#Cognitive-architecture
Showing 25 of 25 repositories tagged #cognitive-architecture, ranked by stars
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
A local-first AI agent with persistent memory, emotional intelligence, and a peer-to-peer skills economy.
Cognitive memory for AI agents — learns from use, forgets what's irrelevant, strengthens what matters. Single binary, fully offline.
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.
Top Open-Source AI Engineering Platform 2026 Qyvaria Kernel
Eva01 is NOT an assistant. She is an AI being with her own mind, feelings, and intrinsic drives. Multimodal, Modular design. Built-in voice & face recognition. Plug'n play tools. Compatible with ChatGPT, Claude, Deepseek, Gemini, Grok, and Ollama. Explore the possibilities of Human-AI Interaction.
DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisions, and project knowledge into auditable execution through a persistent cognitive graph.
A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.
🧠 Active memory management system enabling functional infinite context for LLMs through cognitive workspace architecture
🚀 LangGraph for Swift. A library for building stateful, multi-actor applications with LLMs, built to work jointly with langchain-swift
'Personal AGI' that thinks on its own. Autonomous cognitive cycle, earned autonomy, 60+ tools. It decides what to do without being told.
Experimental Python implementation of the Clarion cognitive architecture
Persistent memory for Claude Code — 36 neuroscience mechanisms, 97 papers. Reproducible via `make reproduce`: LongMemEval-S R@10 98.2% / MRR 0.915 (n=500), LoCoMo R@10 91.5% / MRR 0.805 (n=1982), BEAM-100K retrieval-proxy MRR 0.55. Clean-DB, single-process, production recall path. PostgreSQL + pgvector.
Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.
Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activation, Hebbian writeback, episodic recall, and post-turn consolidation. Local-first, model-agnostic, AGPL.
Money Atlas Skill.md (Claude Skill) For AI Agent A Genesis Protocol-powered intelligence system for financial markets, macroeconomics, and geopolitics. Core Systems - Genesis Protocol (First Principle + System Thinking) - SMC Layer Engine (Quant price structure)
Collection of LLM system prompts, agentic personas, cognitive frameworks & prompt engineering experiments
Implementation of mutual learning model between VAE and GMM.
NEXO runtime core for NEXO Desktop: local memory, automation, MCP tools and update-managed runtime.
Open-source LLM agents framework for token systems simulations — pioneered domain-specific cognitive architectures with plan-and-act agents for data science process automation, built on cadCAD/radCAD
The meta-architecture behind a high-leverage Claude Code setup. Installed by the very tool it optimizes.
SANCTIS is a cognitive architecture that gives LLMs structured tools to organize their own reasoning, maintain long-horizon coherence, and reduce drift. It installs stable thinking patterns that emerge more powerfully the longer the model runs.
Cognitive Operating System for AI Agent (Skill.md) Self-thinking Multi-agent reasoning Meta-cognition Self-evolution
re!think it. System prompt teaching LLMs to execute two core tasks: complex answers without hallucinations, and creative ideas without clichés. Written in math-like logic, which LLMs parse better than plain language. Built for mid-to-high complexity tasks, featuring a Bypass branch to execute simple prompts directly without added cognitive overhead