Memori vs OpenViking
Persistent context for AI agents compared
Memori and OpenViking both help AI agents retain context across sessions. Memori focuses on turning conversations and agent execution into structured memory, while OpenViking organizes documents, memories, and skills in a browsable virtual filesystem with scoped retrieval.

Memori: Persist Structured Memory for AI Agents
Memori is LLM-agnostic memory infrastructure that turns agent conversations and execution into structured, persistent state. Its Python and TypeScript SDKs support managed cloud, single-tenant cloud, VPC, and on-premises deployments.

OpenViking: Organize Agent Memory, Knowledge, and Skills
OpenViking is a context database for AI agents that organizes knowledge, memories, and skills in a browsable virtual filesystem. It supports scoped retrieval and agent integrations, with options to self-host or use a hosted service.
| Memori | OpenViking | |
|---|---|---|
| Language | Python | Python |
| License | — | AGPL-3.0 |
| Stars | 17.2k | 39.2k |
| Forks | 3.8k | 3.1k |
| Last analyzed | Oct 19, 2026 | Oct 3, 2026 |
Key differences
- Memori structures conversations and agent execution as attributed memories, while OpenViking stores resources, memories, and skills under browsable `viking://` paths.
- Memori offers Python and TypeScript SDKs; OpenViking also lists Go SDKs, plus a CLI, HTTP API, web studio, and optional VikingBot framework.
- Memori supports managed cloud, single-tenant cloud, VPC, and on-premises deployments; OpenViking offers self-hosting and a hosted service, with some self-managed capabilities requiring a separate license.
- Memori describes its license as Apache 2.0 in the README; OpenViking's main project is licensed under AGPLv3.
- Memori's stated integrations include MCP, OpenClaw, and Hermes; OpenViking lists coding-agent and MCP integrations, as well as LangChain.
- OpenViking emphasizes retrieval scoped to a directory or subtree and editable Markdown memories; Memori emphasizes memory organized into attributes such as facts, events, preferences, and skills.
Choose Memori if you…
- need structured memory from both conversations and agent execution.
- want deployment choices that include VPC or on-premises environments.
- prefer Python or TypeScript SDKs and integrations such as MCP, OpenClaw, or Hermes.
Choose OpenViking if you…
- want context organized in a browsable virtual filesystem with directory-scoped retrieval.
- need tools such as a CLI, HTTP API, web studio, or Go SDK alongside Python and TypeScript SDKs.
- want to self-host or use a hosted service, and can review AGPLv3 and any component-specific licensing requirements.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.