self-optimization
SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.
소스 정보
- 저장소
- a5c-ai/babysitter
- 최근 소스 활동
- 2026년 6월 1일 07:46
- 감지된 SKILL.md 언어
- 영어
- 스타
- 1,832
- 포크
- 113
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
파일 탐색기
2 개 파일SKILL.md 표시 중
SKILL.md
소스 지침 · 읽기 전용 미리보기- name
- self-optimization
- description
- SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.
- allowed-tools
- Read, Write, Edit, Bash, Grep, Glob, WebFetch, WebSearch, Agent, AskUserQuestion
- graph
- {"domains":["domain:software-engineering"],"skillAreas":["skill-area:agentic-loops","skill-area:orchestration-loop"],"workflows":["workflow:feature-development"],"topics":["topic:developer-experience"],"roles":["role:tech-lead","role:backend-engineer"]}
- Improving routing and agent selection over time
- Adapting to new project patterns without forgetting old ones
- Building cross-session intelligence
## SONA Cycle
1. **Extract Patterns** - Mine execution data for recurring patterns
2. **RETRIEVE** - Search ReasoningBank for matching trajectories
3. **JUDGE** - Evaluate trajectory applicability in current context
4. **DISTILL** - Compress and store new entries
5. **Adapt** - Update weights with EWC++ regularization
## Anti-Forgetting (EWC++)
- Elastic Weight Consolidation prevents overwriting previously learned patterns
- Fisher information matrix tracks parameter importance
- Configurable regularization penalty for new adaptations
## RL Algorithms
Q-Learning, SARSA, PPO, DQN, A2C, TD3, SAC, DDPG, Rainbow
## Agents Used
- `agents/optimizer/` - Performance tuning
- `agents/adaptive-queen/` - Real-time adaptation
## Tool Use
Invoke via babysitter process: `methodologies/ruflo/ruflo-intelligence`
GitHub에서 보기