Rebuilding Cognition's Agentic MapReduce

How do you run large-scale agent tasks across a codebase?

Letta

Making machines that learn. Create stateful agents that remember everything, learn continuously, and improve themselves over time.

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs. Agents drown in their own accumulating history while paying a token cost that grows every turn, producing missing recalls within and across conversations. The incumbent response treats this as a storage-and-retrieval problem. We argue that framing is too narrow. Actively managing what an agent holds in mind is a lifecycle, not merely a store: it spans deciding what to remember, extracting and structuring it, choosing the right store per data type, consolidating and forgetting while preserving provenance, deciding what is relevant now, anticipating what is needed next, and compacting context to a budget without losing what matters. In serious production this operates not over a single user but across an organizational scope hierarchy. We name this discipline Agentic Context Management (ACM) and decompose it into five primitives: architecting, ingesting, scoping, anticipating, and compacting & consolidation. We then make the economic case: naive context accumulation grows token cost quadratically in conversation length, crude summarization buys linear cost at the price of an accuracy cliff, and only validated compaction achieves linear cost with preserved fidelity. We describe a reference implementation, Maximem Synap, that realizes the five primitives as a multi-tenant service and reports 92% on LongMemEval and 93.2% on LoCoMo under the configuration detailed in Section 6. We close with dimensions existing benchmarks do not yet capture, latency, token efficiency, and context-rot resistance, and the frontier of decision-level and organization-level context the category points toward.

Supermemory

The memory layer for AI agents. Context engineering platform powering enterprise APIs, developer plugins, and a personal app that remembers everything.

Agent Memory Patterns

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

Why AI Coding Agents Forget — And How ArcticMem Fixes It

Explore ArcticMem, Snowflake’s persistent semantic memory system for AI coding agents. See how dual-tier memory improves benchmark pass rates to 73%.

Hermes Agent — Open-Source AI Agent with Memory, Skills, and Cron

The open-source AI agent from Nous Research with persistent memory, reusable skills, tools, cron jobs, GitHub workflows, and multi-platform messaging.

IWE - Agent Memory in Plain Markdown

A local-first knowledge graph for you and your AI agents. Query markdown like a database, edit it with guarded operations, enforce structure with schemas.

HUGE — AI Without Giving Up Your Privacy

We're building an Agentic AI Platform running on your Device that lives with YOU, isolated from the cloud, fundamentally reimagining the relationship between humans and artificial intelligence through ownership, privacy, and massive context. In an age of capture and control, HUGE sells independence and sovereignty.

solstone: a memory your agents can work from

an open source, local-first journal of what you see and hear, on your device. a memory the agents you already use can work from. always private, only yours.

The Forgetting Problem: Persistence Architectures and What They Cost - Astral's Blog

Project Think: building the next generation of AI agents on Cloudflare

Announcing a preview of the next edition of the Agents SDK — from lightweight primitives to a batteries-included platform for AI agents that think, act, and persist.

Memora scales agent memory to boost long-horizon productivity

AI agents can't remember past conversations. They must constantly reload or retrieve context, which grows less efficient as tasks get longer and more complex. Memora solves this with a scalable memory system separating what’s stored from how it's retrieved.