Repository intelligence

rojim666/SztuCode

GitHub

本地优先的 AI 编程 Agent,支持 TUI/桌面端、工具权限、会话记忆、Skills、Subagents 与 MCPA local-first AI coding agent with TUI and desktop clients, tool permissions, memory, Skills, Subagents, and MCP support.。

CLOUDM0N decision
REVIEW BEFORE ADOPTION
Trust REVIEW · 45/100
Good fit if

Teams whose requirements match this repository’s core capability.

Watch out for

Review deployment and security evidence before production adoption.

Practical intelligence

What matters before you adopt it

Best for
Teams whose requirements match this repository’s core capability.
Main trade-offs
Review deployment and security evidence before production adoption.
Trust & CVEs

Security evidence without the noise

Trust remains a decision signal; CVEs and scanner evidence explain what is driving the risk.

Security findings
4
CLOUDM0N scanner findings
Critical
0
High
1
Medium
3
Low
0
View trust evidence & security findings
Why this score
No trust rationale was stored for this scan.
CLOUDM0N findings
HIGH
Remote download piped or chained into a shell requires manual review. 2 sample match(es) found.
MEDIUM
The project can spawn operating-system processes; review command construction and input handling. 5 sample match(es) found.
MEDIUM
Broad permission or elevated-command pattern detected. 5 sample match(es) found.
MEDIUM
Dockerfile does not end with an explicit non-root USER.
Architecture from code19 modules · 5 edges
Structural evidence

Modules and dependency edges extracted from repository code. This is code evidence, not README inference.

Code files
665
Modules
19
Dependency edges
5
Core modules
desktop
56 files
npm
2 files
packages/agent-core
7 files
packages/ai
5 files
packages/cli
3 files
packages/client
7 files
packages/evaluation
3 files
packages/protocol
3 files
packages/runtime-ts
180 files
packages/server
8 files
packages/session
7 files
packages/session-fs
4 files
Dependency flow
desktoppackages/protocol
desktopscripts
npmscripts
packages/runtime-tsscripts
scriptspackages/cli
Detected languages
Python · TypeScript · JavaScript · Rust
Detected frameworks
Architecture evidence details
flowchart TD
    %% sztucode — high-level architecture (DRAFT, refine me)
    n0["desktop · 56 files"]
    n1["npm · 2 files"]
    n2["packages/agent-core · 7 files"]
    n3["packages/ai · 5 files"]
    n4["packages/cli · 3 files"]
    n5["packages/client · 7 files"]
    n6["packages/evaluation · 3 files"]
    n7["packages/protocol · 3 files"]
    n8["packages/runtime-ts · 180 files"]
    n9["packages/server · 8 files"]
    n10["packages/session · 7 files"]
    n11["packages/session-fs · 4 files"]
    n12["packages/telemetry · 5 files"]
    n13["py-runtime · 367 files"]
    n14["scripts · scripts · 8 files"]
    n0 --> n7
    n0 --> n14
    n1 --> n14
    n8 --> n14
    n14 --> n4
    class n14 infra
    classDef infra fill:#b35c00,color:#ffffff,stroke:#8f4a00
Agent handoff
Use with any agent
JSON API
Alternatives

Nearby repositories worth comparing before adoption.

Compare top options →
holaOS
holaboss-ai/holaOS
71
Fit

holaOS คือ Agentic OS ที่ทำให้ AI Agent สามารถทำงานดิจิทัลได้ทุกอย่างบนคอมพิวเตอร์ของคุณ ไม่ว่าจะเป็นการจัดการไฟล์ ท่องเว็บ หรือรันโปรแกรมต่างๆ ผ่าน Natural Language ด้วย Electron + TypeScript + MCP Protocol ที่ Open Source สำหรับ Developer ที่อยากสร้าง Desktop AI Agent ของตัวเอง

Trust REVIEW · 45
Compare →
CowAgent
zhayujie/CowAgent
64
Fit

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)

Trust REVIEW · 35
Compare →
headroom
headroomlabs-ai/headroom
63
Fit

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Trust REVIEW · 45
Compare →