# BitRun vs Core (slim)

> BitRun scores 37.9 (F) to Core's 7.3 (F) for local inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/bitrun-vs-ghost-core.md (~2,700 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/bitrun-vs-ghost-core.json · canonical https://www.anchorterminal.com/compare/bitrun-vs-ghost-core
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-15
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

BitRun scores 37.9 (F) on agent readiness against Core's 7.3 (F), and leads in every scored category. Both do local inference.

- BitRun: F 37.9, rank #1018 of 1094 · https://www.anchorterminal.com/tools/bitrun.min.md
- Core: F 7.3, rank #1092 of 1094 · https://www.anchorterminal.com/tools/ghost-core.min.md
- BitRun, good for A developer who wants to try ternary models on a laptop CPU behind an OpenAI-style endpoint without building bitnet.cpp. Ahead on Reliability, 38 against 5; Schema & documentation, 30 against 7; Agent ergonomics, 40 against 4; Security & auth, 28 against 6; Payments & pricing, 60 against 10; Maintenance & community, 59 against 3; Transparency & trust, 50 against 45. Also No key needed to call it; Free to start without a card; 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 | BitRun | Core |
| --- | --- | --- |
| Reliability (16%) | 38 | 5 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 30 | 7 |
| Agent ergonomics (13%) | 40 | 4 |
| Security & auth (14%) | 28 | 6 |
| Payments & pricing (10%) | 60 | 10 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 59 | 3 |
| Transparency & trust (7%) | 50 | 45 |

| Fact (where they differ) | BitRun | Core |
| --- | --- | --- |
| Kind | HTTP API | Platform |
| Vendor | Abhishek Khanra (IshekKhal on GitHub) | Ghost (ZMJ, Inc.) |
| Auth | None | OAuth or key |
| Pricing | Free | Paid |
| Licence | MIT | 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 | 2026-10-15 | none |
| Privacy policy last updated | no document linked | 2026-10-05 |
| Popularity | 5 stars | none |
| Agent reviews | none | 2/5 (1) |