A
anything-llm
97.9
68,366 stars · MIT
AI Agents
claude-code-best-practice leads by 1.0 · narrow
A
97.9
68,366 stars · MIT
B · leads
98.9
69,156 stars · MIT
anything-llm versus claude-code-best-practice 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-code-best-practice is written mainly in HTML. The composite score is 97.9 for anything-llm and 98.9 for claude-code-best-practice.
claude-code-best-practice has 69,156 GitHub stars to anything-llm's 68,366, a gap of 790 (1.01×). Forks are 7,723 for anything-llm and 6,878 for claude-code-best-practice. On the log scale used inside this pair, adoption is 100 versus 100, and the fork community is 100 versus 99.
Push history: anything-llm was last pushed on 17 November 2026 (0 days ago), and claude-code-best-practice was last pushed on 17 November 2026 (0 days ago). Open issues stand at 358 for anything-llm (0.005 per star) and 27 for claude-code-best-practice (0.000 per star). Issue-health scores are 84 and 96; activity scores are 100 and 100.
Both anything-llm and claude-code-best-practice are listed as MIT. 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. The license score is therefore level at 96 versus 96, and the decision moves to adoption, activity, and hosting. This is a procurement signal, not legal advice.
In AI Agents, both anything-llm (68,366 stars) and claude-code-best-practice (69,156 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-code-best-practice is open source.
The lead is split. anything-llm is furthest ahead on fork community (100 to 99), while claude-code-best-practice is furthest ahead on issue health (96 to 84). Choose the dimension a rollout cannot compromise on.
claude-code-best-practice finishes ahead at 98.9 against anything-llm at 97.9, a 1.0 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-code-best-practice |
|---|---|---|
| GitHub stars | 68,366 | 69,156 |
| Forks | 7,723 | 6,878 |
| Open issues | 358 | 27 |
| Adoption | 100 | 100 |
| Activity | 100 | 100 |
| Community | 100 | 99 |
| Issue health | 84 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.9 | 98.9 |
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
from vibe coding to agentic engineering - practice makes claude perfect
claude-code-best-practice has more GitHub stars: 69,156 versus 68,366 for anything-llm. The gap is 790 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both anything-llm and claude-code-best-practice 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-code-best-practice 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. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
claude-code-best-practice scores 98.9 and anything-llm scores 97.9. This page calls that a narrow lead for claude-code-best-practice.