citadel-ai 1.4.0 โ 1.4.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +127 -84
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -1,39 +1,98 @@
|
|
|
1
1
|
# ๐ฐ CITADEL
|
|
2
2
|
|
|
3
|
-
**
|
|
3
|
+
**Tu vibecodes. Ta dรฉmo marche. Mais est-ce que ton projet repose sur du sable ?**
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
CITADEL helps serious vibe coders build with structure, memory, and review โ so their MVP doesn't collapse under hidden mistakes.
|
|
6
6
|
|
|
7
7
|
[](https://www.npmjs.com/package/citadel-ai)
|
|
8
8
|
[](https://opensource.org/licenses/MIT)
|
|
9
9
|
|
|
10
|
+
```bash
|
|
11
|
+
npx citadel-ai init
|
|
12
|
+
```
|
|
13
|
+
|
|
14
|
+
Works with **Claude Code** ยท **Cursor** ยท **Antigravity** ยท **Windsurf**
|
|
15
|
+
|
|
10
16
|
---
|
|
11
17
|
|
|
12
|
-
##
|
|
18
|
+
## Is this for you?
|
|
13
19
|
|
|
14
|
-
CITADEL is
|
|
20
|
+
### CITADEL is for
|
|
15
21
|
|
|
16
|
-
|
|
22
|
+
- Solo founders building their first MVP with AI
|
|
23
|
+
- Operators and PMs who vibecode internal tools
|
|
24
|
+
- Growth builders shipping fast without a dedicated dev team
|
|
25
|
+
- Non-traditional developers who want guardrails, not gatekeeping
|
|
17
26
|
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
|
|
27
|
+
### CITADEL is not for
|
|
28
|
+
|
|
29
|
+
- People looking for one-shot prompts
|
|
30
|
+
- Senior engineers who already have strong architecture discipline
|
|
31
|
+
- Teams that need a production-grade CI/CD platform
|
|
32
|
+
- Complete beginners who have never built anything with AI
|
|
33
|
+
|
|
34
|
+
---
|
|
35
|
+
|
|
36
|
+
## The problem
|
|
37
|
+
|
|
38
|
+
When you vibecode without structure:
|
|
39
|
+
|
|
40
|
+
- The AI skips architecture โ it generates code that works today and breaks tomorrow
|
|
41
|
+
- Nobody reviews โ the builder validates their own work (and misses their own mistakes)
|
|
42
|
+
- Context gets lost โ the AI forgets what was decided 3 messages ago
|
|
43
|
+
- No standards โ spaghetti code, magic numbers, business logic everywhere
|
|
44
|
+
- Security is an afterthought โ auth, encryption, compliance happen "later" (never)
|
|
45
|
+
|
|
46
|
+
You end up with a prototype that demos well and crumbles under real use.
|
|
47
|
+
|
|
48
|
+
---
|
|
49
|
+
|
|
50
|
+
## What CITADEL does
|
|
51
|
+
|
|
52
|
+
CITADEL installs a governance layer into your AI IDE. It doesn't replace your AI โ it makes it work like a disciplined team instead of a solo improviser.
|
|
21
53
|
|
|
22
|
-
|
|
54
|
+
**Forces strategic thinking first.** Before any code, a virtual C-Suite asks questions about your product, architecture, security, data, and growth. You answer. Then specs get drafted. Not the other way around.
|
|
23
55
|
|
|
24
|
-
|
|
56
|
+
**Separates building from reviewing.** The agent that writes code is never the one that reviews it. Like any serious engineering org.
|
|
25
57
|
|
|
26
|
-
|
|
27
|
-
- **42 agent personas** with distinct roles, philosophies, and immutable rules
|
|
28
|
-
- An **orchestrator** that routes work based on the current phase
|
|
29
|
-
- **Phased context loading** โ only the relevant team is loaded, not all 42 agents
|
|
30
|
-
- **Persistent memory** โ decisions, errors, and state survive across sessions
|
|
58
|
+
**Enforces safety checks before shipping.** 5 mandatory gates from inception to deployment. Security has veto power โ no exceptions.
|
|
31
59
|
|
|
32
|
-
|
|
60
|
+
**Keeps project memory across sessions.** Decisions, errors, architecture choices โ all persisted locally. The AI doesn't start from scratch every time.
|
|
33
61
|
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
62
|
+
**Loads only what's needed.** Instead of dumping 42 agent profiles into context (and burning your token quota), CITADEL loads only the team relevant to the current phase. 88% less tokens.
|
|
63
|
+
|
|
64
|
+
---
|
|
65
|
+
|
|
66
|
+
## Without CITADEL / With CITADEL
|
|
67
|
+
|
|
68
|
+
| | Without | With CITADEL |
|
|
69
|
+
|--|---------|-------------|
|
|
70
|
+
| Start | "Build me an app" โ AI dives into code | C-Suite asks: who is this for? what data? what security? |
|
|
71
|
+
| Architecture | Whatever the AI decides in the moment | Explicit ADR, reviewed by a dedicated architecture agent |
|
|
72
|
+
| Code quality | Hope for the best | Standards enforced: 200 lines/file, typed errors, no magic numbers |
|
|
73
|
+
| Review | You read it yourself (and miss things) | Independent checker agents with different perspective |
|
|
74
|
+
| Security | "We'll add auth later" | Security review at every gate. Veto power on deployment |
|
|
75
|
+
| Next session | AI forgot everything | Memory persists decisions, errors, and project context |
|
|
76
|
+
| Token usage | Full context every message (~14K tokens) | Phased loading (~1,800 tokens per phase) |
|
|
77
|
+
|
|
78
|
+
---
|
|
79
|
+
|
|
80
|
+
## How it works โ 5 steps
|
|
81
|
+
|
|
82
|
+
### Step 1: Clarify what you're building
|
|
83
|
+
The C-Suite (product, architecture, security, data, growth) asks questions before anything gets drafted.
|
|
84
|
+
|
|
85
|
+
### Step 2: Lock the strategy
|
|
86
|
+
PRD, architecture decisions, security requirements, data model โ all written to `.citadel/specs/` after your answers.
|
|
87
|
+
|
|
88
|
+
### Step 3: Build with role separation
|
|
89
|
+
Specialized maker agents build per domain (backend, frontend, mobile, API, auth, data). Each one follows strict code standards.
|
|
90
|
+
|
|
91
|
+
### Step 4: Review before shipping
|
|
92
|
+
Independent checker agents validate code quality, tests, performance, security, accessibility. Builder โ reviewer โ always.
|
|
93
|
+
|
|
94
|
+
### Step 5: Ship with memory
|
|
95
|
+
Decisions, errors, and context persist in `.citadel/memory/`. Next session picks up where you left off.
|
|
37
96
|
|
|
38
97
|
---
|
|
39
98
|
|
|
@@ -44,38 +103,34 @@ cd my-project
|
|
|
44
103
|
npx citadel-ai init
|
|
45
104
|
```
|
|
46
105
|
|
|
47
|
-
|
|
106
|
+
This creates:
|
|
48
107
|
|
|
49
108
|
```
|
|
50
109
|
your-project/
|
|
51
|
-
โโโ CLAUDE.md
|
|
52
|
-
โโโ GEMINI.md
|
|
53
|
-
โโโ .cursorrules
|
|
54
|
-
โโโ .windsurfrules
|
|
55
|
-
โโโ .claude/commands/
|
|
56
|
-
โโโ .cursor/commands/
|
|
57
|
-
โโโ .antigravity/rules.md โ Antigravity backup rules
|
|
110
|
+
โโโ CLAUDE.md โ Auto-loaded by Claude Code
|
|
111
|
+
โโโ GEMINI.md โ Auto-loaded by Antigravity
|
|
112
|
+
โโโ .cursorrules โ Auto-loaded by Cursor
|
|
113
|
+
โโโ .windsurfrules โ Auto-loaded by Windsurf
|
|
114
|
+
โโโ .claude/commands/ โ /citadel-help, /citadel-build, /citadel-review...
|
|
115
|
+
โโโ .cursor/commands/
|
|
58
116
|
โโโ .citadel/
|
|
59
|
-
โ โโโ agents/
|
|
60
|
-
โ โโโ teams/
|
|
61
|
-
โ
|
|
62
|
-
โ
|
|
63
|
-
โ
|
|
64
|
-
โ โ โโโ ...
|
|
65
|
-
โ โโโ specs/ โ PRD, ADR, Security, Data Model, Growth
|
|
66
|
-
โ โโโ memory/ โ Session state, decisions, errors (gitignored)
|
|
67
|
-
โ โโโ gates/ โ Gate progress tracking (gitignored)
|
|
68
|
-
โโโ .gitignore โ Updated automatically
|
|
117
|
+
โ โโโ agents/ โ 42 full agent personas (reference)
|
|
118
|
+
โ โโโ teams/ โ 10 team files (phased loading by IDE)
|
|
119
|
+
โ โโโ specs/ โ PRD, ADR, Security, Data Model, Growth
|
|
120
|
+
โ โโโ memory/ โ Persistent state (gitignored)
|
|
121
|
+
โ โโโ gates/ โ Gate tracking (gitignored)
|
|
69
122
|
```
|
|
70
123
|
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
|
74
|
-
|
|
75
|
-
|
|
|
76
|
-
|
|
|
124
|
+
Everything is installed. The IDE reads only what's contextual.
|
|
125
|
+
|
|
126
|
+
| IDE | How to start |
|
|
127
|
+
|-----|-------------|
|
|
128
|
+
| Claude Code | `/citadel-help` |
|
|
129
|
+
| Cursor | `/citadel-help` |
|
|
130
|
+
| Antigravity | Just start chatting |
|
|
131
|
+
| Windsurf | Just start chatting |
|
|
77
132
|
|
|
78
|
-
|
|
133
|
+
Optional CLI (needs API key):
|
|
79
134
|
```bash
|
|
80
135
|
export ANTHROPIC_API_KEY=sk-ant-... # or OPENAI_API_KEY
|
|
81
136
|
npx citadel-ai run
|
|
@@ -83,59 +138,47 @@ npx citadel-ai run
|
|
|
83
138
|
|
|
84
139
|
---
|
|
85
140
|
|
|
86
|
-
##
|
|
87
|
-
|
|
88
|
-
Most AI coding tools are one brain doing everything. CITADEL is an **organization**.
|
|
89
|
-
|
|
90
|
-
### 1. Organization > Single Agent
|
|
141
|
+
## Why it's different
|
|
91
142
|
|
|
92
|
-
|
|
93
|
-
|-------|--------|------|
|
|
94
|
-
| Command | โก ATLAS | Orchestrates, routes, explains |
|
|
95
|
-
| C-Suite | ๐๏ธ LINUS (CTO), ๐ฏ MARTY (CPO), ๐ SEAN (CGO), ๐ก๏ธ BRUCE (CISO), ๐๏ธ MONICA (CDO) | Strategic decisions |
|
|
96
|
-
| Makers (20) | UNCLE BOB, DAN, STEIPETE, KELSEY, JONY, FILIPPO, CODD, KARPATHY, HARRISON, ALEX, GRACE, CHARITY, RICH... | Build |
|
|
97
|
-
| Checkers (16) | GUIDO, KENT, BRENDAN, JAKOB, CHARLIE, AARON, ALEYDA, DATE, DEMING, FLYWAY, TRAIL... | Validate |
|
|
143
|
+
Most AI frameworks give you **more agents**. CITADEL gives you **more discipline**.
|
|
98
144
|
|
|
99
|
-
|
|
145
|
+
- **Organization > single brain.** 42 agents with distinct roles, rules, and personalities โ but loaded per phase, not all at once.
|
|
146
|
+
- **Governance > speed.** Questions before specs. Review before ship. Security veto before deploy.
|
|
147
|
+
- **Memory > amnesia.** Project decisions, architecture choices, and past errors persist locally across sessions.
|
|
148
|
+
- **Efficiency > brute force.** Phased context loading means ~1,800 tokens per phase instead of ~14,000.
|
|
100
149
|
|
|
101
|
-
|
|
150
|
+
---
|
|
102
151
|
|
|
103
|
-
|
|
104
|
-
- **5 mandatory gates** โ Inception โ Pre-Design โ Pre-Build โ Pre-Ship โ Post-Deploy
|
|
105
|
-
- **Chinese Wall** โ Maker โ Checker. The builder never reviews their own work
|
|
106
|
-
- **CISO veto** โ BRUCE can block any deployment. No override possible
|
|
107
|
-
- **Code standards in agent DNA** โ TS strict, 200 lines/file, 30 lines/function, 80% test coverage, anti-patterns auto-rejected
|
|
152
|
+
## The 42 agents
|
|
108
153
|
|
|
109
|
-
|
|
154
|
+
Each agent has a full persona: name, inspiration, philosophy, voice, immutable rules, and system prompt. All stored in `.citadel/agents/`.
|
|
110
155
|
|
|
111
|
-
|
|
156
|
+
**Strategic (C-Suite):** ATLAS (Orchestrator) ยท LINUS (CTO) ยท MARTY (CPO) ยท SEAN (CGO) ยท BRUCE (CISO) ยท MONICA (CDO)
|
|
112
157
|
|
|
113
|
-
|
|
114
|
-
|-------|------------|--------|
|
|
115
|
-
| Inception | `c-suite.md` | ~460 |
|
|
116
|
-
| Build (backend) | `cto-makers.md` | ~680 |
|
|
117
|
-
| Review (code) | `cto-checkers.md` | ~340 |
|
|
118
|
-
| Security audit | `ciso-all.md` | ~740 |
|
|
158
|
+
**Builders (Makers):** UNCLE BOB ยท DAN ยท STEIPETE ยท KELSEY ยท JONY ยท TERESA ยท STRUNK ยท DJ PATIL ยท CYRUS ยท CHAMATH ยท FILIPPO ยท MOXIE ยท MAX ยท CODD ยท KARPATHY ยท HARRISON ยท ALEX ยท GRACE ยท CHARITY ยท RICH
|
|
119
159
|
|
|
120
|
-
|
|
160
|
+
**Validators (Checkers):** GUIDO ยท KENT ยท BRENDAN ยท JAKOB ยท RAZOR ยท LISA ยท NATE ยท ALEYDA ยท PEEP ยท CHARLIE ยท WINDOW ยท DATE ยท DEMING ยท FLYWAY ยท AARON ยท TRAIL
|
|
121
161
|
|
|
122
|
-
|
|
162
|
+
`npx citadel-ai agents` lists them all with roles and teams.
|
|
123
163
|
|
|
124
164
|
---
|
|
125
165
|
|
|
126
|
-
##
|
|
127
|
-
|
|
128
|
-
**CTO Team:** โ๏ธ UNCLE BOB (Backend) ยท ๐จ DAN (Frontend) ยท ๐ฑ STEIPETE (Mobile) ยท ๐ KELSEY (DevOps) ยท ๐ก GRACE (API Design) ยท ๐ญ CHARITY (Observability)
|
|
166
|
+
## Known limitations
|
|
129
167
|
|
|
130
|
-
**
|
|
168
|
+
- **Early stage.** This is v1, actively developed. Expect rough edges.
|
|
169
|
+
- **Not autonomous.** CITADEL structures AI work โ it doesn't run unsupervised.
|
|
170
|
+
- **Not a replacement for a real team.** Great for MVPs and internal tools. For scaling to production, you still need real developers and a CTO.
|
|
171
|
+
- **IDE-dependent.** The phased loading relies on how your IDE reads context files. Behavior varies.
|
|
131
172
|
|
|
132
|
-
|
|
133
|
-
|
|
134
|
-
**CISO Team:** ๐ FILIPPO (Auth) ยท ๐ MOXIE (Encryption) ยท ๐ MAX (Compliance)
|
|
173
|
+
---
|
|
135
174
|
|
|
136
|
-
|
|
175
|
+
## Roadmap
|
|
137
176
|
|
|
138
|
-
|
|
177
|
+
- [ ] Onboarding wizard (guided first 10 minutes)
|
|
178
|
+
- [ ] Demo video (60-second Loom)
|
|
179
|
+
- [ ] More IDE-specific optimizations
|
|
180
|
+
- [ ] Plugin system for custom agents
|
|
181
|
+
- [ ] Non-code use cases (growth teams, marketing, ops)
|
|
139
182
|
|
|
140
183
|
---
|
|
141
184
|
|
|
@@ -144,10 +187,10 @@ Rules file (`GEMINI.md` etc.): ~1,200 tokens โ loaded every message.
|
|
|
144
187
|
| Command | Description |
|
|
145
188
|
|---------|-------------|
|
|
146
189
|
| `npx citadel-ai init` | Install CITADEL in your project |
|
|
147
|
-
| `npx citadel-ai run` | Interactive CLI (needs API key
|
|
190
|
+
| `npx citadel-ai run` | Interactive CLI (needs API key) |
|
|
148
191
|
| `npx citadel-ai agents` | List all 42 agents |
|
|
149
|
-
| `npx citadel-ai status` |
|
|
150
|
-
| `npx citadel-ai help` |
|
|
192
|
+
| `npx citadel-ai status` | Current phase & gate |
|
|
193
|
+
| `npx citadel-ai help` | All commands |
|
|
151
194
|
|
|
152
195
|
---
|
|
153
196
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "citadel-ai",
|
|
3
|
-
"version": "1.4.
|
|
3
|
+
"version": "1.4.1",
|
|
4
4
|
"description": "Enterprise AI dev framework. 42 agents. C-suite governance. Chinese walls. Persistent memory. You talk, they build.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"ai",
|
|
@@ -55,4 +55,4 @@
|
|
|
55
55
|
"engines": {
|
|
56
56
|
"node": ">=18.0.0"
|
|
57
57
|
}
|
|
58
|
-
}
|
|
58
|
+
}
|