ai-memory vs cabinet
Self-hosted Markdown knowledge tools compared
ai-memory and cabinet both keep project knowledge in Markdown files under user control. ai-memory focuses on capturing coding-agent activity and handing work between agents, while cabinet combines a knowledge base with agent orchestration and team workflows.
ai-memory: Share Long-Term Memory Across Coding Agents
A self-hosted Rust service that captures coding-agent activity into a searchable, git-backed Markdown wiki and hands work between agents. It suits developers and teams who want portable project memory without requiring LLM calls.
cabinet: Build a Self-Hosted AI Knowledge Base
Cabinet combines a local, Markdown-based knowledge base with AI agents, scheduled jobs, and team workflows. It is aimed at people who want persistent AI context and automation while keeping their files on disk and under their control.
| ai-memory | cabinet | |
|---|---|---|
| Language | Rust | TypeScript |
| License | MIT | MIT |
| Stars | 9.1k | 2.9k |
| Forks | 632 | 302 |
| Last analyzed | Oct 10, 2026 | Oct 3, 2026 |
Key differences
- ai-memory captures prompts, tool calls, and session boundaries through agent integrations; cabinet organizes work around agents, goals, missions, and tasks.
- ai-memory provides basic capture, search, and handoffs without LLM API calls; cabinet requires Node.js 22 or later and a supported Claude Code or Codex CLI provider.
- ai-memory is written in Rust; cabinet is written in TypeScript. Both use the MIT license.
- ai-memory offers optional vector search, embeddings, and content consolidation; cabinet includes scheduled jobs, Kanban boards, internal chat, and HTML apps in knowledge-base folders.
- ai-memory is aimed at developers and teams handing off coding work across agents, machines, and teammates; cabinet targets individuals and small teams seeking a workspace for knowledge and repeatable agent tasks.
- Both are self-hosted and not archived. ai-memory has 8.8k stars and 608 forks, compared with cabinet's 2.9k stars and 302 forks.
Choose ai-memory if you…
- need to preserve coding-agent sessions and pass typed handoffs between agents.
- want searchable, git-backed project memory whose basic capture and retrieval do not depend on LLM API calls.
- prefer a Rust server and CLI focused on coding-agent context.
Choose cabinet if you…
- want agents, scheduled jobs, goals, and team workflows alongside a Markdown knowledge base.
- need a local workspace with Kanban boards, internal chat, or embedded HTML apps.
- are comfortable running a Node.js application and configuring Claude Code or Codex CLI.
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.