Hecatoncheire — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Hecatoncheire (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Multi-agent continuous development system with local LLM orchestration.
⚠️ Work in Progress — This project is under active development. Some features may not work or may behave unexpectedly. Testing and verification are required before any production use. If you find this useful and want to improve it — contributions are very welcome!
⚠️ В разработке — Проект находится в стадии активной разработки. Что-то может не работать или работать не так, как ожидается. Перед использованием необходимо тестировать и проверять. Если решите допилить и использовать — пожалуйста, контрибьютьте!
[English](#english) | [Русский](#русский)
<a id="english"></a>
Hecatoncheire is an MCP (Model Context Protocol) server implementing a continuous multi-agent workflow where specialized AI agents collaborate on code development tasks. The system uses role separation and intelligent feedback loops to prevent common issues like scope creep and unnecessary complexity.
Single-agent development suffers from inherent limitations:
Multi-agent architecture with strict role separation:
Writer Agent: Implements code based on acceptance criteria Validator Agent: Reviews code and provides targeted feedback Observer Agent: Local LLM that decomposes tasks and checks alignment
User Request
↓
Observer (Local LLM)
└─ Decomposes into acceptance criteria
└─ Defines success conditions
↓
Writer
└─ Implements code
└─ Submits for review
↓
Validator
└─ Reviews against criteria
└─ Approves OR provides feedback
↓
[Loop until approved or max iterations]#### Observer Agent
#### Writer Agent (Chat 1)
write_code() tool#### Validator Agent (Chat 2)
#### 1. Task Initialization
start_task("Create recursive factorial function in Python")Observer decomposes into:
#### 2. Implementation Phase
Writer implements based on criteria and submits:
write_code(
code="def factorial(n):\n if n <= 1:\n return 1\n return n * factorial(n-1)",
description="Recursive factorial with base case"
)#### 3. Validation Phase
Validator reviews and either:
review_code(
feedback="Missing docstring and type hints",
approved=False
)#### 4. Iteration
Writer addresses feedback and resubmits. Loop continues until approval or max iterations reached.
All configuration centralized in config.yaml:
#### Model Configuration
model:
path: "/models/model.gguf"
n_ctx: 4096
n_threads: 8
n_gpu_layers: -1
tensor_split: "2,8" # Multi-GPU split
split_mode: 1#### Observer Configuration
observer:
api_url: "http://localhost:8000"
temperature: 0.65
top_k: 40
top_p: 0.9
min_p: 0.05
repeat_penalty: 1.1
max_tokens: 512#### Prompts
All prompts stored as YAML files in prompts/:
system.yaml: Observer role definitiondecompose.yaml: Task decomposition templatecheck_alignment.yaml: Alignment verification template#### Requirements
#### Setup
git clone https://github.com/srose69/hecatoncheire.git
cd hecatoncheireconfig.yaml:model:
path: "/models/your-model.gguf"docker-compose.yml:volumes:
- /path/to/your/model.gguf:/models/your-model.gguf:ro
- ./config.yaml:/app/config.yaml:rodocker compose build
docker compose up -dmcp_config_example.json):{
"mcpServers": {
"hecatoncheire": {
"command": "docker",
"args": ["exec", "-i", "hecatoncheire", "python", "src/hecatoncheire.py"]
}
}
}Single unified container running two services:
Sequential startup managed by entrypoint.sh:
docker exec#### Verify Observer API
curl http://localhost:8000/v1/models
curl -X POST http://localhost:8000/v1/completions \
-H "Content-Type: application/json" \
-d '{"prompt": "Test prompt", "max_tokens": 50}'#### Monitor Resources
docker logs hecatoncheire
nvidia-smi --query-gpu=index,name,memory.used,memory.total --format=csv -l 1Observer not responding:
docker logs hecatoncheire | grep "Observer Server"
docker port hecatoncheire 8000Out of memory:
n_ctx in config.yamltensor_split for multi-GPU setupsn_gpu_layers to offload less to GPUMCP connection issues:
docker ps<a id="русский"></a>
Hecatoncheire — MCP-сервер (Model Context Protocol), реализующий непрерывный мультиагентный рабочий процесс разработки. Специализированные AI-агенты совместно работают над задачами, используя разделение ролей и обратную связь для предотвращения расползания скоупа и избыточной сложности.
Одноагентная разработка страдает от врождённых ограничений:
Мультиагентная архитектура со строгим разделением ролей:
Writer — реализует код по критериям приёмки Validator — ревьюит код и даёт обратную связь Observer — локальная LLM, декомпозирует задачи и проверяет соответствие
Запрос пользователя
↓
Observer (локальная LLM)
└─ Декомпозиция в критерии приёмки
└─ Определение условий успеха
↓
Writer
└─ Реализация кода
└─ Отправка на ревью
↓
Validator
└─ Ревью по критериям
└─ Одобрение ИЛИ обратная связь
↓
[Цикл до одобрения или лимита итераций]#### Observer
#### Writer (Чат 1)
write_code()#### Validator (Чат 2)
#### Требования
#### Настройка
git clone https://github.com/srose69/hecatoncheire.git
cd hecatoncheireconfig.yaml:model:
path: "/models/your-model.gguf"docker-compose.yml:volumes:
- /path/to/your/model.gguf:/models/your-model.gguf:ro
- ./config.yaml:/app/config.yaml:rodocker compose build
docker compose up -dmcp_config_example.json):{
"mcpServers": {
"hecatoncheire": {
"command": "docker",
"args": ["exec", "-i", "hecatoncheire", "python", "src/hecatoncheire.py"]
}
}
}Observer не отвечает:
docker logs hecatoncheire | grep "Observer Server"
docker port hecatoncheire 8000Нехватка памяти:
n_ctx в config.yamltensor_split для мульти-GPUn_gpu_layersПроблемы с MCP:
docker psdocker logs hecatoncheireThis project is licensed under the PolyForm Shield License 1.0.0. See LICENSE for details.
Commercial use, competition, and redistribution for commercial purposes are not permitted.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.