A minimalist MVP demonstrating a simple yet profound insight: aligning AI memory with human episodic memory granularity. Shows how this single principle enables simple methods to rival complex memory frameworks for conversational tasks.
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.
Open-source causal graph memory for AI agents. 89.9% on LoCoMo. MCP server with ACT-R scoring, spreading activation, and active forgetting.
Multi-agent memory substrate for PostgreSQL — provenance-gated, vector-hybrid recall
Research benchmark: conversational memory learning on a corrected LoCoMo dataset
🚀 A modern, production-ready refactor of the LoCoMo long-term memory benchmark.
Reproduce Verbative's memory benchmarks — LoCoMo and AMA-Bench (all six domains) — against your own installed Verbative memory engine. Includes the harness, the judge-host calibration study, and the published per-question answers and verdicts behind every number we quote.
Per-speaker memory isolation with neural reranking for multi-party LLM agents. 66.6% on LoCoMo (+50.2 pp on temporal over RAG) at 1.02 LLM calls per query.
Benchmarking markdown knowledge graphs as agent memory — LOCOMO and HotPotQA tracks with Claude Code
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).
Simple CSS and animation focus project, clone from abhishekjha.me
Open-source empathic memory benchmark — methodology + runners + adapters. Pulse v3 leads 9-system leaderboard. MIT.
Reproducible LoCoMo, LongMemEval, PersonaMem, FAMA, recall and latency benchmarks for long-term AI memory systems
Independent, reproducible CLI benchmark harness for agent-memory backends (MemPalace, Mem0, Zep/Graphiti, OpenViking): runs LongMemEval, LoCoMo, and contradiction-detection evals against all four and publishes the raw logs, not vendor-curated numbers.
Add a description, image, and links to the locomo topic page so that developers can more easily learn about it.
To associate your repository with the locomo topic, visit your repo's landing page and select "manage topics."