From 243c3df9ff4e0f5ab93641069783c028a297c00c Mon Sep 17 00:00:00 2001 From: Vitalii Cherepanov Date: Mon, 7 Sep 2026 17:15:55 +0200 Subject: [PATCH] Add total-agent-memory server --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 76264cbb9..d9e1dab55 100644 --- a/README.md +++ b/README.md @@ -2682,6 +2682,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to - [unibaseio/membase-mcp](https://github.com/unibaseio/membase-mcp) 📇 ☁️ - Save and query your agent memory in distributed way by Membase - [upstash/context7](https://github.com/upstash/context7) 📇 ☁️ - Up-to-date code documentation for LLMs and AI code editors. - [varun29ankuS/shodh-memory](https://github.com/varun29ankuS/shodh-memory) 🦀 🏠 - Cognitive memory for AI agents with Hebbian learning, 3-tier architecture, and knowledge graphs. Single ~15MB binary, runs offline on edge devices. +- [vbcherepanov/total-agent-memory](https://github.com/vbcherepanov/total-agent-memory) 🐍 🏠 🍎 🪟 🐧 - Persistent local memory for coding agents: temporal knowledge graph with fact invalidation, procedural memory, episodic recall, AST codebase ingest and cross-project analogy. 74 tools, 9 IDEs, and zero LLM or network calls in the default hot path. Reproducible benchmarks — LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. `pip install total-agent-memory` - [samvallad33/vestige](https://github.com/samvallad33/vestige) [![samvallad33/vestige MCP server](https://glama.ai/mcp/servers/samvallad33/vestige/badges/score.svg)](https://glama.ai/mcp/servers/samvallad33/vestige) 🦀 🏠 🍎 🪟 🐧 - Local-first cognitive memory for AI agents. FSRS-6 scheduling, smart ingest, SQLite storage, portable sync, embedded dashboard, and optional Cognitive Sandwich hooks for Claude Code, Cursor, Codex, and other MCP clients. - [vectorize-io/hindsight](https://github.com/vectorize-io/hindsight) 🐍 ☁️ 🏠 - Hindsight: Agent Memory That Works Like Human Memory - Built for AI Agents to manage Long Term Memory - [vornicx/Midas](https://github.com/vornicx/Midas) [![vornicx/Midas MCP server](https://glama.ai/mcp/servers/vornicx/Midas/badges/score.svg)](https://glama.ai/mcp/servers/vornicx/Midas) 🐍 📇 🏠 🍎 🪟 🐧 - Local-first memory for long-horizon AI agents with no LLM at ingest — $0 per message, zero data egress, verbatim source-traceable recall. Typed belief revision, selective forgetting, and a provenance guard that blocks memory-justified destructive actions unless user-confirmed. One `midas init` wires Claude Code, Cursor, Codex, and 6 more clients to one shared SQLite memory; local web inspector and hash-chained audit log. Benchmarked on LongMemEval/LoCoMo/BEAM with one-command repros — including published negatives. `uvx midas-memory-mcp` or `npx -y midas-memory-mcp`