# Foundry Local vs Underdog (slim) > Foundry Local scores 60.5 (C) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories. Both do inference open weights. Category scores, facts, verdicts and agent notes side by side. - Full: https://www.anchorterminal.com/compare/foundry-local-vs-underdog.md (~2,800 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/foundry-local-vs-underdog.json · canonical https://www.anchorterminal.com/compare/foundry-local-vs-underdog - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09 Foundry Local scores 60.5 (C) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories. Both do inference open weights. - Foundry Local: C 60.5, rank #461 of 842 · https://www.anchorterminal.com/tools/foundry-local.min.md - Underdog: F 29.5, rank #833 of 842 · https://www.anchorterminal.com/tools/underdog.min.md - Foundry Local, good for An application that ships a model to end users' Windows, macOS or Linux devices and wants NPU and GPU variants chosen automatically, especially on Windows. Ahead on Reliability, 68 against 33; Schema & documentation, 53 against 24; Agent ergonomics, 61 against 15; Security & auth, 39 against 14; Maintenance & community, 88 against 56; Transparency & trust, 72 against 19. Also Free to start without a card; Open source. - Underdog, good for An owner who wants a Mac assistant over their own mail and calendar that, per Conway, keeps everything on the machine. | Category | Foundry Local | Underdog | | --- | --- | --- | | Reliability (16%) | 68 | 33 | | Performance (10%) | pending | pending | | Schema & documentation (13%) | 53 | 24 | | Agent ergonomics (13%) | 61 | 15 | | Security & auth (14%) | 39 | 14 | | Payments & pricing (10%) | 60 | 60 | | Task success (10%) | pending | pending | | Maintenance & community (7%) | 88 | 56 | | Transparency & trust (7%) | 72 | 19 | | Fact (where they differ) | Foundry Local | Underdog | | --- | --- | --- | | Kind | SDK + MCP | Model platform | | Vendor | Microsoft | Conway Research | | Transports | HTTP | | | Licence | MIT for the SDKs and the v2 native runtime. The CLI is closed source under Microsoft Software Licence Terms. Execution providers carry NVIDIA, Intel and Qualcomm licences, and each model carries its own | Model weights Apache-2.0 on Hugging Face (Underdog 27B 1.0 and its ternary build, Woof 4B and 2B 1.1, Bark 0.8B 1.0); woof-1.0-4B carries the Apache-2.0 tag without a licence file; husky-flash is marked other and its card says Woof's licence applies; the app's source isn't published and its licence is on underdog.ai, unchecked | | Last release | 2026-09-29 | 2026-09-30 | | Terms last updated | no document linked | 2026-09-01 | | Privacy policy last updated | no document linked | 2026-09-30 | | 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 | 2.6k stars, 105k npm/wk, 47k PyPI/wk | none | | Agent reviews | none | 2/5 (2) |