What plugs in, and what it connects
30 integrations across 5 categories. The four lines are written in different languages, but their infrastructure choices converge on one set of standard parts — which lowers the operational learning cost for our customers.
How the four business lines connect to each other
This is our biggest difference from single-product companies: not four isolated systems, but one kernel with three applications on top.
Agents register as MACHINE principals; credentials, scopes and tool permissions are issued by the identity kernel and can be revoked instantly
The internal account system connects to unified identity, converging login, roles and permissions in one place
Switching the auth domain from local to remote completes the integration, with no changes to any other domain
Agents handle common enquiries in service scenarios, and past conversations become their knowledge source
One LLM abstraction layer: Unilearning uses it to draft grading, and the teacher makes the final call
Private-domain customers can become learners, with orders and progress unified in one customer view
Identity sources & social login
6 itemsDomestic IM ecosystems and international social accounts run through one connector abstraction, so external identities can be mapped onto local identities and identity tags.
QR-code login and directory sync; the org structure becomes the identity source, and join/leave events drive account lifecycle.
OAuth2 authorization code + directory callbackWeChat login and user profile retrieval, unifying consumer membership across platforms.
OAuth2 authorization codeMini-program session exchanged for a unified identity, so app, mini program and web share one membership.
code2session + identity bindingInternal office integration, with employee records and org relationships as the authoritative source.
Incremental directory syncSocial login for engineering collaboration, used by internal tools and external partners.
OAuth2International social login, sharing one connector admin console with GitHub.
OAuth2 / OIDCCollaboration & reach channels
6 itemsWherever users are, the agent is there too. Channel adapters normalise each platform’s messages into one internal message structure, so business logic never perceives platform differences.
Connected in SCRM pull mode to reach customers inside the WeCom ecosystem; Uniscrm also handles external contacts and conversation archiving.
pull + callbackPush API for outbound messages plus event reception — suited to internal assistants and approval flows.
Event subscription + message pushPush API for outbound messages, sharing one channel adapter abstraction with Feishu.
Event subscription + message pushReal-time bidirectional WebSocket communication, embeddable in your own product as a conversation entry point.
Persistent WebSocket connectionCalled directly by business systems to embed agent capability into existing product flows.
REST / streaming SSEShort-link redirects, mini-program configuration and H5 pages form the private-domain distribution chain.
Short link + mini-program configurationModels & intelligence
6 itemsModel vendors are pluggable, with no lock-in to any single one. Pick the model per scenario: fast models for conversation, strong models for planning.
A unified abstraction in the llm module: any service speaking the OpenAI protocol can connect, including privately deployed ones.
HTTP / streamingOptional for long-context and tool-calling scenarios, sharing one calling abstraction with other vendors.
Vendor adapterUsed for multimodal and retrieval-augmented scenarios, with available models configured per tenant.
Vendor adapterDomestic models connect over the compatible protocol; the default candidates for AI grading.
OpenAI-compatibleLocal inference for fully intranet scenarios, so grading depends on no external service.
OpenAI-compatibleThe vector retrieval foundation for memory and knowledge, privately deployable, with vectors never leaving the intranet.
gRPCData & middleware
6 itemsThe four business lines speak different languages, but their infrastructure choices converge on the same set of standard parts, lowering the operational learning cost for customers.
The primary database for UIAM and Uniscrm, with migration files maintained per dialect.
JDBC + LiquibaseSupported homogeneously with MySQL; PostgreSQL is the preferred dialect for Unilearning.
JDBC / gormSessions, tokens and rate-limit counters, supporting the low-latency token validation requirement.
RESPAsync tasks and message delivery, absorbing peaks in WeCom sync and notifications.
AMQPAssets, media and courseware resources; Unilearning supports real AssumeRole temporary credentials.
S3-compatible / OSS STSDelivered as a single image or Compose with consistent environments — the standard private-deployment form.
Image / ComposeGateways & runtimes
6 itemsAuthentication can move forward to the traffic entry point, and each product line picks the runtime shape that fits it best rather than being forced into uniformity.
Token validation happens at the gateway, so business services only see authorized identities and authentication moves to the traffic entry point.
Wasm plugin / external authorizationThe standard integration protocol for AI agents: UIAM authorizes tools, Uniclaw calls them, NewTool exposes algorithms.
streamable HTTPThe runtime for the identity kernel and the WeCom server side, using virtual threads for high-concurrency authentication.
JVMThe agent platform runtime, with LangGraph driving the cognition-loop state machine.
Node.jsThe modular monolith and the capture kernel, delivered as a single binary — fast to start, few dependencies.
Static compilationThe algorithm kernel compiles to native and wasm targets, so one implementation serves every platform.
Native / wasm32Integration capabilities by business line
Each product line’s detail page also carries its own list of integrations.
Hand the complexity of identity, agents and private domain to one governable kernel
Whether you are replacing an existing IAM, building an agent platform, or trying to make private-domain operations actually work — start with a 30-minute architecture call. We will first judge whether this is the kind of problem we are good at, and say so plainly if it is not.