국가 기계를 가진 조정 대리인

MCP 서버는 클라이언트가 그들의 국가 변화가 언제 구독하고 업데이트될 수 있는 동적인 자원으로 finite 국가 기계를 호스트합니다.

기능 로드맵 및 상태

진행중인 작업. 훨씬, 몇 비트는 수행해야.

• [x] 도구 코드에 대한 단위 테스트
• [x] MCP 서버 통합 테스트 (both SSE 및 StreamableHttp)
• [x] SSE 수송
• [x] StreamableHttp 수송
• [x] 다중 동시 클라이언트 연결 (both 수송)
• [x] 동적 자원으로 퍼즐 (state machine) 만들기
• [x] 퍼즐 구독
• [x] 퍼즐 변경시 업데이트 알림 수신
• [x] 퍼즐 스냅 샷 받기 (현재 상태 및 사용 가능한 행동)
• [x] 퍼즐 상태 변경
• [ ] 퍼즐 상태에 의한 자원 생성 (제사 및 가드 프롬프트 사용)
• [ ] 트랜지션 가드 프롬프트 생성 (국가별 리소스 사용)
• [ ] 샘플링을 통해 전환 가드
• [ ] 명령줄 REPL
• [ ] REPL을 통해 데모

어떤 문제가 퍼즐 박스 주소를합니까?

협업 및 조정은 관련이 있지만 다른 문제입니다. 협업은 비-trivial 아직 상대적으로 간단한 작업을 위해 좋습니다.

puzzlebox

Coordinating agents with state machines

An MCP server that hosts finite state machines as dynamic resources that clients can subscribe to and be updated when their state changes.

Feature Roadmap and Status

What problem does puzzlebox address?

Teams need coordination

Marshalling multiple agents toward a big goal is tougher than just breaking down a request into tasks, assigning them to available agents and enabling collaboration between them.

Just as a few agents can collaborate to complete a small project, several teams of process-aware agents need to operate within distinct project phases to tackle long horizon efforts.

Consider enterprise-level software development processes:

• A large software project typically moves through a multistep, occasionally backtracking path from inception to design to building to testing to documentation to marketing to production.

• Different teams are focused on different aspects over time, informed by what’s gone before and with an eye toward an ever-changing goal that is refined according to lessons learned.

• Even within a phase, teams may cycle through their own phases, like Agile sprints. A certain amount of work is scoped for the sprint, the team works on their parts, and at the end of the sprint they decide what to tackle next. It accepts that each sprint could change the course of future development. These cycles can also be represented as puzzles.

With puzzlebox, members of agentic teams can be made process-aware, but the process itself is not subject to hallucination.

Scenario: Teams passing the torch

Three agents are working. The current state of their shared puzzle is “Specification”.

• Agent 1 is specifying the domain language.