A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

Clean baseline implementation of PPO using an episodic TransformerXL memory

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.

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

The best-benchmarked open-source memory system for AI coding assistants

Self improving agents through iterations

Code for paper "Episodic Memory Deep Q-Networks" (https://arxiv.org/abs/1805.07603), IJCAI 2018

Open-source AI SRE agent that investigates production incidents using episodic memory and Neo4j knowledge graph. 46 production skills. Self-hosted.

Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories retroactively when outcomes land (deal closed, sprint shipped). Hooks + MCP server for Claude Code, Qdrant + FastEmbed local-first.

Lu, Q., Hasson, U., & Norman, K. A. (2022). A neural network model of when to retrieve and encode episodic memories. eLife

PyTorch implementation of Episodic Meta Reinforcement Learning on variants of the "Two-Step" task. Reproduces the results found in three papers. Check the ReadMe for more details!

Persistent memory for Claude Code — 41 neuroscience papers, 26 biological mechanisms with paper-bearing per-mechanism ablation evidence (E1 v3). LongMemEval R@10 98.4% / MRR 0.9124 (n=500). LoCoMo R@10 94.2% / MRR 0.8278 (n=1986). BEAM-10M +33.4% over flat retrieval. PostgreSQL + pgvector. Verified via 31-row two-benchmark ablation campaign.

Robot Memory - Persistent memory system for AI robots. MCP Server + hybrid search + spatial retrieval.

NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory. CVPR 2023.

Persistent filesystem-based memory system for Claude Code. Pure MIF Level 3 compliant memory storage with YAML frontmatter, bi-temporal tracking, and proactive hooks. No dependencies - just markdown files and git.

Psifr: Analysis and visualization of free recall data

ESTMS enables natural interaction with any VLM agent that learns from the conversation with the user and can help with everyday tasks.

Memory-centric architecture for scalable, energy-efficient AI agents and long-term cognition.

Stop your AI agent from repeating same mistake and learn from previous failures

Depth-aware context compression for LLM proxies. Turn-box marker format with epistemic transparency.