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

Token-native agent memory retrieval for LLMs, without embedding APIs or vector databases.

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.

Reproducible benchmarks for execution-intent memory in long-horizon AI coding agents. ID-RAG cross-corpus matrix + LongMemEval-S subset; BYO API keys.

Multi-agent memory substrate for PostgreSQL — provenance-gated, vector-hybrid recall

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).

Smallest possible working example of CogmemAi (95.1% LongMemEval) wired into the Claude Agent SDK. Two-session demo: save in session 1, recall in session 2.

100-question 6-dimension long-conversation memory benchmark for Chinese-healthcare AI. Sivon reference: 92/100 mean (2026-05-27).

Retrain-free attention patch that makes Llama 3.3 70B ~1.3× more accurate on long-conversation memory

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

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

Benchmark results, scorer, and reproducibility kit for Sibyl Memory. LongMemEval 95.6% (#2). Verify it yourself.

Benchmark harness for HeurChain on LongMemEval-S — reproduce the R@10, MRR, NDCG, and latency numbers from heurchain.com

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.