Agent-Memory vs core
Self-hosted AI memory and assistant projects compared
Agent-Memory provides persistent, searchable memory for coding agents, while core is a broader personal assistant that combines memory with task planning, integrations, and coding agents. Agent-Memory focuses on retaining and inspecting coding context; core coordinates work across connected services and multiple ways of interacting with the assistant.
Agent-Memory: Persistent Memory for AI Coding Agents on iii
Agent-Memory adds persistent, searchable memory to coding agents through the iii engine, sharing context across Claude Code, Cursor, Gemini CLI, Codex CLI, and other MCP or HTTP clients. It captures session activity and retrieves relevant context for later work.
core: Self-Host a Personal AI Assistant for Everyday Work
CORE is a self-hosted AI assistant that combines persistent memory, task planning, app integrations, and coding agents. It suits people who want one assistant to work across their tools, with human approval and control over their data.
| Agent-Memory | core | |
|---|---|---|
| Language | — | TypeScript |
| License | Apache-2.0 | NOASSERTION |
| Stars | 9 | 2k |
| Forks | 4 | 196 |
| Last analyzed | Nov 1, 2026 | Oct 3, 2026 |
Key differences
- Agent-Memory is centered on capturing, searching, and sharing coding-agent memory; core also organizes tasks, plans work, and acts through integrations, a browser, and a terminal.
- Agent-Memory describes MCP and REST API access, lifecycle hooks, and a local viewer; core describes a web interface, messaging channels, voice, and connections to 50+ apps through MCP.
- Agent-Memory is built on the iii engine and can run with its native binary or Docker; core requires Docker and Docker Compose, with additional gateway setup for some capabilities.
- Agent-Memory uses an Apache-2.0 license; core's metadata says NOASSERTION, while its README displays an AGPL 3.0 badge, so verify the license before adoption.
- The supplied repository figures are 6 stars and 1 fork for Agent-Memory, compared with 2k stars and 196 forks for core. Core also lists 211 open issues.
- Agent-Memory targets developers who want coding context retained across sessions and agents; core targets developers and productivity-focused users coordinating work across tools.
Choose Agent-Memory if you…
- need persistent, searchable context specifically for coding-agent sessions.
- want to share memory across compatible coding agents through MCP or a REST API.
- prefer a focused memory server with a viewer for inspecting captured activity.
Choose core if you…
- want one assistant to organize tasks and use context from connected services.
- need integrations, recurring tasks, or event-triggered work through webhooks.
- want to delegate coding work to Claude Code or Codex and access the assistant through supported messaging channels.
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.