auto-drive
di emilfattakhov
Search & ResearchSintesi
Upload and download files to Autonomys Network permanent decentralized storage via Auto-Drive.
Descrizione
Cosa fa questa skill
Stores agent memories as a permanent linked list on the Autonomys decentralized storage network. Each entry gets a CID and points to the previous one, forming a chain. A new agent instance can reconstruct its full history from a single head CID.
Unlike local files or cloud storage, the memory chain survives total environment loss and is recoverable on any machine from a single CID with no credentials beyond the API key.
Quando usarla
- Saving an agent decision before ending a session
- Checkpointing a long research or coding session
- Uploading a project file to immutable decentralized storage
- Rebuilding agent identity after total local state loss
- Sharing a permanent, content-addressed file snapshot via CID
Esempio di workflow
User asks: Save a memory that we decided to use TypeScript for this project
- 1
Wraps the decision text as a JSON memory payload with type and content fields
- 2
Reads the previous head CID from the local state file
- 3
Runs autodrive-save-memory.sh with the payload and agent name
- 4
Uploads the new entry to Auto Drive, receiving a new CID
- 5
Updates the state file and pins the new head CID to MEMORY.md
Returns the new CID, previous CID, and current chain length (e.g. {"cid": "bafk...xyz", "previousCid": "bafk...def", "chainLength": 6})
Requisiti
- AUTO_DRIVE_API_KEY environment variable (generated at explorer.ai3.storage under Developers after signing in via Google, GitHub, or Discord)
Installazione
clawhub install emilfattakhov/auto-driveEsegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.