diff --git a/README.md b/README.md index 13fdd43e8..a161216fb 100644 --- a/README.md +++ b/README.md @@ -2146,6 +2146,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to - [tverney/mcp-agent-memory](https://github.com/tverney/mcp-agent-memory) [![tverney/mcp-agent-memory MCP server](https://glama.ai/mcp/servers/tverney/mcp-agent-memory/badges/score.svg)](https://glama.ai/mcp/servers/tverney/mcp-agent-memory) 📇 🏠 🍎 - Persistent agent memory via filesystem-native consolidation daemon. Agents read/write/search memory through MCP; a background daemon handles consolidation and extraction. Works with Kiro, Claude Desktop, Cursor, and any MCP client. `npx mcp-agent-memory --setup` - [memstate-ai/memstate-mcp](https://github.com/memstate-ai/memstate-mcp) [![memstate-mcp MCP server](https://glama.ai/mcp/servers/memstate-ai/memstate-mcp/badges/score.svg)](https://glama.ai/mcp/servers/memstate-ai/memstate-mcp) 📇 ☁️ - Versioned, structured memory for AI agents. Stores facts as keypaths with full version history, automatic conflict detection, and O(1) token retrieval. - [michael-denyer/memory-mcp](https://github.com/michael-denyer/memory-mcp) 🐍 🏠 🍎 🪟 🐧 - Two-tier memory with hot cache (instant injection) and cold semantic search. Auto-promotes frequently-used patterns, extracts knowledge from Claude outputs, and organizes via knowledge graph relationships. +- [michielinksee/linksee-memory](https://github.com/michielinksee/linksee-memory) [![linksee-memory MCP server](https://glama.ai/mcp/servers/michielinksee/linksee-memory/badges/score.svg)](https://glama.ai/mcp/servers/michielinksee/linksee-memory) 📇 🏠 🍎 🪟 🐧 - Local-first cross-agent memory with a 6-layer structure, Ebbinghaus-style forgetting curve, and drift detection that catches when code diverges from past decisions. One SQLite file shared across Claude Code, Cursor, Codex, and Gemini — no account or API key. `npx linksee-memory` - [mercurialsolo/counsel-mcp](https://github.com/mercurialsolo/counsel-mcp) 📇 ☁️ 🏠 🍎 🪟 🐧 - Connect AI agents to the Counsel API for strategic reasoning, multi-perspective debate analysis, and interactive advisory sessions. - [mlorentedev/hive](https://github.com/mlorentedev/hive) [![hive MCP server](https://glama.ai/mcp/servers/mlorentedev/hive/badges/score.svg)](https://glama.ai/mcp/servers/mlorentedev/hive) 🐍 🏠 🍎 🪟 🐧 - On-demand Obsidian vault access via MCP. Adaptive context loading (67-82% token savings), full-text and ranked search, health checks, auto git commit, and worker delegation to cheaper models. 10 tools, works with any MCP client. - [TheGoatPsy/mneme](https://github.com/TheGoatPsy/mneme) [![mneme MCP server](https://glama.ai/mcp/servers/TheGoatPsy/mneme/badges/score.svg)](https://glama.ai/mcp/servers/TheGoatPsy/mneme) 🐍 🏠 🍎 🪟 🐧 - Vault-native, accountable memory for Claude Code and any MCP client. Markdown is the source of truth, no LLM on the Stop path, redaction before every derived store.