kweaver-core Agent工作流

(Same deploy/ directory as step 2)

Minimum installation — recommended for first-time experience

./deploy.sh kweaver-core install --minimum

./deploy.sh kweaver-core install --set auth.enabled=false --set businessDomain.enabled=false

Full installation (includes auth & business-domain modules)

./deploy.sh kweaver-core install

Minimum install (no auth):

kweaver auth login https://<node-ip> -k

Full install: sign in as the user onboard.sh created (default password 111111 unless you overrode it):

kweaver auth login https://<node-ip> -u test -p '<password>' -k

kweaver bkn list

or with npx instead of a global install:

Install the SDK on the client

After deploying KWeaver Core, we recommend installing kweaver-sdk as your next step. The SDK provides the kweaver CLI and AI Agent Skills — the primary way to interact with the platform.

kweaver-sdk gives AI agents (Claude Code, GPT, custom agents, etc.) access to KWeaver knowledge networks and Decision Agents via the kweaver CLI. It also provides Python and TypeScript SDKs for programmatic integration.

Install the CLI with:

npm install -g @kweaver-ai/kweaver-sdk

Or run it without a global install:

npx kweaver --help

Install

Requires Node.js 22+ (same as @kweaver-ai/kweaver-sdk on npm). Credentials are stored under ~/.kweaver-admin/platforms/, isolated from ~/.kweaver/.

npm install -g @kweaver-ai/kweaver-admin
kweaver-admin --version

🚀 Quick Start

1. Prerequisites & planning — read the Deployment Guide and satisfy its prerequisites. Linux is the supported target for full installs; macOS local dev (kind) is optional — see Mac install (dev) (中文).
2. Pre-install host check / fix with preflight.sh (recommended)

On the target install host, run a system check before deploy.sh. It verifies kernel / sysctl / containerd / kubectl / helm / Node / kweaver CLIs and can fix what's missing (each fix is opt-in unless -y):

git clone https://github.com/kweaver-ai/kweaver-core.git
cd kweaver-core/deploy
chmod +x preflight.sh deploy.sh onboard.sh

sudo bash ./preflight.sh                # check-only (default)
sudo bash ./preflight.sh --fix          # check + interactive fixes
sudo bash ./preflight.sh --fix -y       # auto-approve every fix
sudo bash ./preflight.sh --list-fixes   # preview which fixes would run, no changes
sudo bash ./preflight.sh --help         # all flags (--role, --skip, --report, --output=json, …)

Exit codes: 0 OK, 1 any FAIL, 2 only WARN. Use --report=/tmp/preflight.txt to keep a full log.

1. Run installation scripts:

```bash

🎬 Demo Video

Watch the KWeaver demo on Bilibili.

<a id="toc-quick-start"></a>

Try with Demo Environment

No deployment needed — Apply for a trial first, then connect your AI agent to the demo environment (for the web UI, visit KWeaver DIP).

npx skills add https://github.com/kweaver-ai/kweaver-sdk \
  --skill kweaver-core --skill create-bkn

npm install -g @kweaver-ai/kweaver-sdk
kweaver auth login https://dip-poc.aishu.cn -k

Then ask your AI agent (Cursor, Claude Code, etc.) using natural language:

List all knowledge networks
What object types are in the supply chain knowledge network?
Search the supply chain knowledge network for "supply chain risks"
Show 2 sample customer records
List all Decision Agents
Chat with Agent xxx, ask "What is the current inventory status?"

Or use /kweaver-core slash commands (the skill takes over automatically):

/kweaver-core List all knowledge networks
/kweaver-core What's in the supply chain knowledge network?
/kweaver-core Search knowledge network for "supply chain risks"
/kweaver-core Show 2 sample customer records from the knowledge network
/kweaver-core List all Decision Agents
/kweaver-core Chat with Agent <agent-id>, ask "What is the current inventory status?"

Demo access: Apply for a trial if needed.

Or via environment variables

export KWEAVER_BASE_URL=https://<access-address> export KWEAVER_ADMIN_TOKEN=<bearer-token> # falls back to KWEAVER_TOKEN ```

--api_server_address IP bound to a local network interface for K8s API server (must be a real NIC IP)

./deploy.sh kweaver-core install \ --access_address=<your-ip> \ --api_server_address=<your-ip>

./deploy.sh --help

4. **Verify the deployment**:

🛠️ KWeaver SDK

<a id="toc-kweaver-core-and-sdk"></a>

TypeScript & Python SDK

Minimal example (after CLI login or equivalent credentials):

import kweaver from "@kweaver-ai/kweaver-sdk/kweaver";
kweaver.configure({ config: true, bknId: "your-bkn-id", agentId: "your-agent-id" });

const results = await kweaver.search("What risks exist in the supply chain?");
const reply   = await kweaver.chat("Summarise the top 3 risks");
await kweaver.weaver({ wait: true });   // rebuild BKN index

import kweaver
kweaver.configure(config=True, bkn_id="your-bkn-id", agent_id="your-agent-id")

results = kweaver.search("What risks exist in the supply chain?")
reply   = kweaver.chat("Summarise the top 3 risks")

For streaming, KWeaverClient, and the full API surface, see the kweaver-sdk repository docs and examples.

<a id="toc-kweaver-admin"></a>

Unstructured Data Q&A — Cross-Platform Comparison

Based on 145 HR scenario samples (resume corpus with 118 multi-format PDFs), covering simple information lookup, cross-section experience analysis, and multi-hop comprehensive reasoning. All platforms used DeepSeek V3.2 + BGE M3-Embedding with identical data sources, tested in Agentic mode.

KWeaver Core is the only platform that breaks the traditional RAG "performance impossible triangle" — achieving >99% accuracy while keeping inference cost and latency at production-ready levels. Dify trades high token consumption (1.7x) for decent accuracy; BiSheng sacrifices reasoning depth for speed; RAGFlow falls behind on both accuracy and latency.