head to head · open source
claude-mem vs agent-rules-books
claude-mem has 94,286 GitHub stars, 8,321 forks, 186 open issues and last shipped yesterday. agent-rules-books has 2,829 stars, 501 forks, 5 open issues and last shipped 10 days ago. claude-mem leads on adoption by 3,233% (94,286 vs 2,829 stars). claude-mem is written in TypeScript under Apache-2.0; agent-rules-books is written in various languages under MIT. claude-mem has attracted 9% as many forks as stars, agent-rules-books 18%. claude-mem was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 1 topic tag (claude-code), so they are genuine substitutes rather than adjacent tools.
Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.
← all 20902 open source comparisons
Side by side
| claude-mem | agent-rules-books | |
|---|---|---|
| GitHub stars | ★ 94K | ★ 2.8K |
| License | Apache-2.0 | MIT |
| Written in | TypeScript | — |
| Last push | 2026-09-19 | 2026-09-10 |
| Forks | ⑂ 8.3K | ⑂ 501 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick claude-mem if
- You weight community size — 94K stars and counting
- You want the Apache-2.0 license terms
- Your stack matches TypeScript
- You value the larger contributor base for long-term maintenance
pick agent-rules-books if
- You want the agent-rules-books feature set and don't need the biggest community
- You prefer the MIT license terms
- You evaluated both and agent-rules-books fits your workflow better
About claude-mem
claude mem is an Apache 2.0 TypeScript memory layer for AI coding agents that captures what an agent did during a session, compresses it with AI, and injects the relevant parts back into future sessions, built for developers running Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode and similar tools.
read the full claude-mem overview →
About agent-rules-books
agent rules books is an MIT licensed, tool agnostic collection of AGENTS.md rules and agent skills, distilled from classic software engineering books, that installs into AI coding agents such as Codex, Cursor and Claude Code to steer them toward better refactoring, architecture, domain driven design and code quality.
read the full agent-rules-books overview →
More in AI & Machine Learning
Related comparisons
More AI Development Platforms projects
Compare either of these against the rest of the AI Development Platforms field.
Frequently asked questions
Is claude-mem or agent-rules-books more popular?
claude-mem has 94,286 GitHub stars and agent-rules-books has 2,829. claude-mem has the larger community by that measure.
Are claude-mem and agent-rules-books free?
Both are open source. claude-mem is licensed under Apache-2.0 and agent-rules-books under MIT. Neither carries a licence fee.
What is the difference between claude-mem and agent-rules-books?
claude-mem is written in TypeScript and agent-rules-books in various languages. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, claude-mem or agent-rules-books?
Choose claude-mem if you want the larger community (94,286 stars) or its Apache-2.0 licence terms. Choose agent-rules-books if its feature set, stack or MIT licence fits better. Both are self-hostable.