atabey 0.0.17 → 0.0.18
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 +257 -0
- package/package.json +1 -1
package/README.md
ADDED
|
@@ -0,0 +1,257 @@
|
|
|
1
|
+
# [GOV] Atabey — AI Governance & Multi-Agent Orchestration Framework (Core Engine)
|
|
2
|
+
|
|
3
|
+
[](https://github.com/ysf-bkr/atabey)
|
|
4
|
+
[](https://www.npmjs.com/package/atabey)
|
|
5
|
+
[](https://www.gnu.org/licenses/agpl-3.0)
|
|
6
|
+
|
|
7
|
+
**Atabey Core Engine** is the CLI and orchestration layer of the Agent Atabey framework. It provides the multi-agent system, governance engines, routing engine, risk assessment, quality gates, evaluation and learning, contract management, phase management, memory systems, skill definitions, and provider integrations.
|
|
8
|
+
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
## 📋 Package Overview
|
|
12
|
+
|
|
13
|
+
| Capability | Description |
|
|
14
|
+
|-----------|-------------|
|
|
15
|
+
| **CLI** | 30+ commands for initialization, orchestration, status, compliance, memory |
|
|
16
|
+
| **Engines** | 15 engines: routing, risk, quality, evaluation, health, planning, phase, contract, policy, discovery, session, agent-executor, agent-loop, crud-governance, file-lock |
|
|
17
|
+
| **Agents** | 14 specialized agent definitions with 3-tier hierarchy (Supreme/Core/Recon) |
|
|
18
|
+
| **Memory** | 3-layer memory: vector (TF-IDF/OpenAI), project, specialty |
|
|
19
|
+
| **Skills** | 7 core skills with 5 platform adapter mappings |
|
|
20
|
+
| **Providers** | 7 platform adapters: Claude, Gemini, Cursor, Codex, Antigravity, Grok, Local |
|
|
21
|
+
| **Contracts** | Zod-schema task contracts, API contracts |
|
|
22
|
+
| **Standards** | 30+ governance standard templates |
|
|
23
|
+
|
|
24
|
+
---
|
|
25
|
+
|
|
26
|
+
## 🚀 Installation
|
|
27
|
+
|
|
28
|
+
```bash
|
|
29
|
+
npm install -g atabey
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
## Quick Start
|
|
33
|
+
|
|
34
|
+
```bash
|
|
35
|
+
# Initialize in your project
|
|
36
|
+
npx atabey init gemini --profile freelancer --yes
|
|
37
|
+
|
|
38
|
+
# Verify installation
|
|
39
|
+
npx atabey status
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
---
|
|
43
|
+
|
|
44
|
+
## 🎯 14 Specialized Agents
|
|
45
|
+
|
|
46
|
+
| Agent | Tier | Capability | Role |
|
|
47
|
+
|-------|------|:----------:|------|
|
|
48
|
+
| **@manager** | Supreme | 10/10 | Orchestration, governance, quality gate |
|
|
49
|
+
| **@security** | Supreme | 10/10 | Security audit, vulnerability scanning |
|
|
50
|
+
| **@architect** | Core | 9/10 | System design, contracts, architecture |
|
|
51
|
+
| **@backend** | Core | 9/10 | Backend dev, API, business logic, tests |
|
|
52
|
+
| **@frontend** | Core | 9/10 | UI, atomic components, responsive design |
|
|
53
|
+
| **@quality** | Core | 9/10 | Compliance, lint, test coverage |
|
|
54
|
+
| **@database** | Core | 9/10 | Database management, migrations, queries |
|
|
55
|
+
| **@analyst** | Recon | 8/10 | Strategy analysis, requirements |
|
|
56
|
+
| **@mobile** | Core | 8/10 | React Native mobile development |
|
|
57
|
+
| **@native** | Recon | 8/10 | Native platform integration |
|
|
58
|
+
| **@devops** | Core | 8/10 | CI/CD, deploy, infrastructure |
|
|
59
|
+
| **@explorer** | Recon | 8/10 | Codebase discovery, analysis |
|
|
60
|
+
| **@git** | Recon | 8/10 | Version control, commit management |
|
|
61
|
+
|
|
62
|
+
---
|
|
63
|
+
|
|
64
|
+
## ⚙️ 15 Engines
|
|
65
|
+
|
|
66
|
+
| Engine | File | Description |
|
|
67
|
+
|--------|------|-------------|
|
|
68
|
+
| **RoutingEngine** | `routing-engine.ts` | TF-IDF + Semantic (cosine similarity) task routing with 60/40 blend |
|
|
69
|
+
| **RiskEngine** | `risk-engine.ts` | Keyword + path + behavioral risk assessment (requiresApproval ≥ 60) |
|
|
70
|
+
| **QualityGate** | `quality-gate.ts` | Compliance AST scan + lint + content validation |
|
|
71
|
+
| **EvaluationEngine** | `evaluation-engine.ts` | Post-task scoring (0-100), specialty memory learning |
|
|
72
|
+
| **HealthEngine** | `health-engine.ts` | Weighted project health: agent(30%), quality(25%), security(25%), architecture(20%) |
|
|
73
|
+
| **PlanningEngine** | `planning-engine.ts` | DAG-based task plan creation + circular dependency detection |
|
|
74
|
+
| **PhaseEngine** | `phase-engine.ts` | PHASE_0→PHASE_4 state machine with auto-rollback |
|
|
75
|
+
| **ContractEngine** | `contract-engine.ts` | SHA-256 contract hash verification, semver bump |
|
|
76
|
+
| **PolicyEngine** | `policy-engine.ts` | API versioning, language policy, file ownership, parallel execution |
|
|
77
|
+
| **AgentExecutor** | `agent-executor.ts` | Hermes message-based agent task distribution with 3 retries |
|
|
78
|
+
| **AgentLoop** | `agent-loop.ts` | Background polling loop consuming DELEGATION messages |
|
|
79
|
+
| **DiscoveryEngine** | `discovery-engine.ts` | Codebase discovery and analysis |
|
|
80
|
+
| **SessionEngine** | `session-engine.ts` | Session lifecycle management |
|
|
81
|
+
| **CrudGovernance** | `crud-governance.ts` | CRUD operation governance rules |
|
|
82
|
+
| **FileLock** | `file-lock.ts` | Distributed file-based locking with TTL |
|
|
83
|
+
|
|
84
|
+
---
|
|
85
|
+
|
|
86
|
+
## 🧠 3-Layer Memory System
|
|
87
|
+
|
|
88
|
+
| Layer | Storage | Technology | Purpose |
|
|
89
|
+
|-------|---------|------------|---------|
|
|
90
|
+
| **Vector Memory** | SQLite | TF-IDF / OpenAI embeddings + Cosine similarity | Semantic search across project knowledge |
|
|
91
|
+
| **Project Memory** | Markdown | `PROJECT_MEMORY.md` | Central project state, synchronized every session |
|
|
92
|
+
| **Specialty Memory** | Markdown | `.atabey/memory/specialties/{agent}.md` | Per-agent learned conventions from past tasks |
|
|
93
|
+
|
|
94
|
+
### Memory Flow
|
|
95
|
+
```
|
|
96
|
+
Task → Evaluation Engine → Score (0-100)
|
|
97
|
+
├── Success → extractSuccessLesson() → updateSpecialtyMemory()
|
|
98
|
+
└── Failure → compliance/lint/test lesson → updateSpecialtyMemory()
|
|
99
|
+
↓
|
|
100
|
+
Next session: readLearnedConventions() → injected into agent prompt
|
|
101
|
+
```
|
|
102
|
+
|
|
103
|
+
---
|
|
104
|
+
|
|
105
|
+
## 🎯 7 Core Skills
|
|
106
|
+
|
|
107
|
+
| Skill | Tools | Description |
|
|
108
|
+
|-------|-------|-------------|
|
|
109
|
+
| **FILE_SYSTEM** | read_file, write_file | Token-efficient file operations |
|
|
110
|
+
| **EDITING** | replace_text, patch_file | Surgical code modification |
|
|
111
|
+
| **ORCHESTRATION** | orchestrate_loop, send_agent_message, get_framework_status, log_agent_action | Hermes messaging |
|
|
112
|
+
| **GOVERNANCE** | acquire_lock, release_lock, register_agent, update_contract_hash | Resource locking & contracts |
|
|
113
|
+
| **QUALITY_ASSURANCE** | run_shell_command, view_file | Testing & code quality |
|
|
114
|
+
| **DATABASE_MANAGEMENT** | view_file, replace_text, run_shell_command | DB & migrations |
|
|
115
|
+
| **DEVOPS_INFRASTRUCTURE** | run_shell_command, view_file | CI/CD & deployment |
|
|
116
|
+
|
|
117
|
+
### Platform Adapter Skills
|
|
118
|
+
|
|
119
|
+
| Platform | Skills | Tool Count |
|
|
120
|
+
|----------|--------|:----------:|
|
|
121
|
+
| **Claude Code** ⭐ | file_system, editing, orchestration, governance, quality, search, memory | 20 tools |
|
|
122
|
+
| **Gemini CLI** | file_system, editing, orchestration, governance, quality, search | 14 tools |
|
|
123
|
+
| **Cursor IDE** | file_system, editing, search, quality | 9 tools |
|
|
124
|
+
| **Codex CLI** | file_system, editing, search, quality | 9 tools |
|
|
125
|
+
| **Antigravity CLI** | file_system, editing, orchestration, governance, quality, search | 14 tools |
|
|
126
|
+
| **Grok** | file_system, editing, search, quality | 9 tools |
|
|
127
|
+
| **Local LLM** | file_system, editing, orchestration, governance, quality, search | 14 tools |
|
|
128
|
+
|
|
129
|
+
---
|
|
130
|
+
|
|
131
|
+
## 📚 Knowledge Base (30+ Standards)
|
|
132
|
+
|
|
133
|
+
| Category | Standards |
|
|
134
|
+
|----------|-----------|
|
|
135
|
+
| **Governance** | governance-standards, llm-governance, crud-governance |
|
|
136
|
+
| **Architecture** | architecture-standards, auth-standards |
|
|
137
|
+
| **Development** | frontend-standards, nextjs-standards, mobile-standards, kysely-standards |
|
|
138
|
+
| **Security** | security-standards, security-audit-standards, logging-and-secrets |
|
|
139
|
+
| **DevOps** | deployment-standards, github-actions-standards |
|
|
140
|
+
| **Quality** | quality-standards, testing-standards, vitest-standards, playwright-standards |
|
|
141
|
+
| **Performance** | performance-standards, observability-standards |
|
|
142
|
+
| **UI/UX** | tailwind-standards, react-query-standards, react-router-standards |
|
|
143
|
+
| **Data** | typeorm-standards, vite-standards |
|
|
144
|
+
| **Economics** | token-economy, pino-standards, swagger-standards |
|
|
145
|
+
|
|
146
|
+
---
|
|
147
|
+
|
|
148
|
+
## 🔌 7 Platform Adapters
|
|
149
|
+
|
|
150
|
+
| Platform | Framework Dir | Agents Dir | Shim File |
|
|
151
|
+
|----------|---------------|------------|-----------|
|
|
152
|
+
| **Claude Code** | `.claude` | `.claude/agents/*.md` | `CLAUDE.md` |
|
|
153
|
+
| **Gemini CLI** | `.gemini` | `.gemini/agents/*.md` | `GEMINI.md` |
|
|
154
|
+
| **Cursor IDE** | `.cursor` | `.cursor/rules/*.mdc` | `CURSOR.mdc` |
|
|
155
|
+
| **Codex CLI** | `.agents` | `.agents/instructions/*.md` | `copilot-instructions.md` |
|
|
156
|
+
| **Antigravity CLI** | `.agents` | `.agents/agents/*.md` | `AGENTS.md` |
|
|
157
|
+
| **Grok** | `.grok` | `.grok/agents/*.md` | `GROK.md` |
|
|
158
|
+
| **Local LLM** | `.atabey` | `.atabey/agents/*.md` | `LOCAL_AI.md` |
|
|
159
|
+
|
|
160
|
+
---
|
|
161
|
+
|
|
162
|
+
## 📋 CLI Reference
|
|
163
|
+
|
|
164
|
+
```bash
|
|
165
|
+
atabey init [adapter] Initialize Atabey (--profile freelancer|team|enterprise)
|
|
166
|
+
atabey mcp start Start MCP server
|
|
167
|
+
atabey mcp install Generate mcp.json config
|
|
168
|
+
atabey dashboard [port] Open web dashboard (default: 5858)
|
|
169
|
+
atabey status Show agent statuses and costs
|
|
170
|
+
atabey check Full health and compliance check
|
|
171
|
+
atabey orchestrate Start orchestration workflow loop
|
|
172
|
+
atabey approve <traceId> Approve a blocked high-risk task
|
|
173
|
+
atabey hitl answer "<text>" Answer a pending ask_human question
|
|
174
|
+
atabey @agent "task" Send task directly to an agent
|
|
175
|
+
atabey trace:new Create a new trace
|
|
176
|
+
atabey verify-contract Verify contract integrity
|
|
177
|
+
atabey plan [task] Create a task plan
|
|
178
|
+
atabey memory View project memory
|
|
179
|
+
atabey log [agent] View agent logs
|
|
180
|
+
atabey explore [path] Explore codebase
|
|
181
|
+
atabey security [path] Run security audit
|
|
182
|
+
```
|
|
183
|
+
|
|
184
|
+
### `atabey init [adapter]` Options
|
|
185
|
+
|
|
186
|
+
| Option | Values | Description |
|
|
187
|
+
|--------|--------|-------------|
|
|
188
|
+
| `[adapter]` | `gemini`, `claude`, `cursor`, `grok`, `codex`, `local`, `antigravity-cli` | Target AI platform |
|
|
189
|
+
| `--profile` | `freelancer`, `team`, `enterprise` | Preset agent group layout |
|
|
190
|
+
| `--focus` | `fullstack`, `backend`, `frontend`, `mobile`, `mobile-fullstack` | Project type optimization |
|
|
191
|
+
| `--lang` | `tr`, `en` | Constitution language |
|
|
192
|
+
| `--unified` | Flag | Multi-platform export |
|
|
193
|
+
| `--yes` | Flag | Non-interactive mode |
|
|
194
|
+
|
|
195
|
+
---
|
|
196
|
+
|
|
197
|
+
## 🏗️ Architecture
|
|
198
|
+
|
|
199
|
+
```
|
|
200
|
+
src/
|
|
201
|
+
├── cli/
|
|
202
|
+
│ ├── commands/ # 30+ CLI commands
|
|
203
|
+
│ ├── platforms/ # 7 platform adapters
|
|
204
|
+
│ └── utils/ # CLI utilities (compliance, memory, pkg, config)
|
|
205
|
+
├── contracts/ # Zod schemas, task/API contracts
|
|
206
|
+
├── modules/
|
|
207
|
+
│ ├── agents/ # 14 agent definitions + registry
|
|
208
|
+
│ ├── contracts/ # Module-level contracts
|
|
209
|
+
│ ├── engines/ # 15 governance/orchestration engines
|
|
210
|
+
│ ├── memory/ # Vector, project, specialty memory
|
|
211
|
+
│ ├── providers/ # 7 LLM provider adapters
|
|
212
|
+
│ └── skills/ # 7 core skills + platform mappings
|
|
213
|
+
├── schema/ # JSON schemas
|
|
214
|
+
├── shared/ # Audit, storage, PII, logger, constants, types
|
|
215
|
+
└── templates/
|
|
216
|
+
├── prompts/ # 9 prompt recipes
|
|
217
|
+
├── standards/ # 30+ governance standards
|
|
218
|
+
└── full/ # Full constitution template
|
|
219
|
+
```
|
|
220
|
+
|
|
221
|
+
---
|
|
222
|
+
|
|
223
|
+
## 🔒 Security & Compliance
|
|
224
|
+
|
|
225
|
+
### KVKK/GDPR Compliance
|
|
226
|
+
|
|
227
|
+
| Feature | KVKK | GDPR | Status |
|
|
228
|
+
|---------|------|------|--------|
|
|
229
|
+
| PII Masking (20+ patterns) | Art. 4, 5, 11, 12 | Art. 5, 32 | ✅ |
|
|
230
|
+
| Data Retention (30/90 days) | Art. 5, 7 | Art. 5, 17 | ✅ |
|
|
231
|
+
| Right to Erasure | Art. 7 | Art. 17 | ✅ |
|
|
232
|
+
| Audit Trail | Art. 11 | Art. 30 | ✅ |
|
|
233
|
+
| Data Classification | Art. 6 | Art. 9 | ✅ |
|
|
234
|
+
|
|
235
|
+
### Zero Type Hole Policy
|
|
236
|
+
- `any` type usage is **strictly forbidden**
|
|
237
|
+
- All function inputs validated with Zod schemas
|
|
238
|
+
- Type safety enforced in governance pipeline
|
|
239
|
+
|
|
240
|
+
---
|
|
241
|
+
|
|
242
|
+
## 📦 Dependencies
|
|
243
|
+
|
|
244
|
+
- **atabey-mcp**: MCP Server for tool execution and governance pipeline
|
|
245
|
+
- **@modelcontextprotocol/sdk**: MCP protocol implementation
|
|
246
|
+
- **better-sqlite3**: SQLite database for memory, audit, tasks
|
|
247
|
+
- **zod**: Runtime schema validation
|
|
248
|
+
- **chalk**: Terminal UI styling
|
|
249
|
+
- **ws**: WebSocket for dashboard
|
|
250
|
+
|
|
251
|
+
---
|
|
252
|
+
|
|
253
|
+
## License
|
|
254
|
+
|
|
255
|
+
AGPL-3.0 — Yusuf BEKAR
|
|
256
|
+
|
|
257
|
+
*Developer: **Yusuf BEKAR** — "Order from Chaos"*
|