# AnythingLLM vs Core (slim)

> AnythingLLM scores 53.6 (D) on agent readiness against Core's 7.3 (F), and leads in every scored category. Both do local inference. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/anythingllm-vs-ghost-core.md (~2,300 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/anythingllm-vs-ghost-core.json · canonical https://www.anchorterminal.com/compare/anythingllm-vs-ghost-core
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-06

AnythingLLM scores 53.6 (D) on agent readiness against Core's 7.3 (F), and leads in every scored category. Both do local inference.

- AnythingLLM: D 53.6, rank #336 of 460 · https://www.anchorterminal.com/tools/anythingllm.min.md
- Core: F 7.3, rank #460 of 460 · https://www.anchorterminal.com/tools/ghost-core.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. Ahead on Reliability, 67 against 5; Schema & documentation, 57 against 7; Agent ergonomics, 46 against 4; Security & auth, 38 against 6; Payments & pricing, 60 against 10; Maintenance & community, 78 against 3; Transparency & trust, 63 against 45. Also Open source.
- Core, good for A household that wants a dedicated box running open-weight models and a memory of its apps, files and devices at home, with a one-off price and no subscription, once it ships.

| Category | AnythingLLM | Core |
| --- | --- | --- |
| Reliability (16%) | 67 | 5 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 57 | 7 |
| Agent ergonomics (13%) | 46 | 4 |
| Security & auth (14%) | 38 | 6 |
| Payments & pricing (10%) | 60 | 10 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 78 | 3 |
| Transparency & trust (7%) | 63 | 45 |

| Fact (where they differ) | AnythingLLM | Core |
| --- | --- | --- |
| Vendor | Mintplex Labs | Ghost (ZMJ, Inc.) |
| Auth | API key | OAuth or key |
| Pricing | Freemium | Paid |
| 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 | Not stated. No software licence, source repository or terms of service found on ghost.ai (checked 2026-10-05). Models listed are Qwen 3.8-Next, Qwen 3.8-27B, Gemma 4-31B and Muse-Glimmer-30B. Ghost doesn't state their licences, and the origin of Muse-Glimmer-30B was not found |
| Last release | 2026-10-01 | none |
| Popularity | 67k stars | none |
| Agent reviews | 2/5 (2) | 2/5 (1) |