{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_d3myp2eazvvd","handle":"iflow-mcp-belindamo-kg-mem","url":"https://wellknown.network/agents/iflow-mcp-belindamo-kg-mem","links":{"self":"https://wellknown.network/agents/iflow-mcp-belindamo-kg-mem/record.json","html":"https://wellknown.network/agents/iflow-mcp-belindamo-kg-mem","markdown":"https://wellknown.network/agents/iflow-mcp-belindamo-kg-mem/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-belindamo-kg-mem","status":"https://wellknown.network/api/v1/agents/iflow-mcp-belindamo-kg-mem/status","claim":"https://wellknown.network/agents/iflow-mcp-belindamo-kg-mem/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-belindamo-kg-mem/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-belindamo-kg-mem/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-belindamo-kg-mem/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-belindamo-kg-mem/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-belindamo-kg-mem","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_belindamo-kg_mem","summary":"A Model Context Protocol (MCP) server that implements a knowledge graph-based memory system with AI-powered entity and relation extraction","description":"# KG Memory: Knowledge Graph Memory with a MCP Server\n\nA Model Context Protocol (MCP) server that implements a **heavily typed** knowledge graph-based memory system with AI-powered entity and relation extraction. Unlike other memory systems that rely on basic summarization or unstructured storage, our system uses **structured ontologies** to extract meaningful, typed relationships from unstructured text.\n\n## Why Choose a Heavily Typed Approach?\n\nMost AI memory systems treat information as unstructured blobs or simple key-value pairs. This system is different - we use **strongly typed ontologies** that define exactly what kinds of entities and relationships exist in your domain. This means:\n\n- **Predictable structure** - You know exactly what types of information will be extracted\n- **Domain-specific accuracy** - Tailored extraction for your specific use case\n- **Relationship validation** - Only valid connections between entity types are allowed\n- **Query precision** - Ask complex questions about specific relationship patterns\n\n## Comparison with Other Memory Systems\n\nWe're the only system that combines **heavy typing** with **local storage** and **native MCP integration**, making us ideal for developers who want predictable, domain-specific memory extraction without external dependencies.\n\n| Feature                | **kg\\_mcp** (Ours)                     | Graphiti/Zep                                                   | Mem0                               | Letta                         | GraphRAG               |\n| ---------------------- | -------------------------------------- | -------------------------------------------------------------- | ---------------------------------- | ----------------------------- | ---------------------- |\n| **Type System**        | ✅ **Heavily typed ontologies**         | ⚡ Temporal knowledge graphs                                    | ❌ Unstructured memories            | ❌ Unstructured storage        | ❌ Community summaries  |\n| **Str…","publisher":null,"homepage":"https://github.com/belindamo/kg_mem","repository":"https://github.com/belindamo/kg_mem","version":"0.1.2","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_belindamo-kg_mem","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"derived"},{"slug":"knowledge.memory","name":"Agent Memory","confidence":0.756,"provenance":"derived"}],"categories":["knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_belindamo-kg_mem","registry":"pypi","observedAt":"2026-11-09T07:25:37.859Z","publishedAt":"2026-02-14T01:49:25.377820Z","latestVersion":"0.1.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_belindamo-kg_mem","url":"https://pypi.org/project/iflow-mcp_belindamo-kg_mem/","firstSeenAt":"2026-09-09T18:20:42.384Z","fetchedAt":"2026-11-09T07:24:38.660Z","normalizedAt":"2026-11-09T07:24:38.660Z"}]},"firstSeenAt":"2026-09-09T18:20:42.384Z","updatedAt":"2026-11-09T07:25:37.859Z"}