- pack.py: single-call context pack, budgeted, sanitized, cached, with served-id tracking that turns a citation into POSITIVE feedback - assist.py: error-signature lookup (never raw stdout, which returned 0 results in v1) - maintain.py: transactional consolidation (add merged -> verify -> delete sources) - transcript.py: JSONL parsing into non-overlapping windows via a cursor - cli.py: the twelve commands the hooks invoke; detached assist queues a block that the next prompt hook drains, keeping the hot path network-free - hooks generated from one spec; plugin manifest, MCP wiring, five skills Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
22 lines
672 B
JSON
22 lines
672 B
JSON
{
|
|
"name": "mem0-agent",
|
|
"version": "0.1.0",
|
|
"description": "Coding-agent memory that remembers your preferences, decisions and hard-won gotchas across sessions, machines and editors",
|
|
"author": {
|
|
"name": "Mem0",
|
|
"url": "https://mem0.ai"
|
|
},
|
|
"homepage": "https://docs.mem0.ai",
|
|
"repository": "https://github.com/mem0ai/mem0",
|
|
"license": "Apache-2.0",
|
|
"keywords": ["memory", "mem0", "context", "personalization"],
|
|
"userConfig": {
|
|
"api_key": {
|
|
"type": "string",
|
|
"description": "Mem0 API key from https://app.mem0.ai. Stored in your OS keychain, never written to a file.",
|
|
"sensitive": true,
|
|
"required": true
|
|
}
|
|
}
|
|
}
|