nanzi-ai-agent-platform

🚀 开源企业级多智能体平台与 ChatBI 数据洞察平台。支持多 Agent 协作、RAG 知识增强、物理数据源直连与安全沙箱执行、Redis 长期记忆引擎，并集成多模态 EmbedChat 挂件与全方位 Token 消耗审计看板，完整 RBAC权限控制和 Harness支持。

Not yet verifiedsource: GitHubPythonMITcommit 5cdaf5418437

Python, MIT licensed. The project labels itself: agentscope, agentscope runtime, ai agents, aigc, chat bi, chatbot, dsh and harness.

nanzi-ai-agent-platform has not been verified yet.

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 30 of 100 (the mean of this project's run scores).

At a glance

verdict
Not yet verified
Argusic Score
30 / 100
recorded runs
1
last tested
stars
220
forks
58
open issues
1
watchers
5
size
133 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the most recent recorded attempt, which did not reach a verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing nanzi-ai-agent-platform, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • 11 个 apply-sql-native.sh 测试因缺少 mysql/psql 命令行客户端而失败5 minutes
  • Python 3.11 在容器中不可用，使用系统 Python 3.12.3，项目代码兼容运行
  • Node.js 18.19.1 不满足 Vite 7 前端构建要求（需 20.19+），前端无法编译
  • 容器中无 MySQL/Redis Stack/PostgreSQL/Docker 服务，服务无法启动
Install time
35 minutes
Cold machine to finish
28 minutes
Errors hit and fixed
4 hit, 0 fixed with no human help
How the result was proved
python -m pytest tests/test_admin_bootstrap_scripts.py tests/test_mail_markdown_render.py tests/test_xml_parsing.py tests/test_context_internal_constants_contract.py tests/test_conftest_redis_flush_guard.py tests/test_known_failures_baseline.py tests/test_deployment_checklist_contract.py 返回 50 passed
Model tokens used
580,723
Exact commit tested
5cdaf5418437
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

- 后端 ASGI 应用模块 (`app.main`) 编译成功，创建了 13 个路由
**测试**:
- 在无 MySQL/Redis/PostgreSQL/Docker 的容器中，运行了各类无需基础架构的测试
- `no_infrastructure` 标记的测试里，`test_admin_bootstrap_scripts.py` 等 50 个测试全部通过
- 扩展批次的 240+ 个测试通过
- 前端 Vue 构建失败：Node.js 18.19.1 不满足 Vite 7 的最低要求（20.19+）
**已知失败/错误**:
- 11 个 `apply-sql-native.sh` 测试失败 — 因 `mysql`/`psql` CLI 客户端未安装
- 无法启动服务 — 需要 MySQL 和 Redis Stack（支持 RediSearch 的版本）
- 3 个 `test_dockerignore_contract.py` 测试出错 — Docker 不可用
- 大量需要基础设施的测试因无 MySQL/Redis 而出现 ERROR（非代码本身问题）
现在给出最终 JSON 结果：

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Did not run30.000.15

Topics (from GitHub)

agentscopeagentscope-runtimeai-agentsaigcchat-bichatbotdshharnessknowledge-managementlangchainragflow

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/nanzi-ai-agent-platform.svg)](https://argusic.com/subject/nanzi-ai-agent-platform)

Questions

Does nanzi-ai-agent-platform run?
nanzi-ai-agent-platform has not been fully verified yet. No recorded run has produced a verdict yet.
How did Argusic test nanzi-ai-agent-platform?
On a fresh, disposable machine, with every command recorded. One attempt is recorded, and the full method is on the methodology page.
Where is the evidence for nanzi-ai-agent-platform?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion