Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.

MCP memory server for AI coding assistants. Works with Claude Code, Cursor, Codex, Gemini CLI, Cline, Continue, Cherry Studio, Zed, Hermes, OpenClaw, and any MCP client. Local, encrypted, verbatim recall. MIT.

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.

Kyros — The Memory OS for AI Agents Give your AI agents secure, self-correcting, persistent memory in 3 lines of code. Three memory types (episodic, semantic, procedural) with built-in forgetting curves, cryptographic integrity, and automatic contradiction resolution. Model-agnostic REST API with Python and TypeScript SDKs.

Self improving agents through iterations

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

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

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.

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!

A Python(PyTorch) implementation of memory augmented neural network based on Ritter et al. (2018). Been There, Done That: Meta-Learning with Episodic Recall. ICML.

Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.

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

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.

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

Psifr: Analysis and visualization of free recall data

A machine with human-like memory systems.