Add deadends.dev to Knowledge & Memory

Structured database of dead ends for AI agents: what does not work for a
given error and why, with workarounds, success rates and an error
transition graph. Covers code errors and country-specific real-world
rules where generic answers are most often wrong.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0199S8ifL4cWxaFzgAjaCkMR

README.md

@@ -2280,6 +2280,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [dcostenco/prism-mcp](https://github.com/dcostenco/prism-mcp) [![dcostenco/BCBA MCP server](https://glama.ai/mcp/servers/dcostenco/BCBA/badges/score.svg)](https://glama.ai/mcp/servers/dcostenco/BCBA) 📇 🏠 🍎 🪟 🐧 - Zero-config persistent memory for AI agents with local SQLite. Mind Palace web dashboard, time travel (rewind/replay sessions), agent telepathy (cross-client memory sharing), code mode templates, morning briefings, and progressive context loading. 25 tools, 6 resources, 4 prompts.
 - [darktw/usecortex-mcp](https://github.com/darktw/usecortex-mcp) [![darktw/usecortex-mcp MCP server](https://glama.ai/mcp/servers/darktw/usecortex-mcp/badges/score.svg)](https://glama.ai/mcp/servers/darktw/usecortex-mcp) ☁️ - Persistent knowledge memory for AI agents. Two-way flow: read context into projects and write discoveries back. Structured by topic with AES-256 encryption.
 - [davidgut1982/lore-mcp](https://github.com/davidgut1982/lore-mcp) [![davidgut1982/lore-mcp MCP server](https://glama.ai/mcp/servers/davidgut1982/lore-mcp/badges/score.svg)](https://glama.ai/mcp/servers/davidgut1982/lore-mcp) 🐍 🏠 ☁️ 🍎 🪟 🐧 - Persistent knowledge layer for AI agents. KB, investigation threads, journal with multi-agent attribution. SQLite/PostgreSQL/Supabase.
+- [dbwls99706/deadends.dev](https://github.com/dbwls99706/deadends.dev) 🐍 ☁️ 🏠 🍎 🪟 🐧 - Structured knowledge of what does NOT work. 2,400+ entries across 54 domains record the dead ends for an error - the fix that looks right and fails, and why - alongside workarounds with success rates and an error transition graph. Covers code errors and country-specific real-world rules (visa, banking, legal, emergency) where generic answers are most often wrong. `pip install deadends-dev`, or hosted at `https://deadends.dev/mcp`
 - [decisionnode/DecisionNode](https://github.com/decisionnode/DecisionNode) [![decisionnode/DecisionNode MCP server](https://glama.ai/mcp/servers/decisionnode/DecisionNode/badges/score.svg)](https://glama.ai/mcp/servers/decisionnode/DecisionNode) 📇 🏠 🍎 🪟 🐧 - Record development decisions as structured JSON, embed as vectors via Gemini, and search semantically over MCP. Shared store across Claude Code, Cursor, Windsurf, and any MCP client. CLI + MCP server, local-only, free Gemini embedding tier.
 - [giuliohome-org/doc-manager](https://github.com/giuliohome-org/doc-manager) [![giuliohome-org/doc-manager MCP server](https://glama.ai/mcp/servers/giuliohome-org/doc-manager/badges/score.svg)](https://glama.ai/mcp/servers/giuliohome-org/doc-manager) 🦀 ☁️ - Personal document vault on Azure Blob Storage with a built-in MCP server. Client-side AES-256-GCM zero-knowledge encryption: encrypted docs stay opaque to Claude, plaintext docs are fully readable, writable, and searchable from chat.
 - [Destrayon/Connapse](https://github.com/Destrayon/Connapse) [![Destrayon/Connapse MCP server](https://glama.ai/mcp/servers/Destrayon/Connapse/badges/score.svg)](https://glama.ai/mcp/servers/Destrayon/Connapse) #️⃣ 🏠 🍎 🪟 🐧 - Self-hosted knowledge backend for AI agents with hybrid vector + keyword search, container-isolated indexes, and 11 MCP tools. .NET, Docker-ready.