Ori-Mnemos
★ 306
vs
agents-best-practices
★ 1.1k
Ori-Mnemos vs agents-best-practices
Ori-Mnemos: Ori Mnemos is an open-source persistent memory infrastructure for AI agents that implements human cognition models on a knowledge graph. It uses ACT-R decay, spreading activation, and Hebbian learning to manage memory, and achieves state-of-the-art retrieval performance while being zero-infrastructure and portable.; agents-best-practices: A provider-neutral Agent Skill library for designing, auditing, and refactoring agentic harnesses compatible with Codex and Claude Code. It covers the full control plane of an agent runtime: typed tool design, permission checks, context management, memory, and observability. Targeted at developers building production-ready agent systems across any domain or AI provider.
01
TL;DR
Choose Ori-Mnemos if…Multi-hop retrieval QA (e.g., HotpotQA)
Choose agents-best-practices if…Generate MVP agent harness blueprints for any business domain (CRM, ops, finance, healthcare)
02
Side-by-Side Comparison
03
Features
Ori-Mnemos01Persistent memory across sessions, clients, and machines
02Knowledge graph with wiki-links, PageRank, and community detection
03Three memory spaces with cognitive forgetting (ACT-R decay)
04Four-signal fusion retrieval (semantic, BM25, PageRank, warmth)
05Retrieval intelligence with Q-learning and meta-learning
agents-best-practices01Provider-neutral agentic loop design compatible with OpenAI, Anthropic, and compatible APIs
02Typed tool definitions with structured results and runtime permission checks outside the model
03Planning mode and approval-gated execution patterns for safe agent actions
04Context management, memory, and auto-compaction with active state preservation
05Observability, evals, launch gates, and incident response checklists
04
Use Cases
Ori-Mnemos↳Multi-hop retrieval QA (e.g., HotpotQA)
↳Long-term conversational memory (e.g., LoCoMo)
↳Persistent AI agent identity and knowledge
agents-best-practices↳Generate MVP agent harness blueprints for any business domain (CRM, ops, finance, healthcare)
↳Audit and refactor brittle or over-permissioned existing agent systems
↳Design narrow typed tools and connector governance for multi-system agents
05
Best For
Ori-MnemosMemory & ContextRAG / Knowledge Base
agents-best-practicesTrendingMulti-AgentDev Tooling
FAQ
FAQ
What is the difference between Ori-Mnemos and agents-best-practices?
Both Ori-Mnemos and agents-best-practices are in the Memory & Context category. Ori-Mnemos has 306 stars, while agents-best-practices has 1.1k stars.
Which is better, Ori-Mnemos or agents-best-practices?
The best choice depends on your use case. Choose Ori-Mnemos if Multi-hop retrieval QA (e.g., HotpotQA), and agents-best-practices if Generate MVP agent harness blueprints for any business domain (CRM, ops, finance, healthcare).
Is Ori-Mnemos free or open source?
Yes, Ori-Mnemos is open source on GitHub (Apache-2.0).
Is agents-best-practices free or open source?
Yes, agents-best-practices is open source on GitHub (MIT).
→