AgentIndex icon
AgentIndex
TrueMemory logo
TrueMemory
★ 382
vs
agent-network logo
agent-network
★ 101

TrueMemory vs agent-network

TrueMemory: TrueMemory is a neuroscience-inspired persistent memory system for AI agents. It achieves state-of-the-art scores on LoCoMo, LongMemEval, and BEAM benchmarks while running entirely offline on a single SQLite file. The six-layer retrieval pipeline with an encoding gate filters noise and stores only meaningful information.; agent-network: Agent Network is a local-first multi-agent collaboration platform that runs entirely on your machine. It provides a unified CLI to manage Hub, Web Dashboard, and multiple agents, supporting various LLM providers and automatic task distribution via MCP tools. Optional LAN sharing is available.

01

TL;DR

TrueMemory logo
TrueMemoryRAG / Knowledge Base · ★ 382

Personal AI assistant that remembers user preferences and history across conversations.

Read TrueMemory full review →
agent-network logo
agent-networkMulti-Agent · ★ 101

Running multiple AI agents locally for collaborative task execution

Read agent-network full review →
02

Side-by-Side Comparison

Field
TrueMemory logoTrueMemory
agent-network logoagent-network
Category
RAG / Knowledge Base
Multi-Agent
Stars
★ 382
★ 101
License
AGPL-3.0
Apache-2.0
Install Command
curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh | sh
npm install -g @sleep2agi/agent-network
Updated
1w ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agent-memory, ai, ai-agents
agent-network, ai-agents, anthropic
03

Features

TrueMemory logoTrueMemory
01Remembers everything across sessions – facts, preferences, decisions, corrections.
02State-of-the-art benchmark scores: 93.0% on LoCoMo, 92.0% on LongMemEval, 76.6% on BEAM-1M.
03Runs locally on a single SQLite file – zero cloud, zero API keys for Edge and Base tiers.
04Neuroscience-inspired architecture with six retrieval layers and an encoding gate.
05Works with Claude Code and Claude Desktop via pre-built lifecycle hooks.
agent-network logoagent-network
01Single CLI for Hub, Dashboard, and Agent runtimes (Claude Code CLI, Claude Agent SDK, Codex SDK)
02Switch between 8 LLM providers (Anthropic, OpenAI, MiniMax, DeepSeek, GLM, Kimi, InternLM, OpenRouter) via ANTHROPIC_BASE_URL
03Local or cross-server mesh network with real-time SSE communication and automatic agent discovery
0417 built-in MCP tools for automatic task delegation between agents without manual orchestration
05Built-in Web Dashboard (Chat, Nodes, Tasks, Messages, Networks, Logs, Admin) with 4 themes
04

Use Cases

TrueMemory logoTrueMemory
↳Personal AI assistant that remembers user preferences and history across conversations.
↳Developer tool that maintains context across long coding sessions.
↳Research and simulation where agents need long-horizon memory.
agent-network logoagent-network
↳Running multiple AI agents locally for collaborative task execution
↳Deploying agents across multiple servers or workstations connected via a single Hub
↳Unified management and switching between various LLM providers for different agent tasks
FAQ

FAQ

What is the difference between TrueMemory and agent-network?
Both TrueMemory and agent-network are in the RAG / Knowledge Base category. TrueMemory has 382 stars, while agent-network has 101 stars.
Which is better, TrueMemory or agent-network?
The best choice depends on your use case. Choose TrueMemory if Personal AI assistant that remembers user preferences and history across conversations., and agent-network if Running multiple AI agents locally for collaborative task execution.
Is TrueMemory free or open source?
Yes, TrueMemory is open source on GitHub (AGPL-3.0).
Is agent-network free or open source?
Yes, agent-network is open source on GitHub (Apache-2.0).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to TrueMemory →Alternatives to agent-network →TrueMemory details →agent-network details →