Multi-tenant AI Agent Platform

UniclawEnterprise multi-tenant AI agent platform

Digital workers that think, remember and grow. Built on NestJS 11 and Prisma 7: 25 business modules covering the cognition loop, three-tier memory, a five-layer persona, skill evolution and multi-agent collaboration; 19 built-in tools ready to use; multi-channel access via WeCom, Feishu, DingTalk, web chat and API.

Betauniclaw-copit
25
business modules
19
built-in tools
41
data models
4
cognition engines

The cognition loop is four engines wired into a closed circuit: intent extraction → planning → assessment → reflection. Each step is an independently testable module, not one long prompt.

Not another chatbot shell — an agent runtime with a cognition loop and long-term memory.

7×24
unattended service window
3 tiers
memory tiers
5 layers
persona layers
N+
multi-agent orchestration
Capabilities

What problem does it actually solve

Four core capabilities, mapped to four real business needs.

Digital workers

Replaces repetitive human effort: 7×24 responsive support, lead qualification, order follow-up and after-sales handling, with configurable capability boundaries and human-handoff policies.

Cognition engine

A LangGraph-orchestrated cognition loop: intent recognition, tool selection, result reflection and self-correction, so long task chains stay under control.

Memory system

Milvus-based vector memory and structured profiles coexist on two tracks, keeping context consistent across sessions.

Private delivery

The full stack deploys privately; models, data and memory stay inside the customer’s own network boundary.

Highlights

Capabilities at a glance

  • Four cognition engines: intent-extractor → plan-engine → assess-engine → reflect-engine
  • Three-tier memory: session → episodic → semantic, with decay and context-overflow governance
  • Five-layer persona: role, tone, boundaries, domain knowledge and behavioural policy injected in layers
  • 19 built-in tools: web search, SQL queries, chart generation, code execution, email, knowledge retrieval and more
  • Multi-agent collaboration: orchestrator, supervisor and a communication protocol
  • Multi-channel access: WeCom (SCRM pull), Feishu (push API), DingTalk (push API), web chat (WebSocket)
Code Facts

Not a product that lives in slides

The numbers below come from the real code in the uniclaw-copit repository: modules, tables, endpoints and capability items.

25
business modules
19
built-in tools
41
data models
4
cognition engines
3
channel adapter families
11
memory-related services
Stack

Tech stack

NestJS 11TypeScriptPrisma 7LangChainLangGraphMilvusMariaDBRedisMCPDocker
Other business lines
Get in touch

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.