# Internalize > Managed knowledge adapters and asynchronous GLM 5.3 inference. The hosted console is currently a preview: no live payment collection or model execution. Read availability before running examples. ## Start here - [Availability](https://convergingthought.com/docs-markdown/getting-started/availability) - [Quickstart](https://convergingthought.com/docs-markdown/getting-started/quickstart) - [OpenAPI specification](https://convergingthought.com/openapi.json) - [Complete documentation](https://convergingthought.com/llms-full.txt) ## Guides and references - [Activate an adapter](https://convergingthought.com/docs-markdown/api-reference/activation): POST /v1/adapters/activate — change future routing with an expected-version check. - [Chat Completions](https://convergingthought.com/docs-markdown/api-reference/chat-completions): OpenAI-compatible text and function calls, backed by durable inference jobs. - [Conventions and limits](https://convergingthought.com/docs-markdown/api-reference/conventions): Headers, request IDs, idempotency, pagination, time, and input limits. - [Errors and retry decisions](https://convergingthought.com/docs-markdown/api-reference/errors): Distinguish rejected requests, failed jobs, and outcomes that need reconciliation. - [API overview](https://convergingthought.com/docs-markdown/api-reference): The complete public HTTP surface for asynchronous GLM 5.3 inference and managed adapters. - [Create an inference](https://convergingthought.com/docs-markdown/api-reference/inferences): POST /v1/inferences — answer using the subject's active adapter and only the messages you send. - [Create an internalization](https://convergingthought.com/docs-markdown/api-reference/internalizations): POST /v1/internalizations — learn a passage into a new adapter candidate. - [Read and list jobs](https://convergingthought.com/docs-markdown/api-reference/jobs): GET /v1/jobs/{id} and GET /v1/jobs — durable outcomes, usage, and settlement. - [List models](https://convergingthought.com/docs-markdown/api-reference/models): GET /v1/models — discover the currently supported model and published rates. - [List subjects and versions](https://convergingthought.com/docs-markdown/api-reference/subjects): GET /v1/subjects — inspect the active route and recent retained adapters. - [Credits and pricing](https://convergingthought.com/docs-markdown/billing): Prepaid usage, learning budgets, memory hosting, and settlement. - [Spending limits and reservations](https://convergingthought.com/docs-markdown/billing/limits): Understand the two admission checks: available credit and monthly budget capacity. - [Purchases, receipts, and refunds](https://convergingthought.com/docs-markdown/billing/payments): Follow credit from a verified payment event into the project ledger. - [Data handling](https://convergingthought.com/docs-markdown/concepts/data-handling): Understand the source, result, checkpoint, and telemetry boundaries. - [How learning works](https://convergingthought.com/docs-markdown/concepts/how-it-works): From source knowledge to a validated adapter that answers without the source in context. - [Core concepts](https://convergingthought.com/docs-markdown/concepts): The objects and boundaries behind a persistent model memory. - [Job lifecycle](https://convergingthought.com/docs-markdown/concepts/jobs): Follow one operation from admission and credit reservation through execution and settlement. - [Projects and subjects](https://convergingthought.com/docs-markdown/concepts/subjects): Choose stable identities that match who should share learned knowledge. - [Validation and quality](https://convergingthought.com/docs-markdown/concepts/validation): Read the candidate's checks correctly and separate learning success from product readiness. - [Versions and routing](https://convergingthought.com/docs-markdown/concepts/versions-and-routing): Immutable candidates, explicit activation, and a stable subject for every new request. - [Authentication](https://convergingthought.com/docs-markdown/getting-started/authentication): Use project-scoped server keys with explicit permissions and a controlled rotation path. - [Preview availability](https://convergingthought.com/docs-markdown/getting-started/availability): What you can use today, what is gated, and how to interpret the examples in these docs. - [Choose an interface](https://convergingthought.com/docs-markdown/getting-started/interfaces): Use the console for inspection, HTTP for integration, and the tool boundary for agent memory. - [Project setup](https://convergingthought.com/docs-markdown/getting-started/onboarding): Establish the project, credentials, and spending boundary before making model calls. - [Make your first call](https://convergingthought.com/docs-markdown/getting-started/quickstart): Connect your model client, then optionally add learned knowledge. - [Build agent memory](https://convergingthought.com/docs-markdown/guides/agent-memory): Turn selected, authorized knowledge into durable subject state without storing credentials in the model. - [Evaluate learned knowledge](https://convergingthought.com/docs-markdown/guides/evaluation): Test recall, applications, exceptions, and retention without leaking the source into the prompt. - [Prepare knowledge](https://convergingthought.com/docs-markdown/guides/knowledge): Write a self-contained source that supports clear questions, applications, and exceptions. - [Serve multiple customers](https://convergingthought.com/docs-markdown/guides/multitenancy): Isolate each customer's learned weights with one tenant ID and a memory name. - [Integrate a production application](https://convergingthought.com/docs-markdown/guides/production): Keep authorization, operation identity, budgets, and observability aligned across the whole request path. - [Deploy knowledge updates](https://convergingthought.com/docs-markdown/guides/rollouts): Sequence learning, activation, evaluation, and rollback without overwriting another release. - [Internalize](https://convergingthought.com/docs-markdown): Learn knowledge into model weights. Keep the source out of subsequent prompts. - [Documentation for agents](https://convergingthought.com/docs-markdown/integrations/agent-docs): Discover the API and read focused Markdown pages before taking a paid action. - [OpenAI Agents SDK](https://convergingthought.com/docs-markdown/integrations/agents-sdk): Run an existing agent through the explicit Chat Completions model adapter. - [Agent tool integration](https://convergingthought.com/docs-markdown/integrations/agents): Expose one learning tool with a trusted subject boundary and an inspectable asynchronous result. - [Vercel AI SDK](https://convergingthought.com/docs-markdown/integrations/ai-sdk): Use Internalize with generateText, streamText, and your own tools. - [Connect your agent](https://convergingthought.com/docs-markdown/integrations): Use the model in your existing stack, then add learning when it is useful. - [LangChain and LangGraph](https://convergingthought.com/docs-markdown/integrations/langchain): Keep your chain or graph and replace its chat-model connection. - [Add learning](https://convergingthought.com/docs-markdown/integrations/learning): Give an agent one tool that updates learned weights without exposing routing authority. - [OpenAI SDKs](https://convergingthought.com/docs-markdown/integrations/openai): Connect Python or TypeScript with the Chat Completions API. - [Privacy](https://convergingthought.com/docs-markdown/privacy): What the platform records. - [Memory](https://convergingthought.com/docs-markdown/product/adapters): Manage learned knowledge, active model state, and retained memory versions. - [Manage API keys](https://convergingthought.com/docs-markdown/product/keys): Create one credential per workload, inspect its identity, and revoke it when no longer needed. - [Console overview](https://convergingthought.com/docs-markdown/product/overview): Find setup, credentials, requests, adapters, usage, and spending controls in one project workspace. - [Use the playground](https://convergingthought.com/docs-markdown/product/playground): Chat with the base model, add knowledge to memory, and inspect the version behind an answer. - [Activity](https://convergingthought.com/docs-markdown/product/requests): Follow status, routing, token usage, results, and charges for each admitted operation. - [Project settings](https://convergingthought.com/docs-markdown/product/settings): Change the project label, control monthly spending, and inspect recent administrative activity. - [Read usage](https://convergingthought.com/docs-markdown/product/usage): Understand settled token counts, call totals, and daily spend. - [SDKs and HTTP clients](https://convergingthought.com/docs-markdown/sdk-reference/overview): Choose a client without changing the public job, routing, or billing semantics. - [Polling and recovery](https://convergingthought.com/docs-markdown/sdk-reference/polling): Keep one durable operation through retries, process restarts, and long-running work. - [Python over HTTP](https://convergingthought.com/docs-markdown/sdk-reference/python): Submit and poll using Python's standard library, without an unpublished SDK dependency. - [TypeScript client](https://convergingthought.com/docs-markdown/sdk-reference/typescript): The exact interface of the private workspace SDK, with explicit operation identity and result checks. - [Service terms](https://convergingthought.com/docs-markdown/terms): Preview service conditions. - [Access and setup problems](https://convergingthought.com/docs-markdown/troubleshooting/access): Diagnose credentials, scopes, preview gates, and project mismatches before changing code. - [Safe diagnostics](https://convergingthought.com/docs-markdown/troubleshooting/diagnostics): Collect the smallest useful report without exposing API secrets or model content. - [Stalled and failed jobs](https://convergingthought.com/docs-markdown/troubleshooting/jobs): Recover the original operation without duplicating paid inference or learning. - [Knowledge and routing problems](https://convergingthought.com/docs-markdown/troubleshooting/knowledge): Separate a wrong route, a failed activation, expired hosting, and a genuine learning failure.