Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses
-
Updated
Aug 30, 2026 - Python
Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses
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.
Neuroscience-inspired memory framework for AI agents
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
Provider-free persistent cognition for AI agents: verified memory, failure frontiers, proof-gated branches, and reversible learning.
A dual-layer memory system for AI agents with incremental clustering, graph-based retrieval, and conflict resolution.
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.
agentmemory Viewer 简体中文汉化补丁 — 纯文案替换,不改功能逻辑、不发送数据,覆盖 295 条界面文案(适配 agentmemory v0.9.29)
The first collision-based memory system: it doesn't retrieve old ideas — it smashes old cards into new ones.
🛠️ Experiment with AI agents in a local sandbox to run, score, and compare outputs without the need for complex frameworks.
MCP stdio → Streamable HTTP (Python/Starlette): `agentmemory` serves as shared long-term memory for Freebuff and OpenCode — includes a watchdog, `/health` status (ok|degraded|down), systemd units, and E2E testing.
To associate your repository with the agentmemory topic, visit your repo's landing page and select "manage topics."