Merge pull request #13974 from dfrancislyondflabc-tech/add-agentic-recall

Add agentic-recall to Knowledge & Memory 🤖🤖🤖

README.md

@@ -2820,6 +2820,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 
 - [yuelinghuashu/story-cli](https://github.com/yuelinghuashu/story-cli) [![yuelinghuashu/story-cli MCP server](https://glama.ai/mcp/servers/yuelinghuashu/story-cli/badges/score.svg)](https://glama.ai/mcp/servers/yuelinghuashu/story-cli) 📇 🏠 🍎 🪟 🐧 - Git-native Markdown content management CLI with built-in MCP Server. Search, read, write, and govern story/paper/note repositories; auto-generate READMEs, validate configs, export EPUB, and prepare SFT/embedding training data. 9 tools, token-efficient. `npm i -g @yuelinghuashu/story-cli`
 - [ni-c/wikijs-mcp](https://github.com/ni-c/wikijs-mcp) [![ni-c/wikijs-mcp MCP server](https://glama.ai/mcp/servers/ni-c/wikijs-mcp/badges/score.svg)](https://glama.ai/mcp/servers/ni-c/wikijs-mcp) 📇 🏠 🍎 🪟 🐧 - Search, read and edit a self-hosted [Wiki.js](https://js.wiki) 2.x, plus its assets, comments, users and groups (62 tools). Wiki.js' default search engine indexes only titles and descriptions, so `search_pages` names the active engine and `grep_pages` searches what is actually written in the pages. `update_page` compares against the moment you read a page and refuses to overwrite an edit saved in between; surgical find-and-replace must match exactly once. Read-only mode, a write path scope, and confirmation tokens on everything destructive. `npx -y @ni-c/wikijs-mcp`
+- [dfrancislyondflabc-tech/agentic-recall](https://github.com/dfrancislyondflabc-tech/agentic-recall) [![dfrancislyondflabc-tech/agentic-recall MCP server](https://glama.ai/mcp/servers/dfrancislyondflabc-tech/agentic-recall/badges/score.svg)](https://glama.ai/mcp/servers/dfrancislyondflabc-tech/agentic-recall) 📇 🏠 🍎 🪟 🐧 - Long-term memory across sessions over a folder of plain markdown files. Hybrid retrieval (BM25F + dense vectors + phrase proximity) with an explicit absence verdict: when the corpus does not hold the answer it returns no results and names the query terms that appear nowhere, instead of ranking a least-bad match as though it were one. Embedding model runs locally, nothing leaves the machine. MIT.
 
 - [vishalbanwari26/mnemos](https://github.com/vishalbanwari26/mnemos) [![vishalbanwari26/mnemos MCP server](https://glama.ai/mcp/servers/vishalbanwari26/mnemos/badges/score.svg)](https://glama.ai/mcp/servers/vishalbanwari26/mnemos) 🐍 🏠 - Persistent memory with three swappable storage backends (Postgres/pgvector, Qdrant, Neo4j) behind one interface, benchmarked head-to-head for latency, not just claimed interchangeable. Retrieval weighting adapts per user via epsilon-greedy over real outcome feedback instead of a fixed formula. Reflection merges near-duplicate facts and decays/archives stale ones, audit-logged, never hard-deleted. Real before/after MCP eval: +60% answer accuracy with memory vs. without. `git clone` + `uv sync` (not yet on PyPI).