djasdh/interest-memory2

@djasdh/interest-memory

Cross-session long-term memory for AI agents — local Go service (~50MB RAM, SQLite-vec, verify-augmented) with bridges for DeepSeek Harness, Claude Code, Codex, Hermes, OpenClaw, opencode, pi, Reasonix.

AI 分析

核心用途是提供低资源占用的本地向量化长期记忆。适合对隐私要求高、需要跨多个 AI 客户端共享记忆的开发者。

パッケージ
@djasdh/interest-memory
バージョン
1.0.0
ライセンス
MIT
最終更新
2026/08/21

インストール

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:djasdh/interest-memory

ドキュメント

README 全文を読む ↗

Resource usage (measured)

MetricValue
Binary size~18 MB (cgo static sqlite-vec)
Idle memory~17 MB RSS (measured)
Pipeline peak<75 MB RSS
Initial footprint~20 MB (binary + empty DB)
Growth~38 MB after a week of use; mostly raw session transcripts (~71%)

session_transcripts keeps full raw text — trim externally to bound disk growth; fork.max_concurrency / verify.max_concurrency cap peak memory.