A
anything-llm
95.9
68,366 stars · MIT
AI Agents
claude-mem leads by 3.2 · narrow
A
95.9
68,366 stars · MIT
B · leads
99.1
117,865 stars · Apache-2.0
anything-llm versus claude-mem is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. anything-llm is written mainly in JavaScript; claude-mem is written mainly in TypeScript. The composite score is 95.9 for anything-llm and 99.1 for claude-mem.
claude-mem has 117,865 GitHub stars to anything-llm's 68,366, a gap of 49,499 (1.72×). Forks are 7,723 for anything-llm and 10,242 for claude-mem. On the log scale used inside this pair, adoption is 95 versus 100, and the fork community is 97 versus 100.
Push history: anything-llm was last pushed on 17 November 2026 (0 days ago), and claude-mem was last pushed on 17 November 2026 (0 days ago). Open issues stand at 358 for anything-llm (0.005 per star) and 159 for claude-mem (0.001 per star). Issue-health scores are 84 and 96; activity scores are 100 and 100.
anything-llm is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. claude-mem is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. License scores in this pair are 96 for anything-llm and 96 for claude-mem. This is a procurement signal, not legal advice.
In AI Agents, both anything-llm (68,366 stars) and claude-mem (117,865 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: anything-llm is open source, claude-mem is open source.
claude-mem is ahead on every scored dimension that is not level. Level dimensions: recent activity, license flexibility, self-hosting. The widest gap is issue health at 12 points (84 vs 96), and the tightest is self-hosting at 0 points (100 vs 100).
claude-mem finishes ahead at 99.1 against anything-llm at 95.9, a 3.2 point narrow margin under the published weights.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | anything-llm | claude-mem |
|---|---|---|
| GitHub stars | 68,366 | 117,865 |
| Forks | 7,723 | 10,242 |
| Open issues | 358 | 159 |
| Adoption | 95 | 100 |
| Activity | 100 | 100 |
| Community | 97 | 100 |
| Issue health | 84 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 95.9 | 99.1 |
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
claude-mem has more GitHub stars: 117,865 versus 68,366 for anything-llm. The gap is 49,499 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both anything-llm and claude-mem as self-hostable. Confirm each project's deploy docs before you plan a migration.
anything-llm is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. claude-mem is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
claude-mem scores 99.1 and anything-llm scores 95.9. This page calls that a narrow lead for claude-mem.