AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
자체 호스팅 에이전트 메모리 플랫폼, 인증된 OpenAI 호환 프록시 제공, 지속 메모리·컨텍스트 조합은 3단계 동일 진입점에 적용
Self-hosted agent memory platform. An authenticated OpenAI-compatible proxy ships today; persistent memory and context assembly land on that same ingress in Phase 3.
개발 도구Python · GoGitHub @Rick1330온라인운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
Production-grade AI agent memory and context management platform (monorepo)
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
AI-agent memory, context assembly, and secure LLM proxying for multi-tenant systems.
Phases 0–3.5 are shipped. Phase 4 is in progress: Track P operator readiness is the prerequisite for redesigned Track D capability slices. The current repository contains mounted, tenant-scoped, read-only 4.D.1 context/overview and 4.D.2 metadata-only trace list/detail surfaces. These are mounted-but-provisional, not proof of production identity, deployment, hosted acceptance, full management APIs, raw provenance, replay, or operator actions.README 전문 보기 ↗지금 README 전체를 불러올 수 없습니다. 원문 링크에서 읽을 수 있습니다. 아래는 저장된 발췌입니다.
AI-agent memory, context assembly, and secure LLM proxying for multi-tenant systems.
Phases 0–3.5 are shipped. Phase 4 is in progress: Track P operator readiness is the prerequisite for redesigned Track D capability slices. The current repository contains mounted, tenant-scoped, read-only 4.D.1 context/overview and 4.D.2 metadata-only trace list/detail surfaces. These are mounted-but-provisional, not proof of production identity, deployment, hosted acceptance, full management APIs, raw provenance, replay, or operator actions.README 전문 보기 ↗