{"name":"io.github.n24q02m/mnemo","slug":"n24q02m-mnemo","title":null,"description":"Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.","url":"https://mcp.market/server/n24q02m-mnemo","rating":null,"grade":"B","score":83,"certified":false,"status":"active","category":"search","tags":["search"],"presence":{"score":39,"stars":12,"forks":7,"downloads_week":505,"last_push_at":"2026-10-13T23:12:49.000Z","license":"Apache-2.0"},"uptime":null,"claimed":false,"transport":"pypi","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/n24q02m/mnemo.git","website":null,"version":"2.21.0","remotes":[],"packages":[{"registryType":"pypi","identifier":"mnemo-mcp","version":"2.21.0","runtimeHint":"uvx","transport":{"type":"streamable-http","url":"http://127.0.0.1:8000/mcp"},"environmentVariables":[{"description":"Provider API keys (format: PROVIDER_API_KEY:key,...). Select models per task with EMBEDDING_MODELS / RERANK_MODELS / LLM_MODELS (CSV provider/model, order = litellm fallback); provider is inferred from the model prefix. Empty embedding/rerank chains select Fastretrieval local ONNX/GGUF models; configured cloud chains never silently fall back to local.","isSecret":true,"name":"API_KEYS"}]}],"tools":[],"scan":null,"grade_history":[],"reviews":[]}