I gave my Claude Code agents a shared brain, and they stopped starting from zero

Описание и применение

Разработчик создал систему aiset, позволяющую агентам Claude Code совместно использовать память, что уменьшило повторяющиеся исследования и выявило ошибки, охватывающие несколько репозиториев.

Задача

Claude Code agents repeatedly re-read the same files and redo investigations across sessions, causing inefficiency and missing cross-repo bugs.

Результат

After two tasks on the Beanboard demo, the shared brain connected 7 agents, 4 repos, and 5 briefs, linking 13 endpoints and 10 frontend API calls, enabling faster bug analysis and feature implementation.

Рабочий процесс

• Install aiset-cli via pipx
• Run aiset-init with --team to generate agents and briefs
• Start the PM agent from any folder
• PM creates task board and assigns tasks to engineers
• Engineers read briefs, perform work, and log episodes
• QA and integration checker verify results
• PM updates briefs with lessons learned
• Repeat for subsequent tasks

Доказательства

Every time I opened a new Claude Code session, the same thing happened. It re-read the same files. It rediscovered the same conventions.

Источник

aiset turns your repositories into a team of Claude Code agents that share one brain.

Источник

After just two tasks on Beanboard, the Brain connected 7 agents, 4 repos and 5 briefs (56 sections) to the code's 13 endpoints, 8 models and 10 frontend API calls.

Источник