mnemosyne
★ 151
vs
memini
★ 28
mnemosyne vs memini
mnemosyne: Mnemosyne provides persistent memory for AI agents, enabling them to carry work forward, recover original evidence, and adapt by retiring obsolete lessons when their source changes. It connects memory to its consequences, allowing agents to resume from handoffs, withhold skills after failures, and benefit from a wiser start.; memini: memini is a shared, persistent memory service designed for AI agents, providing a single location for agents to remember and recall information with continuously improving retrieval quality. It's built as a Go binary, offers zero-configuration startup, and scales from embedded SQLite on a laptop to Postgres in Kubernetes.
01
TL;DR
mnemosyneMemory & Context · ★ 151
Building AI agents that require long-term, verifiable memory for decision-making and learning.
meminiMemory & Context · ★ 28
Enhancing AI Agents with Long-Term Memory: Integrate memini to give AI agents (like Claude Code, opencode, Hermes) the ability to remember past interactions and learn over time.
02
Side-by-Side Comparison
Field
mnemosynememiniCategory
Memory & Context
Memory & Context
Stars
★ 151
★ 28
License
MIT
AGPL-3.0
Install Command
git clone --branch v2.0.0-rc.9 --depth 1 https://github.com/28naem-del/mnemosyne.git && cd mnemosyne && npm ci --ignore-scripts && npm run build
export MEMINI_EMBED_BASE_URL=http://localhost:8081/v1 && export MEMINI_EMBED_MODEL=bge-m3 && export MEMINI_EMBED_DIMS=1024 && mise run run
Updated
1d ago
3d ago
Open Source
Yes
Yes
Tags
AI Agents, Persistent Memory, Context Management
AI Agents, Persistent Memory, Vector Search
03
Features
mnemosyne01Memory with evidence: Private-by-default records, explicit sharing, corrections, conflicts, source history, and dependent retirement.
02Continuity across agents: Structured checkpoints preserve goals, decisions, artifacts, and next actions; source changes can retire obsolete handoffs.
03Adaptive context: Budgeted observations, hierarchical summaries, and expandable original source bytes, with evidence revalidation.
04Recall across words and meaning: Scoped BM25 by default; optional embeddings, hybrid fusion, and reranking over authorized records.
05Evidence-gated skills: Candidate procedures, explicit trial requirements, and retirement after failed or changed evidence.
memini01Shared, Persistent Memory: Provides a dedicated service for AI agents to store and retrieve memories, designed for long-term persistence.
02Hybrid Retrieval & Re-ranking: Employs a hybrid (vector + keyword) retrieval method, fused with Reciprocal Rank Fusion (RRF), and re-ranks results by relevance, recency, and importance, not just similarity.
03Tiered Memory System: Implements a tiered memory structure (working, episodic, semantic, procedural) with decay mechanisms.
04Pluggable Storage: Supports flexible storage options, including embedded SQLite-vec for local use and Postgres with VectorChord for scalable deployments.
05Optional LLM Consolidation: Features an opt-in LLM consolidation pipeline for background deduplication and contradiction resolution, but can run headless (without an LLM) using marker heuristics.
06Model Context Protocol (MCP) Support: Compatible with MCP-capable agents, offering both Streamable HTTP and stdio transports.
04
Use Cases
mnemosyne↳Building AI agents that require long-term, verifiable memory for decision-making and learning.
↳Enabling agents to resume complex tasks or projects across multiple sessions or handoffs without losing context.
↳Developing AI systems that adapt to new information by invalidating or correcting outdated knowledge based on source changes.
↳Creating self-improving agents where skills are refined or retired based on trial outcomes and evidence.
↳Managing dynamic context for large language models, ensuring relevance and adherence to evidence within token budgets.
memini↳Enhancing AI Agents with Long-Term Memory: Integrate memini to give AI agents (like Claude Code, opencode, Hermes) the ability to remember past interactions and learn over time.
↳Self-Hosting a Shared Memory Service: Deploy memini for a team or homelab environment to provide a centralized, persistent memory store for multiple AI agents.
↳Improving AI Recall Quality: Tune memini's retrieval parameters to fix bad recall and achieve higher accuracy in retrieving relevant information for AI models.
↳Managing Multi-Agent Namespaces: Lay out distinct namespaces within memini to provide isolation and organized memory management for several different AI agents.
↳Backend for Open WebUI Memory: Utilize memini as a robust memory backend for platforms like Open WebUI, integrating its memory and tool capabilities.
FAQ
FAQ
What is the difference between mnemosyne and memini?
Both mnemosyne and memini are in the Memory & Context category. mnemosyne has 151 stars, while memini has 28 stars.
Which is better, mnemosyne or memini?
The best choice depends on your use case. Choose mnemosyne if Building AI agents that require long-term, verifiable memory for decision-making and learning., and memini if Enhancing AI Agents with Long-Term Memory: Integrate memini to give AI agents (like Claude Code, opencode, Hermes) the ability to remember past interactions and learn over time..
Is mnemosyne free or open source?
Yes, mnemosyne is open source on GitHub (MIT).
Is memini free or open source?
Yes, memini is open source on GitHub (AGPL-3.0).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→