A Multi Agent Memory MCP That Connect Agents Across Systems and Machines

Local-first AI memory — runs offline on any machine with 8 GB+ RAM (SBC, mini PC, laptop, workstation). Zero-loss verbatim archive, knowledge graph, hybrid retrieval. Framework-agnostic, no cloud.

Agent memory without the retrieval tax. Fidelity-preserving memory for Claude Code and AI agents — local-first, fast, and with no LLM in the default retrieval path. 83.2% R@1 on LongMemEval-S, $0/query retrieval.

Your AI forgets everything between sessions. This fixes that — 98%+ retrieval accuracy, 100% on LongMemEval, 99% token savings. 44 MCP tools. Fully local, zero cost.

Local-first Agentic Memory Layer Framework for MCP Agents and Multiple Computers • Over 60 tools • Hybrid search (FTS5 + vector + MMR) • GDPR • 100% local) • FIPS 140-3 ready

Persistent memory for AI agents. Single Rust CLI, hybrid Gemini + FTS5 + RRF retrieval. R@5 = 0.99 on LongMemEval S (beats MemPalace). Agent-native: no MCP, no server, just shell out.

Official Python SDK for RecallrAI – a revolutionary contextual memory system that enables AI assistants to form meaningful connections between conversations, just like human memory.

Public, reproducible benchmarks for Agent Brain on LongMemEval-M. 71.7% accuracy (Test 0). Companion code to https://doi.org/10.5281/zenodo.19673132 (Concept DOI → latest version, currently v3).

LENS - AI Memory Benchmark - Memory as Experience, Not Facts

Multi-agent strategic intelligence system with hybrid memory retrieval. Research project.

Anti-RAG dual-whitebox memory for LLM agents. 2.72 MB SQLite + Markdown kernel, no vector DB, no embeddings. Lifts qwen2.5:7b from 1.79% to 60.71% on NoLiMa-32k (+58.9pp), 88.71% on LV-Eval EN 256k, 84.8% on LongMemEval-S. Restart-safe, concurrency-bullet-proof, 100% transparent.

Reproducible evaluation harness for agent memory systems (LongMemEval and beyond).

Evaluate autonomous AI memory systems using reproducible benchmarks and the LongMemEval-M dataset for Agent Brain.