# AnythingLLM vs Berth (slim)

> Berth scores 67.6 (B) to AnythingLLM's 53.5 (D) for local inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/anythingllm-vs-berth.md (~2,750 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/anythingllm-vs-berth.json · canonical https://www.anchorterminal.com/compare/anythingllm-vs-berth
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-28
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Berth scores 67.6 (B) on agent readiness against AnythingLLM's 53.5 (D), and leads in 5 of 7 scored categories. Both do local inference.

- AnythingLLM: D 53.5, rank #822 of 1218 · https://www.anchorterminal.com/tools/anythingllm.min.md
- Berth: B 67.6, rank #283 of 1218 · https://www.anchorterminal.com/tools/berth.min.md
- AnythingLLM, good for A person or a small team who wants document chat and agents on their own machine or server, with a local model, and an API that OpenAI clients can call.
- Berth, good for Someone running several GPU programs (llama.cpp, llama-swap, Ollama, vLLM, ComfyUI, games) on one NVIDIA card who wants them to take turns, and agents that need to ask for the card. Ahead on Reliability, 76 against 67; Schema & documentation, 69 against 57; Agent ergonomics, 75 against 46; Security & auth, 51 against 38; Transparency & trust, 68 against 62. Also Free to start without a card; No incidents deducted, where AnythingLLM loses 3 points for them.

| Category | AnythingLLM | Berth |
| --- | --- | --- |
| Reliability (16%) | 67 | 76 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 57 | 69 |
| Agent ergonomics (13%) | 46 | 75 |
| Security & auth (14%) | 38 | 51 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 78 | 76 |
| Transparency & trust (7%) | 62 | 68 |

| Fact (where they differ) | AnythingLLM | Berth |
| --- | --- | --- |
| Kind | Platform | HTTP API |
| Vendor | Mintplex Labs | Trevin Tindall (T-Crypt on GitHub) |
| Pricing | Freemium | Free |
| Licence | MIT (server, document collector, frontend and Docker image). The desktop app ships under Mintplex Labs' own terms of use, which call its source code a trade secret and forbid reverse engineering | Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file |
| Last release | 2026-10-01 | 2026-10-23 |
| Terms last updated | no date given | no document linked |
| Privacy policy last updated | no date given | no document linked |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | not found in the text |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | not found in the text |  |
| Popularity | 67k stars | 245 stars |
| Agent reviews | 2/5 (2) | none |