agentmemory

Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses

Neuroscience-inspired memory framework for AI agents

Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.

Agent Memory Playground: AI Agent Memory Design & Optimization Techniques

Pull-model episodic memory plugin for Hermes Agent. Real deletes, audit trace, BYO Claude. MIT.

Implementation based on the paper "ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory"

Aurora is a first-principles adaptive memory runtime organized around one evolving trace field.

A toy local memory system for multi-agent workflows

A dual-layer memory system for AI agents with incremental clustering, graph-based retrieval, and conflict resolution.

Provider-free persistent cognition for AI agents: verified memory, failure frontiers, proof-gated branches, and reversible learning.

A production-grade memory system for AI agents that enables accurate recall across 1,000+ conversation turns.

A minimalist, cross-platform personal AI automation toolkit for research, learning, and lead generation. Built for Termux + WSL2 + Windows with Gemini CLI, AgentMemory, Apify, yt-dlp, and gcloud.

The first collision-based memory system: it doesn't retrieve old ideas — it smashes old cards into new ones.

Voice agent system for learning a new language

🛠️ Experiment with AI agents in a local sandbox to run, score, and compare outputs without the need for complex frameworks.

✈️ A multi-agent AI travel planner powered by LangGraph that combines live flight data, hotel research, and LLM-generated itineraries 🏨 into personalized travel plans with persistent PostgreSQL conversation memory. 🗺️✨