A state-based autonomous agent framework. Crafting digital entities with non-linear cognitive memory and self-evolving emotions. (Work in Progress)
-
Updated
Jun 1, 2026 - Rust
A state-based autonomous agent framework. Crafting digital entities with non-linear cognitive memory and self-evolving emotions. (Work in Progress)
special agent's memory
Cognitive orchestration OS for Claude Code — 28 agents, 113 skills, 71 commands, dual-process routing, GRPO lifelong learning, native Agent Teams, MCP server.
High-performance Cognitive Memory Architecture for AI Agents. Features 4-layer hierarchy, Knowledge Graph, 3D Dashboard, and Hybrid Retrieval.
AEGIS — Agentic AI Learning Platform with Epistemic State Modeling, Ebbinghaus Forgetting Curve, and Cognitive DNA Adaptation.
OpenManus-Max: A fully refactored OpenManus with Manus-level capabilities. DAG Scheduler, Hierarchical Memory, 20+ Tools, Multi-Level Permissions & Trust Attenuation.
分层记忆宫殿架构 - 突破Hermes Agent 2,200字符记忆限制
🌳 Filesystem-native hierarchical memory tree for AI coding agents. Three-layer architecture: Focus board (WATCH.md) → Keyword index (MEMORY.md) → Detail branches (Level 1+N). Infinite capacity, zero dependencies, auto-cascade recall.
(experimental) Parallel multi-agent swarm architecture for collective AI intelligence. All agents live. All agents share memory. All agents iterate until consensus.
Enable parallel multi-agent consensus research with a live shared memory and preserved dissent using a three-tier hierarchical model.
An adressable hierarchical memory system for LLMs. Compress a 10k-token context into 2k active tokens without losing information — by making the rest adressable on demand.
Pattern - MCP server for hierarchical agent memory
Add a description, image, and links to the hierarchical-memory topic page so that developers can more easily learn about it.
To associate your repository with the hierarchical-memory topic, visit your repo's landing page and select "manage topics."