longmemeval

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

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

The Cost of Remembering: filesystem memory matches long-context accuracy on LongMemEval while reading 97% fewer tokens and costing 95% less. Harness, run data, 129 agent-built memories, and paper source.

Zero-LLM agent memory for Claude Code and AI agents: local-first BM25, dense-vector, and reciprocal-rank-fusion retrieval. Returns original passages verbatim by default. Available on PyPI as fidelis-memory. MIT.

Agent memory for LLM agents: 7 neuroscience-inspired layers, zero-dependency TypeScript. Wins 9/9 answer-quality comparisons on LongMemEval-500 (3 judges, Bonferroni).

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.

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

Open evaluation harness for AI agent memory systems. Runs LoCoMo and LongMemEval against Synap, Mem0, Zep and Supermemory with pluggable provider adapters.

TMCRA Core — local-first, scope-isolated long-term memory runtime for AI agents.

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

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

Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).

LongMemEval 中文子集：识流基于 DeepSeek-V4-Flash 的 500 题公开评测结果与可复核数据。

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

First-Person Agent Memory Bench. 10 Categories including fact recall, multi-hop links, temporal reasoning, fact overwrites, speaker traps, refusal, credibility, and agentic tool usage. 540K token / 60 session corpus, all in first person. Dynamic output-answer-key portion. Comprehensive report with visuals and miss breakdown.

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

Open testbench for agent-memory evaluation. Inspect historical evidence locally with no API key and no Docker.

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