head to head · open source
claude-mem vs LightRAG
claude-mem has 94,145 GitHub stars, 8,309 forks, 186 open issues and last shipped 2 days ago. LightRAG has 39,738 stars, 5,589 forks, 222 open issues and last shipped yesterday. claude-mem leads on adoption by 137% (94,145 vs 39,738 stars). claude-mem is written in TypeScript under Apache-2.0; LightRAG is written in Python under MIT. claude-mem has attracted 9% as many forks as stars, LightRAG 14%. LightRAG was the more recently maintained of the two, and both are self-hostable with no licence fee.
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 13541 open source comparisons
Side by side
| claude-mem | LightRAG | |
|---|---|---|
| GitHub stars | ★ 94K | ★ 40K |
| License | Apache-2.0 | MIT |
| Written in | TypeScript | Python |
| Last push | 2026-09-17 | 2026-09-18 |
| Forks | ⑂ 8.3K | ⑂ 5.6K |
| 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 LightRAG if
- You want the LightRAG feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches Python
- You evaluated both and LightRAG 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 LightRAG
LightRAG is a Python retrieval augmented generation framework, released under the MIT licence and presented in an EMNLP 2025 paper, that builds a knowledge graph over documents so that queries can be answered from both graph structure and vector similarity.
read the full LightRAG 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 LightRAG more popular?
claude-mem has 94,145 GitHub stars and LightRAG has 39,738. claude-mem has the larger community by that measure.
Are claude-mem and LightRAG free?
Both are open source. claude-mem is licensed under Apache-2.0 and LightRAG under MIT. Neither carries a licence fee.
What is the difference between claude-mem and LightRAG?
claude-mem is written in TypeScript and LightRAG in Python. 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 LightRAG?
Choose claude-mem if you want the larger community (94,145 stars) or its Apache-2.0 licence terms. Choose LightRAG if its feature set, stack or MIT licence fits better. Both are self-hostable.