--- title: "3D-Mem vs automem" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/umass-embodied-agi-3d-mem-vs-verygoodplugins-automem" tools: ["umass-embodied-agi-3d-mem", "verygoodplugins-automem"] --- # 3D-Mem vs automem *GraphCanon updated Aug 21, 2026* ## Verdict Pick 3D-Mem if 3D-Mem excels in environments where embodied AI needs spatial intelligence for exploration and reasoning in 3D scenes; pick automem if autoMem leverages both graph and vector database technologies to provide AI assistants with durable relational memory. [3D-Mem](https://umass-embodied-agi.github.io/3D-Mem/) reports 270 GitHub stars, 17 forks, and 3 open issues, last pushed Oct 2, 2025. [automem](https://automem.ai/) has 802 stars, 102 forks, and 15 open issues, last pushed Aug 14, 2026. Figures are from public GitHub metadata via [3D-Mem's repository](https://github.com/UMass-Embodied-AGI/3D-Mem) and [automem's repository](https://github.com/verygoodplugins/automem). | | [3D-Mem](/tools/umass-embodied-agi-3d-mem.md) | [automem](/tools/verygoodplugins-automem.md) | | --- | --- | --- | | Tagline | 3D scene memory for embodied AI exploration and reasoning | Graph-vector memory service for durable, relational AI assistant memory | | Stars | 270 | 802 | | Forks | 17 | 102 | | Open issues | 3 | 15 | | Language | Python | Python | | Adopt for | 3D-Mem excels in environments where embodied AI needs spatial intelligence for exploration and reasoning in 3D scenes. | AutoMem leverages both graph and vector database technologies to provide AI assistants with durable relational memory. | | Persona | - | - | | Runtime | - | - | | License | MIT | AutoMem is licensed under the MIT License, which means it is free to use, modify, and distribute as long as license terms are met. | | Categories | Computer Vision | AI Agents, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [3D-Mem](/tools/umass-embodied-agi-3d-mem.md) | [automem](/tools/verygoodplugins-automem.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Active (82%) | | Days since push | 302d | 7d | | Open issues (now) | 3 | 15 | | Stars delta | Unknown | +9 (30d) | | Open issues delta | Unknown | +4 (30d) | | Full report | [trust report](/tools/umass-embodied-agi-3d-mem/trust.md) | [trust report](/tools/verygoodplugins-automem/trust.md) | ## Decision facts: 3D-Mem - **Adopt for:** 3D-Mem excels in environments where embodied AI needs spatial intelligence for exploration and reasoning in 3D scenes. ## Decision facts: automem - **Pricing:** freemium - Free for open-source use, with no explicit commercial licensing information provided. - **Adopt for:** AutoMem leverages both graph and vector database technologies to provide AI assistants with durable relational memory. - **License detail:** AutoMem is licensed under the MIT License, which means it is free to use, modify, and distribute as long as license terms are met. ## Choose when ### Choose 3D-Mem if… - Tags unique to 3D-Mem: ai, embodied-ai, spatial-intelligence. - Also covers Computer Vision. - Use if your project involves embodied AI systems that require detailed scene understanding in 3D ### Choose automem if… - Pricing: Free for open-source use, with no explicit commercial licensing information provided.. - Tags unique to automem: ai-memory, anthropic, falkordb, graph-database. - Also covers AI Agents, Vector Databases. - automem ships Docker support for self-hosted deployment. - Use AutoMem when you need an AI assistant capable of maintaining rich, relational memories over time. ## When NOT to use 3D-Mem - Avoid for environments where 2D image analysis suffices over deeper 3D spatial reasoning - This may not be suitable if real-time performance is more critical than the richness of 3D scene intelligence ## When NOT to use automem - Avoid using AutoMem if your application does not benefit from persistent memory or relational context, as it might add unnecessary overhead. - If you require a simpler key-value storage system for less complex or non-relational data, AutoMem's graph and vector capabilities may be overkill. ## Common questions ### What is the difference between 3D-Mem and automem? 3D-Mem: 3D scene memory for embodied AI exploration and reasoning. automem: Graph-vector memory service for durable, relational AI assistant memory. See the comparison table for live GitHub stats and shared categories. ### When should I choose 3D-Mem over automem? Choose 3D-Mem over automem when Tags unique to 3D-Mem: ai, embodied-ai, spatial-intelligence; Also covers Computer Vision; Use if your project involves embodied AI systems that require detailed scene understanding in 3D. ### When should I choose automem over 3D-Mem? Choose automem over 3D-Mem when Pricing: Free for open-source use, with no explicit commercial licensing information provided.; Tags unique to automem: ai-memory, anthropic, falkordb, graph-database; Also covers AI Agents, Vector Databases; automem ships Docker support for self-hosted deployment; Use AutoMem when you need an AI assistant capable of maintaining rich, relational memories over time. ### When should I avoid 3D-Mem? Avoid for environments where 2D image analysis suffices over deeper 3D spatial reasoning This may not be suitable if real-time performance is more critical than the richness of 3D scene intelligence ### When should I avoid automem? Avoid using AutoMem if your application does not benefit from persistent memory or relational context, as it might add unnecessary overhead. If you require a simpler key-value storage system for less complex or non-relational data, AutoMem's graph and vector capabilities may be overkill. ### Is 3D-Mem or automem more popular on GitHub? automem has more GitHub stars (802 vs 270). Stars measure visibility, not whether either tool fits your constraints. ### Are 3D-Mem and automem open source? Yes - both are open-source projects on GitHub (3D-Mem: MIT, automem: MIT). ### Where can I find alternatives to 3D-Mem or automem? GraphCanon lists graph-backed alternatives at [3D-Mem alternatives](/tools/umass-embodied-agi-3d-mem/alternatives) and [automem alternatives](/tools/verygoodplugins-automem/alternatives) ([3D-Mem markdown twin](/tools/umass-embodied-agi-3d-mem/alternatives.md), [automem markdown twin](/tools/verygoodplugins-automem/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/umass-embodied-agi-3d-mem-vs-verygoodplugins-automem.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, 3D-Mem or automem? 3D-Mem: Slowing. automem: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for 3D-Mem and automem? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [3D-Mem trust report](/tools/umass-embodied-agi-3d-mem/trust); [automem trust report](/tools/verygoodplugins-automem/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=umass-embodied-agi-3d-mem`](/api/graphcanon/graph?tool=umass-embodied-agi-3d-mem) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_