Adaptive Recall

Adaptive Recall is a hosted memory server that stores, retrieves, and manages long-term memory for AI applications. It connects via MCP or REST API.

- Multi-strategy retrieval: four search strategies run in parallel (vector similarity, temporal recency, full-text keyword, knowledge graph traversal) and the system learns which to prioritize for each type of query
- Cognitive scoring: results ranked using ACT-R activation modeling from cognitive science, factoring in recency, access frequency, entity connections, and validated confidence
- Knowledge graph: entities and relationships extracted automatically from stored memories, used as a retrieval pathway alongside text similarity
- Memory lifecycle: memories progress through stages, gain or lose confidence based on corroborating evidence, and fade naturally when unused
- Self-improving: ML models train on your usage patterns, every parameter change must pass statistical validation against real query history before being adopted
- Retrieval quality monitoring: the system verifies its own retrieval consistency and identifies knowledge gaps

Add to your MCP client config (Claude Code, Codex, Cursor, or any MCP-compatible tool):

{ "mcpServers": { "adaptive-recall": { "type": "url", "url": "https://YOUR_SERVER_URL/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

For Claude Code, add this to.mcp.jsonin your project or~/.claude/settings.jsonfor global access. For Gemini CLI, add to~/.gemini/settings.jsonusinghttpUrlinstead ofurl. For Codex, add to your Codex MCP configuration.

Every action is also available as an HTTP endpoint athttps://YOUR_SERVER_URL/v1/. All requests require a Bearer token in the Authorization header.

When storing memories, assign a type that affects how the memory is managed:

Learning types(evolve over time, gain/lose confidence, have lifecycle stages):

- general_knowledge- facts, observations, reference information
- user_knowledge- information about people and their preferences

Lookup types(static reference, no lifecycle):

- callable_scripts- tool and script references
- work_project- project tracking, tasks, deadlines
- cross_reference- pointers to external information and resources
- learned_procedure- multi-step workflows and procedures

Self-hosted Rust-based MCP server for AI agent memory — persistent, queryable memory with hybrid search, knowledge graphs, built-in embeddings, and 14 core tools (expandable to 86+ with profile-based tiering).

Self-improving MCP memory server for AI agents. One command, no cloud, no config. Hybrid search, feedback loop quality system, dashboard UI, auto-linking knowledge graph. Gets better the more you use it.

Persistent memory for AI agents using a semantic knowledge graph. Store, retrieve, and connect memories with semantic search — so your AI remembers context across sessions.

🏠 🍎 🪟 🐧 - A self-contained Memory server with single-binary architecture (embedded DB & models, no dependencies). Provides persistent semantic and graph-based memory for AI agents.

Smriti is a Model Context Protocol (MCP) server that provides persistent, graph-based memory for LLM applications. Built on LadybugDB (embedded property graph database), it uses EcphoryRAG-inspired multi-stage retrieval - combining cue extraction, graph traversal, vector similarity, and multi-hop association - to deliver human-like memory recall.

MCP-native memory layer for Claude Code, Cursor, Cline, Continue, and 16 other AI tools. Hybrid search (BM25 + pgvector + graph), self-hosted on Supabase + Vercel, 100% MIT, no paywall.

Highly efficient context management for agentic AI: MCP code search, evidence packs, graph context, and memory for large projects.

Self-hosted MCP server giving AI agents persistent memory — Markdown source of truth, hybrid BM25+embedding search, typed graph relations.

Authenticated MCP and agent gateway for Forge Cascade private AI memory, provenance, graph search, and capsule lineage.