agentmemory
oleh badaramoni
DevOps & CloudRingkasan
End-to-end encrypted cloud memory for AI agents.
Deskripsi
Apa yang Dilakukan Skill Ini
AgentMemory is a cloud storage service for AI agents with end-to-end encryption, semantic search, and 100GB free storage. It stores memories, files, and secrets, syncing automatically across sessions and devices.
Local memory files lose context on restart, can't be searched semantically, and store secrets in plain text; AgentMemory replaces all three with persistent cloud storage, vector search, and an encrypted secrets vault.
Kapan Menggunakannya
- Persisting user preferences between agent sessions
- Storing API keys and credentials in an encrypted vault
- Searching past context by meaning instead of exact keywords
- Uploading documents and images for agents to reference later
- Syncing agent memory across multiple devices or restarts
Contoh Alur Kerja
User asks: Remember that I prefer TypeScript for all new projects
- 1
Search /api/memories/search to check for an existing TypeScript preference memory
- 2
Find no duplicate, POST new memory to /api/memories with content and metadata category 'preferences'
- 3
Receive confirmation response with memory ID
- 4
Auto-sync propagates the memory to cloud for retrieval in future sessions
Memory stored with ID mem_abc123; future sessions retrieve the TypeScript preference via semantic search
Persyaratan
- AgentMemory account at agentmemory.cloud
- AgentMemory API key (am_xxx format, obtained after account creation)
Instalasi
clawhub install badaramoni/agentmemoryJalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.