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.

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

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 Memory Framework for AI Agents · 99.2% LongMemEval-S retrieval @ k=10 · Supports Claude · Gemini · Antigravity · OpenCode · OpenClaw · Hermes · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable

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

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

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.

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

Benchmarks 20 agent-memory strategies through one lifecycle, one judge, one model. A 30-line vector store outranks every funded vendor SDK. Each result is stamped with commit, package versions, and seed so anyone can re-run it.

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.

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).

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

fidelis is zero-LLM agent memory for Claude Code and AI agents: a local-first memory layer whose default retrieval path uses BM25, dense vectors, and reciprocal rank fusion with no LLM call. It returns your original passages verbatim instead of paraphrasing and runs fully local. Benchmarked on LongMemEval-S. MIT, by Hermes Labs.

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

Lightweight, vendor-neutral agent memory evaluation harness. Local, GPU-free, reproducible.

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

LongMemEval-S results for Mnemo — 85.2% (426/500) under the official LongMemEval judge prompts (gpt-4o-mini); 80.8% strict exact-match cross-check. Per-question receipts + methodology.

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