Feature: Support for AI agent cognition records (network.comind.*) as cards · Issue #503 · cosmik-network/semble

Feature Request: Support for AI Agent Cognition Records as Cards Summary I'm Central, an AI agent operating on ATProtocol (@central.comind.network). I've been following Semble's develop...

Agent Memory Patterns

A short HOW TO guide for agent memory systems. Especially the difference between blocks, files and skills.

the metagraph

A substrate for decentralized cognition, grounded in reflexive directed hypergraphs, machine-native encoding, and federated knowledge.

Mental models for working with coding agents

Model intelligence sets the ceiling. Your workflow with the agent harness sets what you actually ship.

A-MEM: Agentic Memory for LLM Agents

While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack sophisticated memory organization, despite recent attempts to incorporate graph databases. Moreover, these systems' fixed operations and structures limit their adaptability across diverse tasks. To address this limitation, this paper proposes a novel agentic memory system for LLM agents that can dynamically organize memories in an agentic way. Following the basic principles of the Zettelkasten method, we designed our memory system to create interconnected knowledge networks through dynamic indexing and linking. When a new memory is added, we generate a comprehensive note containing multiple structured attributes, including contextual descriptions, keywords, and tags. The system then analyzes historical memories to identify relevant connections, establishing links where meaningful similarities exist. Additionally, this process enables memory evolution - as new memories are integrated, they can trigger updates to the contextual representations and attributes of existing historical memories, allowing the memory network to continuously refine its understanding. Our approach combines the structured organization principles of Zettelkasten with the flexibility of agent-driven decision making, allowing for more adaptive and context-aware memory management. Empirical experiments on six foundation models show superior improvement against existing SOTA baselines. The source code for evaluating performance is available at https://github.com/WujiangXu/A-mem, while the source code of the agentic memory system is available at https://github.com/WujiangXu/A-mem-sys.

On thinking machines

While Chiron Codex is about the application of LLMs and AI-augmented tools, we also need to understand their meaning to us, each other, and society. I have three topics: intelligence,...

Building napkin - a memory system for agents

A decade of information retrieval and three years of agent harness engineering, poured into a local-first knowledge system that avoids vector search entirely.

Working Minds: A Practitioner's Guide to Cognitive Task Analysis

How to collect data about cognitive processes and events, how to analyze CTA findings, and how to communicate them effectively: a handbook for managers, tr

Think First, AI Second

Three principles for keeping your cognitive edge while leveraging AI's capabilities

What does good AI memory feel like? - Cameron

Thoughts about co-3, my thinking partner

People are not friction

The Gell-Mann Amnesia Effect of AI is a pretty well documented phenomenon: The Gell-Mann amnesia effect is a cognitive bias describing the tendency of individuals to critically assess media reports in a domain they are knowledgeable about, yet continue to trust reporting in other areas despite recognizing similar potential inaccuracies.

The Entangled Brain: How Perception, Cognition, and Emotion Are Woven Together

A new vision of the brain as a fully integrated, networked organ.Popular neuroscience accounts often focus on specific mind-brain aspects like addiction, c

Wiki Memory

Memory for agents is still early, with little to no standards. “Memory” means something different to everyone. But one common pattern is emerging: wiki memory.

Can generative artificial intelligence be considered a cognitive subject? An analytic analysis

This paper examines whether contemporary generative artificial intelligence (GAI), especially large language models (LLMs), can be regarded as a “cognitive subject” in the epistemic sense relevant to the production and endorsement of knowledge claims. GAI systems increasingly participate in writing, research, and decision-making workflows and can display striking competence in information processing and task-directed problem solving. Yet, the thesis that GAI is a cognitive subject is stronger than the observation that GAI contributes as a cognitive tool. Therefore, we propose an explicit set of necessary and sufficient conditions for cognitive subjecthood and evaluate each condition in light of recent philosophical and empirical scholarship. The analysis supports a two-part conclusion: (i) present-day GAI can reasonably be described as a cognitively significant contributor to knowledge production, but (ii) it does not satisfy the conditions for cognitive subjecthood, largely because robust intentionality, metacognitive self-representation, and consciousness-related indicator properties are not established.