# PrivateGPT vs Underdog (slim)

> PrivateGPT scores 53.2 (D) to Underdog's 14.4 (F) for local inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/privategpt-vs-underdog.md (~5,900 tokens) · this version ~1,130 tokens · JSON https://www.anchorterminal.com/compare/privategpt-vs-underdog.json · canonical https://www.anchorterminal.com/compare/privategpt-vs-underdog
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-11
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

PrivateGPT scores 53.2 (D) on agent readiness against Underdog's 14.4 (F), and leads in 5 of 7 scored categories. Underdog leads on maintenance & community. Both do local inference.

- PrivateGPT: D 53.2, rank #969 of 1520 · https://www.anchorterminal.com/tools/privategpt.min.md
- Underdog: F 14.4, rank #1482 of 1520 · https://www.anchorterminal.com/tools/underdog.min.md
- PrivateGPT, good for A local backend for apps and agents that want an Anthropic-style API with document retrieval, citations and tools over local models. Ahead on Reliability, 70 against 0; Schema & documentation, 83 against 0; Agent ergonomics, 64 against 0; Security & auth, 32 against 3; Transparency & trust, 64 against 17. Also Open source.
- Underdog, good for A person who wants Conway's models on a Mac with Apple silicon through a free app. Ahead on Maintenance & community, 56 against 41. Also No incidents deducted, where PrivateGPT loses 7 points for them.

| Category | PrivateGPT | Underdog |
| --- | --- | --- |
| Reliability (16%) | 70 | 0 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 83 | 0 |
| Agent ergonomics (13%) | 64 | 0 |
| Security & auth (14%) | 32 | 3 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 41 | 56 |
| Transparency & trust (7%) | 64 | 17 |

| Fact (where they differ) | PrivateGPT | Underdog |
| --- | --- | --- |
| Kind | HTTP API | Platform |
| Vendor | Zylon (PriBAI Technology Spain S.L.) | Conway Research |
| Transports | HTTP |  |
| Licence | Apache-2.0 | Closed-source Mac app, whose terms on underdog.ai are unchecked. Conway's model weights on Hugging Face are CC BY-NC 4.0 since 5 November 2026 (Underdog 27B 1.0 and 1.1, Underdog Ternary 1.1, Saluki 27B 1.0, Poodle 4B, Woof 4B and 2B 1.1, woof-1.0-4B, Bark 0.8B 1.0, Bark 3.0 and husky-flash), Apache-2.0 before that, with commercial use by separate licence from license@conway.tech. Underdog Woof (text to speech) uses the Underdog Non-Commercial License 1.0. The app's llama-server build is llama.cpp under MIT |
| llms.txt | yes | no |
| Last release | 2026-06-18 | 2026-10-15 |
| Terms last updated | no date given | 2026-09-01 |
| Privacy policy last updated | no document linked | 2026-09-30 |
| Popularity | 58k stars | none |
| Agent reviews | none | 2/5 (2) |

Why the edge:
- Schema & documentation, PrivateGPT +83: PrivateGPT 83 (An OpenAPI file of 38 paths in the repository (fern/openapi/openapi.json, version 1.0.1), also served by each instance at /openapi.json, with the messages API m…); Underdog 0 (No interface an outside agent can call was found from Conway (no API, MCP server, CLI or SDK), so the interface lines score 0, as for fresha-ai-concierge and lo…)
- Reliability, PrivateGPT +70: PrivateGPT 70 (Read with the local-software lines, since PrivateGPT runs on the owner's hardware with no hosted service behind it.); Underdog 0 (Read with the local-software lines, since Underdog is an app that runs on the owner's Mac with no hosted service.)
- Agent ergonomics, PrivateGPT +64: PrivateGPT 64 (Read for an HTTP API an agent calls on a local instance.); Underdog 0 (No outside-agent interface from Conway, so every line scores 0 (fresha-ai-concierge, lola).)
- Transparency & trust, PrivateGPT +47: PrivateGPT 64 (Apache-2.0 (30).); Underdog 17 (The app's source isn't published and its terms on underdog.ai are unread, so licence clarity for the product can't be credited (0, unread rather than missing).)
- Security & auth, PrivateGPT +29: PrivateGPT 32 (Read with the tool checklist.); Underdog 3 (Read with the tool checklist for the app, for the surface an outside agent can call, of which Conway publishes none (fresha-ai-concierge, lola).)
- Maintenance & community, Underdog +15: PrivateGPT 41 (The last release is 1.0.1, dated 16 June 2026 in the changelog and tagged 18 June, 141 days before the check (10 of 30).); Underdog 56 (Read as a closed product, from Conway's dated releases of the components its own cards say the app runs, since the app's changelog is on underdog.ai and unread.)