Home / Biz AI Agent
Open source · Apache-2.0 · Biz AI Agent

Your IT system,
an AI agent.

Biz AI Agent is a fully open-source AI agent framework: one business system + one DSH = one AI employee. Describe the business you need, and AI coding tools such as Claude Code and Codex build and verify the agent by following the skill that ships with it.

Fully open sourceBuilt by AI coding toolsAnswers with your own rightsWith sources13 SNSPeople decide
terminal
# 1. get the open-source repository
git clone https://github.com/ITC-cloud-soft/biz-ai-agent.git
cd biz-ai-agent && npm install

# 2. open an AI coding tool (the skill is included)
claude        # or codex

# 3. ask in your own words
> Use the agent-builder skill to build a "travel expenses" AI agent
OPEN SOURCE ── PUBLIC ON GITHUBgithub.com/ITC-cloud-soft/biz-ai-agentApache License 2.0. The source code, manual, skill and examples are all public. Free for commercial use.
52 / 52Bridge v1 conformance checks
15 / 15end-to-end on a real DSH
13SNS (LINE, Slack, Teams …)
0actions the AI can confirm or approve
Core ideas

An agent is first an ordinary IT system.

No drag-and-drop flow editor. The business system is the system of record and flows are code, guarded by the manifest, the conformance suite, business tests, evals and logs.

🏛️

The business system is the record

Data, roles, who sees what and who decides: all of it stays in the business system.

✋

The AI only reads and proposes

It reads with the asking employee's own delegation; its only write is a proposal that runs when a person accepts it. People decide amounts.

🔔

The business system decides who is told

Recipients of notifications, approval cards and reports are decided by the business system, with the same rule as its web screens.

🔒

No personal data in events

IDs, numbers, dates and states only. Names, reasons and amounts are shown on the web after a permission check.

🛡️

Permissions first

Every search and every graph answer is filtered by the asker's rights before ranking. What you cannot see, the AI cannot see.

🧩

One business = one agent

One business system and one DSH make one AI employee. The whole Biz Assistant Framework plus the agent layer (knowledge, graph, settings) in one repository.

Build it with AI

Just describe the business.
An AI coding tool builds it.

You do not write the agent from scratch. Following the agent-builder skill in the repository, the AI builds everything from the business system to the knowledge, evals, settings screens and DSH settings, and verifies it with commands. The equipment-loans example was built from scratch by an AI with only this skill.

⌨️

Claude Code

Run claude at the repository root. The skill is in .claude/skills/agent-builder/ and loads automatically; /agent-builder calls it directly.

🧠

Codex

Run codex at the repository root. The skill is in .agents/skills/agent-builder/ and is discovered automatically; $agent-builder calls it directly.

✨

Any other AI coding tool

Ask it to "read skills/agent-builder/SKILL.md completely first and follow its steps".

your request (example)
Use the agent-builder skill to build a "travel expenses" AI agent:
- employees ask about the expense rules and check their own claims on LINE
- managers approve their team's claims; above 100,000 yen finance approves too
- finance gets a monthly count report
- the rules are in <your documents> (Japanese and Chinese)

What the AI does

  • Asks you the decisions first, writes them into AGENT_PLAN.md and waits (with nobody to ask: the recommended default, marked "to confirm")
  • Copies the reference implementation and writes the business system and its manifest, up to conformance 52 / 52
  • Adds knowledge and the graph, writes the evals before tuning, and builds the settings screens, SNS approvals and reports and the DSH profile
  • Verifies every step with commands and reports the results, what is not verified and what is to confirm

What you do: answer the decisions · provide the documents · review the plan and the report · try it locally · deploy

What the AI produces

What you get is an ordinary Node.js project.

Everything is created in examples/<system-id>/ as files under git.

AGENT_PLAN.mdthe decisions and their evidence: who decided what, what is to confirm, the numbers
bridge.manifest.yamlthe system's self-description (ontology): roles, entities, events, the AI's tools, screen routes
src/app.mjsthe business system: data, sign-in, business rules (hooks), business API, settings plugin, knowledge, graph, DSH gateway
src/server.mjsthe entry point: port, secrets and data directory from environment variables
knowledge/*.mdthe company documents (visibility written inside)
evals/the eval questions and their runner
test/*.test.mjstests for business rules, conformance, knowledge permissions, graph, eval floor and the settings plugin
dsh-profile/the product profile of the AI plane (DSH)
Deploy

Deploy it like any website.

01

Browser · IM: staff open the screens / webhooks from LINE and others

02

HTTPS reverse proxy: nginx, Caddy …, your domain

03

Business system (a Node.js web app): node src/server.mjs, with the DSH gateway

04

AI plane (DSH): one more process on the same machine, listening on 127.0.0.1 only

  • The business system is an ordinary Node.js web app: npm install, then NODE_ENV=production node src/server.mjs (kept running by systemd, pm2, Docker …)
  • Secrets come only from environment variables; the data directory goes on persistent storage
  • DSH is used only through the gateway inside the web app; IM webhooks point at the web app's public paths
  • Besides that you need only a model API. A database only for pgvector
How it works

What you cannot see, the AI cannot see.

A question ── an employee asks about the leave rules on LINE

01

Message: dsh-im receives it and checks the employee has linked their account

02

Tool: the knowledge search runs with that employee's delegation

03

Search by rights: the business system returns only readable sections, with sources

04

Guards: the citation guard adds the sources, the link guard removes foreign links

05

Answer: back to LINE with links to the business screens

An approval ── an administrator uploads a company document

01

Checked for personal data; approval.requested recorded in a transaction

02

The approval card goes to another administrator on LINE (never the uploader)

03

"Approve" is decided by the same mayDecide as the web, then published

04

After the index is rebuilt, a count-only report reaches the report roles

Knowledge

Three search methods. All permission-first.

Vectors and the graph compare only the chunks the asker may read. If a model fails, search falls back to BM25F and the screen shows the error code.

methodneedshow
BM25Fnothing (default)weights title, keywords, headings and text; synonyms can be tuned
RAGan embedding modelBM25F + vectors (fused by RRF), stored in pgvector or a file; the text itself is not stored
Knowledge grapha base modeldocuments extracted into entities and relations, stored as JSON; search = BM25F + graph

Administrators: /agent-settings

Models (keys as environment variable names only), document upload and approval, the search method, the organisation's IM bots (13 SNS + e-mail), approval and report settings. Japanese, English and Chinese; light and dark.

Employees: /me/sns

Issue a link code (6 digits, 10 minutes) and send "連携 123456" to the organisation's bot in a private chat. You see only your own links, and choose the notification types and quiet hours yourself.

Rules

The rules are set in code and configuration.

The AI reads and proposes

Write APIs answer delegations with 403. It never decides amounts.

The business system picks recipients

Each person is checked: "may they see it on the web?" If unsure, nothing is sent.

Only the person links

Through the business system's own sign-in. Administrators cannot do it for them.

No secrets anywhere

The repository, configuration, logs and chat hold environment variable names only.

Outbound settings stay closed

Opening one is an explicit change with a written reason; the checker verifies it.

Test on fictional data

Tests use fictional data and an isolated DSH home only.

Evals before tuning

20+ questions per language. hit@3 of 80 % or more, 0 leaks.

"Not verified" is said

Everything is checked by commands; what was not run is reported.

Quick start

Run it on your machine first.

Node.js 24.9+ and npm, plus pnpm for the end-to-end run. No database, API key or chat account needed.

terminal
git clone https://github.com/ITC-cloud-soft/biz-ai-agent.git && cd biz-ai-agent
npm install
npm run vendor:install      # once
npm test                    # about 900 tests, 0 fail
npm run e2e                 # real DSH + mock model + mock LINE: 15 / 15 PASS

Build the AI agent for your business
with AI, starting today.

All the source is public on GitHub (Apache-2.0). We also help with adoption.