Adaptive Recall

AI 애플리케이션을 위한 적응형 MCP 메모리 시스템입니다. 데이터에 가장 적합한 검색 전략을 학습하고, 인지 과학 모델을 사용해 결과를 평가하며, 지식 그래프를 자동으로 구축하고, 실제 쿼리 기록을 기반으로 모든 파라미터 변경을 검증한 후 적용합니다. 특허 출원 중입니다.

GitHub
3

문서

Adaptive Recall

Adaptive memory system for AI applications. Patent pending.

adaptiverecall.com | Documentation | Sign Up Free

What It Does

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

Connect

Sign up at adaptiverecall.com to get your server URL and API key.

MCP Configuration

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.json in your project or ~/.claude/settings.json for global access. For Gemini CLI, add to ~/.gemini/settings.json using httpUrl instead of url. For Codex, add to your Codex MCP configuration.

REST API

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

Actions

ActionDescription
storeSave a new memory. Generates embeddings and extracts entities automatically.
recallSearch memories using multi-strategy retrieval with cognitive scoring.
updateModify an existing memory. Re-embeds automatically if content changes.
forgetRemove a memory by ID or by finding the closest match to a query.
graphExplore the knowledge graph, traversing entity relationships by name and depth.
statusSystem health, memory counts, confidence distribution, and knowledge gap detection.
snapshotGet a formatted overview of stored memories, organized by type.
feedbackSend feedback directly to the Adaptive Recall developers.

Memory Types

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

Pricing

Free, Starter, Pro, and Business plans available. See adaptiverecall.com for details.

Links