md optional changelog tables index md orders md customers md order_items md metrics churn_score md monthly_recurring_revenue md runbooks pipeline_failure md incident_response md apis payments_api md enter fullscreen mode exit fullscreen mode two reserved filenames carry defined meaning at any directory level an index md file enumerates the directory s contents to support progressive disclosure letting a human or agent see what is available before opening individual documents a log md file records changes in date grouped entries newest first real world examples example 1 data team knowledge base your data team documents tables metrics and known data quality issues an agent building a sql query can read the bundle before generating the query understanding column semantics join patterns and gotchas type metric title monthly_recurring_revenue description sum of all active subscription charges normalized to a monthly value tags revenue finance sla monthly recurring revenue mrr mrr sum subscription_amount billing_period_months where status active source table subscriptions tables subscriptions md caveats annual plans divide by 12 do not count them as 12x monthly trial accounts are excluded status trial see churn_score churn_score md for related attrition metric enter fullscreen mode exit fullscreen mode an agent reading this before writing a revenue dashboard query avoids the annual plan division error that junior analysts make constantly example 2 platform team runbook your sre team writes runbooks as okf concepts an on call agent can navigate the bundle to diagnose and respond to incidents type runbook title ml pipeline failure response tags on call mlops critical ml pipeline failure response symptoms cloudwatch alarm prod pipeline 5xx errors sagemaker pipeline execution status failed diagnosis steps 1 check pipeline logs pipeline_logs md in cloudwatch 2 verify feature store systems feature_store md sync completed 3 check training data tables training_data md for schema drift resolution if root cause is data schema drift update the preprocessing component components preprocess md re run pipeline manually via eventbridge escalate to ml platform team teams ml_platform md if unresolved in 30 minutes enter fullscreen mode exit fullscreen mode the agent reads the runbook follows cross links to related concepts and can diagnose or escalate all from the same markdown files a human uses example 3 api documentation bundle your platform team ships an okf bundle alongside their service any agent integrating with the api reads the bundle for endpoint semantics auth patterns and rate limits without needing to parse openapi specs or call an mcp server type api title payments api resource https api internal payments v2 tags payments core pci payments api rest api for all payment processing operations auth bearer token from auth service services auth md tokens expire after 1 hour key endpoints post charges create a new charge see charge schema schemas charge md get charges id retrieve charge status post refunds issue a refund requires refunds write scope rate limits 100 req min per api key burst to 200 for 10 seconds returns 429 on breach pci scope all fields tagged pci true must not be logged see pci policy policies pci md enter fullscreen mode exit fullscreen mode okf vs rag vs mcp these three are complementary not competing okf rag mcp what it is curated knowledge format query time retrieval from chunks runtime tool data connection protocol when knowledge is prepared ahead of time authored at query time derived live at request time best for stable org knowledge schemas runbooks large unstructured corpora live data actions tool calls requires infrastructure no just files yes vector db embeddings yes mcp server rag re derives knowledge at query time from raw chunks an okf bundle stores curated cross linked concepts that an agent reads and updates directly mcp governs how ai agents connect to tools and live data sources the runtime plumbing okf does not replace mcp the practical pattern use okf for stable knowledge table schemas metric definitions runbooks rag for large document archives and mcp for live apis and tool calls getting started in 5 minutes create a bundle mkdir my knowledge bundle cd my knowledge bundle create your first concept cat tables orders md eof type table title orders description one row per customer order resource postgresql prod ecommerce orders tags revenue core orders source of truth for revenue joins to customers on customer_id eof validate conformance npx okf validate my knowledge bundle enter fullscreen mode exit fullscreen mode run the open source okf validator over your bundle node validator okf validate mjs your bundle it returns pass or fail names every rule a file tripped and exits with a code you can gate ci on point any agent at the directory import pathlib def load_okf_bundle bundle_path str dict concepts for path in pathlib path bundle_path rglob md if path name in index md log md continue text path read_text concept_id str path relative_to bundle_path removesuffix md concepts concept_id text return concepts load bundle and inject into agent context bundle load_okf_bundle my knowledge bundle context n n join f k n v for k v in bundle items enter fullscreen mode exit fullscreen mode ️ what to know before adopting it s v0 1 and explicitly experimental okf v0 1 is an early experimental spec that google calls a starting point not a finished standard expect the spec to evolve don t build mission critical tooling that assumes field names won t change structural interoperability not semantic okf already gives agents a shared way to find and read context it does not yet give them shared semantics for what that context means two teams using okf can exchange bundles whether their agents interpret them identically depends on conventions that aren t yet standardized no vendor lock in by design an okf bundle lives in any git repository on any filesystem readable by any tool that can parse markdown you can switch consumers without migrating your content complements agents md and claude md those convention files tell an agent how to behave in a repo okf describes a body of data and knowledge they solve different layers of the same problem audit ready by default every okf bundle has optional log md files at any directory level changes are tracked in iso 8601 format for regulated industries this means your knowledge base is audit ready by default ️ the early mover case the spec is apache 2 0 free to use and takes five minutes to learn the honest case for adopting now is the same as schema markup a decade ago it is cheap to ship it makes your knowledge legible to the agents that are starting to answer questions about you and early movers learn the format before it matters start with one team s most pain prone knowledge the tables that always get misused the metrics that always get mis defined the runbook that nobody can find at 2am write three okf concept files point an agent at them see what changes the spec reference implementations and sample bundles are on github github com googlecloudplatform knowledge catalog found this helpful follow for more ai architecture deep dives top comments 1 subscribe personal trusted user create template templates let you quickly answer faqs or store snippets for re use submit preview dismiss collapse expand hari haran hari haran hari haran follow finding hidden features smarter workflows and ai solutions to help creators and developers save time location chennai india joined jun 25 2026 jul 4 dropdown menu copy link hide interesting concept a common knowledge format could make it much easier for ai agents to share context and reduce duplicated effort across tools like comment like comment 2 likes like comment button reply code of conduct report abuse are you sure you want to hide this comment it will become hidden in your post but will still be visible via the comment s permalink hide child comments as well confirm for further actions you may consider blocking this person and or reporting abuse suhas mallesh follow location san francisco california joined may 7 2024 more from suhas mallesh a real rag pipeline on azure internal docs q a with terraform model agnostic azure ai rag terraform a real rag pipeline on gcp internal docs q a with terraform model agnostic googlecloud ai rag terraform a real rag pipeline on aws internal docs q a with terraform model agnostic aws ai rag terraform dev community a space to discuss and keep up software development and manage your software career home dev challenges dev videos dev education tracks dev help advertise on dev organization accounts dev showcase about contact free postgres database dev shop mlh code of conduct privacy policy terms of use built on forem the open source software that powers dev and other inclusive communities made with love and ruby on rails dev community 2016 2026 we re a place where coders share stay up to date and grow their careers log in create account