--- title: "Ori-Mnemos vs mengram" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/aayoawoyemi-ori-mnemos-vs-alibaizhanov-mengram" tools: ["aayoawoyemi-ori-mnemos", "alibaizhanov-mengram"] --- # Ori-Mnemos vs mengram *GraphCanon updated Sep 30, 2026* ## Verdict Pick Ori-Mnemos if ori-Mnemos is a local-first, persistent agentic memory system leveraging SQLite and TypeScript. It incorporates Recursive Memory Harness (RMH) for AI agents; pick mengram if mengram provides human-like memory capabilities for AI agents, including semantic, episodic, and procedural memory, enabling learning from experiences and failures. It offers free API access, Python and JS SDKs, and is a. [Ori-Mnemos](https://orimnemos.com.) reports 324 GitHub stars, 31 forks, and 1 open issues, last pushed Sep 20, 2026. [mengram](https://mengram.io) has 196 stars, 34 forks, and 25 open issues, last pushed Sep 16, 2026. Figures are from public GitHub metadata via [Ori-Mnemos's repository](https://github.com/aayoawoyemi/Ori-Mnemos) and [mengram's repository](https://github.com/alibaizhanov/mengram). | | [Ori-Mnemos](/tools/aayoawoyemi-ori-mnemos.md) | [mengram](/tools/alibaizhanov-mengram.md) | | --- | --- | --- | | Tagline | Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). | Human-like memory for AI agents | | Stars | 324 | 196 | | Forks | 31 | 34 | | Open issues | 1 | 25 | | Language | TypeScript | Python | | Adopt for | Ori-Mnemos is a local-first, persistent agentic memory system leveraging SQLite and TypeScript. It incorporates Recursive Memory Harness (RMH) for AI agents. | mengram provides human-like memory capabilities for AI agents, including semantic, episodic, and procedural memory, enabling learning from experiences and failures. It offers free API access, Python and JS SDKs, and is a | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Apache-2.0 | | Categories | AI Agents, Data & Retrieval | AI Agents, Data & Retrieval | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [Ori-Mnemos](/tools/aayoawoyemi-ori-mnemos.md) | [mengram](/tools/alibaizhanov-mengram.md) | | --- | --- | --- | | Days since push | 0d | 1d | | Open issues (now) | 1 | 25 | | Stars delta | +10 (30d) | +12 (30d) | | Open issues delta | +1 (30d) | -2 (30d) | | Full report | [trust report](/tools/aayoawoyemi-ori-mnemos/trust.md) | [trust report](/tools/alibaizhanov-mengram/trust.md) | ## Shared compatibility - **Cursor**: [Ori-Mnemos](/tools/aayoawoyemi-ori-mnemos.md) - Works with Cursor; [mengram](/tools/alibaizhanov-mengram.md) - Works with Cursor ## Decision facts: Ori-Mnemos - **Adopt for:** Ori-Mnemos is a local-first, persistent agentic memory system leveraging SQLite and TypeScript. It incorporates Recursive Memory Harness (RMH) for AI agents. ## Decision facts: mengram - **Adopt for:** mengram provides human-like memory capabilities for AI agents, including semantic, episodic, and procedural memory, enabling learning from experiences and failures. It offers free API access, Python and JS SDKs, and is a ## Choose when ### Choose Ori-Mnemos if… - Ori-Mnemos is primarily TypeScript; mengram is Python. - Tags unique to Ori-Mnemos: knowledge-graph, llm, local-first, markdown. - Ori-Mnemos ships an MCP server manifest. - When you need a robust, local-first solution that prioritizes offline capabilities and security. ### Choose mengram if… - mengram is primarily Python; Ori-Mnemos is TypeScript. - Tags unique to mengram: ai-memory, claude-desktop, cognitive-architecture, cohere. - mengram ships Docker support for self-hosted deployment. - When you need an AI agent that can learn from its experiences and failures, leveraging semantic, episodic, and procedural memory capabilities. ## When NOT to use Ori-Mnemos - When real-time synchronization across devices or cloud integration is a non-negotiable requirement for your application. - If you are looking for a memory system that leverages distributed databases for scalable access patterns; Ori-Mnemos focuses on local storage using SQLite. - In environments where complex, multi-node architectures and high availability requirements demand more than a single point of data persistence. ## When NOT to use mengram - If your project does not require the specific memory capabilities of semantic, episodic, and procedural memory, mengram might offer more features than necessary. - If you are looking for a tool that does not require the setup of an MCP server, mengram might not be the best fit as it involves configuring this server. - For projects that do not need integration with LangChain, CrewAI, or OpenClaw, the specific integrations provided by mengram may not be beneficial. - If your AI agent development does not benefit from the use of pgvector, mengram's recent debugging efforts in this area may not be relevant to your needs. ## Common questions ### What is the difference between Ori-Mnemos and mengram? Ori-Mnemos: Local-first persistent agentic memory powered by Recursive Memory Harness (RMH).. mengram: Human-like memory for AI agents. See the comparison table for live GitHub stats and shared categories. ### When should I choose Ori-Mnemos over mengram? Choose Ori-Mnemos over mengram when Ori-Mnemos is primarily TypeScript; mengram is Python; Tags unique to Ori-Mnemos: knowledge-graph, llm, local-first, markdown; Ori-Mnemos ships an MCP server manifest; When you need a robust, local-first solution that prioritizes offline capabilities and security. ### When should I choose mengram over Ori-Mnemos? Choose mengram over Ori-Mnemos when mengram is primarily Python; Ori-Mnemos is TypeScript; Tags unique to mengram: ai-memory, claude-desktop, cognitive-architecture, cohere; mengram ships Docker support for self-hosted deployment; When you need an AI agent that can learn from its experiences and failures, leveraging semantic, episodic, and procedural memory capabilities. ### When should I avoid Ori-Mnemos? When real-time synchronization across devices or cloud integration is a non-negotiable requirement for your application. If you are looking for a memory system that leverages distributed databases for scalable access patterns; Ori-Mnemos focuses on local storage using SQLite. In environments where complex, multi-node architectures and high availability requirements demand more than a single point of data persistence. ### When should I avoid mengram? If your project does not require the specific memory capabilities of semantic, episodic, and procedural memory, mengram might offer more features than necessary. If you are looking for a tool that does not require the setup of an MCP server, mengram might not be the best fit as it involves configuring this server. For projects that do not need integration with LangChain, CrewAI, or OpenClaw, the specific integrations provided by mengram may not be beneficial. If your AI agent development does not benefit from the use of pgvector, mengram's recent debugging efforts in this area may not be relevant to your needs. ### Is Ori-Mnemos or mengram more popular on GitHub? Ori-Mnemos has more GitHub stars (324 vs 196). Stars measure visibility, not whether either tool fits your constraints. ### Are Ori-Mnemos and mengram open source? Yes - both are open-source projects on GitHub (Ori-Mnemos: Apache-2.0, mengram: Apache-2.0). ### Where can I find alternatives to Ori-Mnemos or mengram? GraphCanon lists graph-backed alternatives at [Ori-Mnemos alternatives](/tools/aayoawoyemi-ori-mnemos/alternatives) and [mengram alternatives](/tools/alibaizhanov-mengram/alternatives) ([Ori-Mnemos markdown twin](/tools/aayoawoyemi-ori-mnemos/alternatives.md), [mengram markdown twin](/tools/alibaizhanov-mengram/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/aayoawoyemi-ori-mnemos-vs-alibaizhanov-mengram.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, Ori-Mnemos or mengram? Ori-Mnemos: Very active. mengram: Very 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 Ori-Mnemos and mengram? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [Ori-Mnemos trust report](/tools/aayoawoyemi-ori-mnemos/trust); [mengram trust report](/tools/alibaizhanov-mengram/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=aayoawoyemi-ori-mnemos`](/api/graphcanon/graph?tool=aayoawoyemi-ori-mnemos) - 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/_