Show HN: Adaptive Recall, persistent memory for AI assistants over MCP

AI Apps API launched Adaptive Recall, a persistent memory system for AI assistants that uses cognitive science and machine learning to improve retrieval quality over time. The API offers features like adaptive retrieval, cognitive scoring, knowledge graph construction, and self-improving ML pipelines, accessible via MCP or REST.

Adaptive Memory for AI Applications Store, recall, and forget with a memory system that learns from every interaction. Retrieval quality improves automatically over time, powered by cognitive science and machine learning. Get Started Free /auth.php?action=signup Beyond Vector Search Most memory APIs store embeddings and search by cosine similarity. Adaptive Recall does that and five layers more. Standard Memory API Adaptive Recall +Four retrieval strategies running in parallel +ACT-R cognitive scoring from 30 years of research +Automatic knowledge graph construction +Memory lifecycle with confidence evolution +Evidence-gated parameter learning +Self-verification of retrieval quality +Curiosity-driven knowledge gap detection +ML pipeline that trains on your usage patterns What Makes It Different Six capabilities that no other memory API offers, working together in every query. Adaptive Retrieval Four search strategies run in parallel: vector similarity, temporal recency, full-text keyword, and knowledge graph traversal. The system learns which strategies to prioritize for each type of query. Learn more → /features/ retrieval Cognitive Scoring Results are ranked using ACT-R activation modeling from cognitive science. Recency, access frequency, entity connections, and validated confidence all factor into which memories surface first. Learn more → /features/ scoring Knowledge Graph Entities and relationships are extracted automatically from stored memories. The graph becomes a retrieval pathway, finding relevant information through connections rather than just text similarity. Learn more → /features/ graph Memory Lifecycle Memories are not static rows in a database. They progress through stages, gain or lose confidence based on corroborating evidence, and fade naturally when no longer accessed. Learn more → /features/ lifecycle Self-Improving System The system trains ML models on your usage data, validates every parameter change against real query history, and monitors its own retrieval quality. It gets better the more you use it. Learn more → /features/ learning Simple API Eight tools: store, recall, update, forget, graph, status, snapshot, feedback. Works over MCP for Claude Code and other CLI tools, or plain HTTP REST for any application. Bearer token auth, JSON in and out. Learn more → /features/ api Adaptive Recall is built and maintained by AI Apps API https://www.aiappsapi.com/ , the company behind a family of AI tools and custom agent systems.