open-index vs agentmemory
Persistent, searchable context for AI agents compared
open-index builds structured domain knowledge that agents can search and maintain, while agentmemory captures coding-agent activity to support recall across sessions. The main difference is scope: open-index centers on curated, schema-defined context graphs, while agentmemory centers on persistent memory for coding workflows.
open-index: Build Agent Memory on SQLite and OpenSearch
Open Index is a domain-agnostic memory layer for agents, built around a searchable context graph with SQLite and FTS5 by default, plus an OpenSearch backend. Define structured concepts and relationships, then let agents search and maintain that knowledge through MCP.
agentmemory: Persistent Memory for AI Coding Agents
agentmemory gives coding agents persistent, searchable memory across sessions and tools. It captures work through agent integrations and exposes shared memory through MCP and REST, with a local-first runtime built on iii-engine.
| open-index | agentmemory | |
|---|---|---|
| Language | Python | TypeScript |
| License | MIT | Apache-2.0 |
| Stars | 112 | 29.1k |
| Forks | 5 | 2.5k |
| Last analyzed | Oct 21, 2026 | Oct 3, 2026 |
Key differences
- open-index models concepts, fields, entities, and relationships; agentmemory captures prompts and tool activity and organizes observations into memory tiers.
- open-index supports file-backed or database-backed knowledge and imports from files or connectors; agentmemory integrates with coding-agent hooks and provides MCP and REST access.
- open-index is written in Python and licensed under MIT; agentmemory is written in TypeScript and licensed under Apache-2.0.
- open-index uses SQLite and FTS5 by default, with optional OpenSearch; agentmemory uses BM25 by default, with optional vector embeddings and graph-based matching.
- open-index is suited to domain knowledge across areas such as support, infrastructure, and sales; agentmemory focuses on coding-project context across sessions and agents.
- open-index lists 112 stars and 5 forks; agentmemory lists 29.1k stars and 2.5k forks, and its supplied metadata also lists 599 open issues.
Choose open-index if you…
- need validated, schema-defined domain records and relationships for agents.
- want file-backed knowledge that can be reviewed in git, or database-backed data fed by connectors.
- need to expose a shared context graph through MCP, with SQLite by default and OpenSearch as an option.
Choose agentmemory if you…
- want coding agents to capture session activity and retrieve project context later.
- need memory shared across compatible coding agents through MCP or REST.
- want BM25 keyword search by default, with optional local embeddings and a session viewer.
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.