Merge pull request #14338 from pjpoulose/main

Add PIL to Knowledge & Memory

README.md

@@ -2886,6 +2886,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [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).
+- [pjpoulose/PIL](https://github.com/pjpoulose/PIL) [![pjpoulose/PIL MCP server](https://glama.ai/mcp/servers/pjpoulose/PIL/badges/score.svg)](https://glama.ai/mcp/servers/pjpoulose/PIL) 📇 🏠 🐍 🍎 🪟 🐧 - Personal Instagram Library: turns your Instagram saved posts into a private, AI-searchable knowledge base on your own machine. Vision-AI deep reads (summaries, key points, how-tos, links, tags) go into local SQLite, queried live through a read-only stdio MCP server by Cursor, Claude Code, and Claude Desktop — or as a static export for any AI tool. Code is shared, data stays home.
 
 ### ⚖️ <a name="legal"></a>Legal
 Access to legal information, legislation, and legal databases. Enables AI models to search and analyze legal documents and regulatory information.