{
  "markdown": "# Adaptive Recall\n\nAdaptive memory system for AI applications. Patent pending.\n\n[adaptiverecall.com](https://adaptiverecall.com) | [Documentation](https://adaptiverecall.com/docs.php) | [Sign Up Free](https://adaptiverecall.com/auth.php?action=signup)\n\n## What It Does\n\nAdaptive Recall is a hosted memory server that stores, retrieves, and manages long-term memory for AI applications. It connects via MCP or REST API.\n\n- **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\n- **Cognitive scoring**: results ranked using ACT-R activation modeling from cognitive science, factoring in recency, access frequency, entity connections, and validated confidence\n- **Knowledge graph**: entities and relationships extracted automatically from stored memories, used as a retrieval pathway alongside text similarity\n- **Memory lifecycle**: memories progress through stages, gain or lose confidence based on corroborating evidence, and fade naturally when unused\n- **Self-improving**: ML models train on your usage patterns, every parameter change must pass statistical validation against real query history before being adopted\n- **Retrieval quality monitoring**: the system verifies its own retrieval consistency and identifies knowledge gaps\n\n## Connect\n\nSign up at [adaptiverecall.com](https://adaptiverecall.com/auth.php?action=signup) to get your server URL and API key.\n\n### MCP Configuration\n\nAdd to your MCP client config (Claude Code, Codex, Cursor, or any MCP-compatible tool):\n\n```json\n{\n  \"mcpServers\": {\n    \"adaptive-recall\": {\n      \"type\": \"url\",\n      \"url\": \"https://YOUR_SERVER_URL/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\nFor 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.\n\n### REST API\n\nEvery action is also available as an HTTP endpoint at `https://YOUR_SERVER_URL/v1/`. All requests require a Bearer token in the Authorization header.\n\n## Actions\n\n| Action | Description |\n|--------|-------------|\n| **store** | Save a new memory. Generates embeddings and extracts entities automatically. |\n| **recall** | Search memories using multi-strategy retrieval with cognitive scoring. |\n| **update** | Modify an existing memory. Re-embeds automatically if content changes. |\n| **forget** | Remove a memory by ID or by finding the closest match to a query. |\n| **graph** | Explore the knowledge graph, traversing entity relationships by name and depth. |\n| **status** | System health, memory counts, confidence distribution, and knowledge gap detection. |\n| **snapshot** | Get a formatted overview of stored memories, organized by type. |\n| **feedback** | Send feedback directly to the Adaptive Recall developers. |\n\n## Memory Types\n\nWhen storing memories, assign a type that affects how the memory is managed:\n\n**Learning types** (evolve over time, gain/lose confidence, have lifecycle stages):\n- `general_knowledge` - facts, observations, reference information\n- `user_knowledge` - information about people and their preferences\n\n**Lookup types** (static reference, no lifecycle):\n- `callable_scripts` - tool and script references\n- `work_project` - project tracking, tasks, deadlines\n- `cross_reference` - pointers to external information and resources\n- `learned_procedure` - multi-step workflows and procedures\n\n## Pricing\n\nFree, Starter, Pro, and Business plans available. See [adaptiverecall.com](https://adaptiverecall.com/pricing.php) for details.\n\n## Links\n\n- [Website](https://adaptiverecall.com)\n- [Documentation](https://adaptiverecall.com/docs.php)\n- [Sign Up](https://adaptiverecall.com/auth.php?action=signup)\n",
  "bytes": 3936,
  "sha": "b18e41d6aa1a3940e6d4af9f7231cd2a7bb704cc2e2e7b7fc1c4af7c2bff62c5",
  "repo_slug": "aiappsapi/adaptive-recall",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_aiappsapi_adaptive_recall_1740bba3/readme"
}