Continuo Memory
A persistent memory system for MCP that implements hierarchical compression and semantic search using ChromaDB and sentence transformers. Built by D.D. and Gustavo Porto, it provides three-tier memory storage (N0 chunks, N1 micro-summaries, N2 meta-summaries) with automatic compression of older content to maintain efficiency while preserving context. The server offers tools for storing content, performing semantic searches, and retrieving memory statistics, supporting both local embeddings via sentence-transformers and cloud-based OpenAI embeddings. Useful for applications requiring long-term context retention, knowledge base management, and RAG-based retrieval where traditional context windows are insufficient.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/gtokai/continuo-memory-mcp
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Continuo Memory from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.