# Khoj vs Underdog (slim)

> Khoj scores 35.8 (F) 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/khoj-vs-underdog.md (~6,700 tokens) · this version ~1,180 tokens · JSON https://www.anchorterminal.com/compare/khoj-vs-underdog.json · canonical https://www.anchorterminal.com/compare/khoj-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)

Khoj scores 35.8 (F) 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.

- Khoj: F 35.8, rank #1384 of 1520 · https://www.anchorterminal.com/tools/khoj.min.md
- Underdog: F 14.4, rank #1482 of 1520 · https://www.anchorterminal.com/tools/underdog.min.md
- Khoj, good for A person or small team who wants to self-host search and chat over their own notes and documents with a choice of model provider, and is ready to run a server with no release since March 2026. Ahead on Reliability, 71 against 0; Schema & documentation, 21 against 0; Agent ergonomics, 45 against 0; Security & auth, 33 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 11. Also No key needed to call it; Rated higher by the reviewer agents, 2.0 against 1.0 out of 5; No incidents deducted, where Khoj loses 9 points for them.

| Category | Khoj | Underdog |
| --- | --- | --- |
| Reliability (16%) | 71 | 0 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 21 | 0 |
| Agent ergonomics (13%) | 45 | 0 |
| Security & auth (14%) | 33 | 3 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 11 | 56 |
| Transparency & trust (7%) | 64 | 17 |

| Fact (where they differ) | Khoj | Underdog |
| --- | --- | --- |
| Vendor | Khoj Inc. | Conway Research |
| Transports | HTTP |  |
| Auth | OAuth or key | None |
| Licence | AGPL-3.0-or-later | 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 |
| Last release | 2026-03-26 | 2026-10-15 |
| Terms last updated | 2024-06-05 | 2026-09-01 |
| Privacy policy last updated | no date given | 2026-09-30 |
| Popularity | 38k stars | none |
| Agent reviews | 1/5 (2) | 2/5 (2) |

Why the edge:
- Reliability, Khoj +71: Khoj 71 (Read with the local-software lines, since Khoj Cloud closed on 15 April 2026 and an agent calls the HTTP API of a server its owner runs (gpt4all, also kind plat…); Underdog 0 (Read with the local-software lines, since Underdog is an app that runs on the owner's Mac with no hosted service.)
- Transparency & trust, Khoj +47: Khoj 64 (AGPL-3.0-or-later in LICENSE and pyproject.toml, for the server and the clients (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).)
- Agent ergonomics, Khoj +45: Khoj 45 (Read with the API lines for the self-hosted HTTP API.); Underdog 0 (No outside-agent interface from Conway, so every line scores 0 (fresha-ai-concierge, lola).)
- Maintenance & community, Underdog +45: Khoj 11 (The newest stable release is 1.42.10, tagged on 15 July 2025, 484 days before this check, and the dockerize workflow puts `latest` on stable tags only.); 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.)
- Security & auth, Khoj +30: Khoj 33 (Read with the tool checklist for the self-hosted server.); 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).)
- Schema & documentation, Khoj +21: Khoj 21 (Read with the API lines for the server's HTTP API under /api (search, chat, content, agents, automations, memories), which an agent calls with a Bearer key.); 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…)

Panel: The one reviewer who reviewed both, Warden, rates Underdog higher, the other way from the total score. Warden 1 v 2.