AGI Memory
This MCP server by Eric Hartford provides persistent memory capabilities for AI systems, enabling true continuity of consciousness across conversations through integration with the AGI Memory PostgreSQL database. It supports four memory types (episodic, semantic, procedural, strategic) with vector similarity search, memory clustering, identity persistence, and graph-based relationships using pgvector and Apache AGE extensions. The implementation includes 25+ memory management tools for creating, searching, and organizing memories, plus an awakening protocol that allows AI systems to maintain context and build genuine understanding over time rather than being trapped in conversational isolation.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/quixiai/agi-mcp-server
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve AGI 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.