AI tools for building AI agents: memory
Memory layers that let agents remember users, past sessions and facts over time. Of the 204 tools on our building AI agents page, 13 fit this narrower job. By pricing: 11 open source, 2 pricing on the maker's site. The most-starred open repos here are Deer Flow (83,959 stars), Nanobot (49,096 stars), Agno (42,769 stars). Most come from the frameworks (7), personal agents (2), MCP & infra (2) categories.
Deer Flow
ByteDance's open-source long-horizon agent harness that researches, codes and creates using sandboxes, memory and sub-agents.
Added
Nanobot
Ultra-lightweight, self-hosted personal agent framework in Python with a web UI, tools, memory and MCP support.
Added
Agno
Python framework and runtime for building, running and managing multi-agent systems with memory, knowledge and tools.
Added
Letta
Framework for stateful agents with long-term memory (formerly MemGPT).
Added
Osaurus
Native macOS harness for AI agents with any model, memory and autonomous execution.
Added
Honcho
Memory library and service for building stateful agents that remember users.
Added
AIOS
Research AI agent operating system that handles scheduling, context switching, memory, storage and tool management for LLM-based agents.
Added
SimpleMem
Research-backed lifelong memory library for LLM agents that stores, compresses and retrieves text and multimodal memories, usable over MCP.
Added
LazyCodex
Agent harness for Codex that adds project memory, planning, execution and verified completion for complex codebases.
Added
Cheshire Cat
Open-source AI agent microservice designed to be easy to understand and extend, with plugins and memory.
Added
Neuron AI
PHP framework for creating and orchestrating AI agents with LLMs, tools, vector stores and memory.
Added
tRPC-Agent-Go
Go framework for production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation and OpenTelemetry.
Added
BaseAI
Web AI framework from Langbase for building AI agents with memory (RAG) and deploying them serverless.
Added
GitHub repos (12)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| Deer Flow ↗ | 83,959 | MIT | 2026-10-18 |
| Nanobot ↗ | 49,096 | MIT | 2026-10-18 |
| Agno ↗ | 42,769 | Apache License 2.0 | 2026-10-17 |
| Letta ↗ | 25,125 | Apache License 2.0 | 2026-09-10 |
| Osaurus ↗ | 8,052 | MIT | 2026-10-18 |
| Honcho ↗ | 7,648 | GNU AGPL v3.0 | 2026-10-16 |
| AIOS ↗ | 6,480 | — | — |
| SimpleMem ↗ | 3,836 | — | — |
| LazyCodex ↗ | 3,792 | — | — |
| Cheshire Cat ↗ | 3,095 | — | — |
| Neuron AI ↗ | 2,146 | — | — |
| tRPC-Agent-Go ↗ | 1,867 | — | — |
12 repos. Stars and licence come from each repo, checked when the listing was last verified.
FAQ
What are the best AI tools for building AI agents focused on memory?
We list 13. The first three by GitHub stars and featured status are Deer Flow: ByteDance's open-source long-horizon agent harness that researches, codes and creates using sandboxes, memory and sub-agents.; Nanobot: Ultra-lightweight, self-hosted personal agent framework in Python with a web UI, tools, memory and MCP support.; Agno: Python framework and runtime for building, running and managing multi-agent systems with memory, knowledge and tools.
Are there free or open-source options?
Yes: 11 open source, 2 pricing on the maker's site. Pricing is as each maker states it.
More from building AI agents
Tools are grouped by what each says it does. Missing one? Submit it free.