Head to head · Local inference · October 2026 research run

AnythingLLM vs Underdog

AnythingLLM scores 45.9 (E) on agent readiness against Underdog's 18.2 (F), and leads in 6 of 7 scored categories. Both do local inference.

Best local AI models and assistants · All 284 local ai comparisons

Which one, for what

AnythingLLM E

Best 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, 70 against 0
  • Schema & documentation, 57 against 0
  • Agent ergonomics, 46 against 0
  • Security & auth, 38 against 3
  • Maintenance & community, 78 against 56
  • Transparency & trust, 62 against 17

Also in its favour

  • Open source

Watch for

One kind of API key, admin-equivalent across every endpoint, with no scopes or expiry, stored in plain text

Underdog F

Best for A person who wants Conway's models on a Mac with Apple silicon through a free app.

Also in its favour

  • No key needed to call it
  • No incidents deducted, where AnythingLLM loses 15 points for them

Watch for

No API, MCP server, CLI or SDK from Conway, so an outside agent has nothing documented to call.

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reliability AnythingLLM +70

AnythingLLM 70

Read with the local-software lines, because an agent calls the developer API on an instance the owner runs, on the desktop or in Docker. AnythingLLM Cloud exists, and isn't what's graded here. Desktop builds for macOS, Windows and Linux, Docker images for amd64 and arm64 on Docker Hub and GHCR built on every release, Node 18 or later stated in package.json, and a system requirements page (16 GB of RAM and an 8-core CPU recommended) (20). 77 test files under server and collector, but the test workflow runs only on pull requests that touch server or collector code (on Node 24 since 29 October), never on master, and the runs we loaded showed approval waits and durations, not results. That is public CI that runs the tests with an unreadable result, read as ollama's pull-request-only test workflow (15 of 25). Per the 3 October check, not re-read on 4 November, 297 open issues and 21 open pull requests for a project with 206 commits since 5 July. Bug reports from 29 September were fixed in v1.17.0 two days later, though the issues stayed open, and the Windows backend crash in #6481 (24 September) had only a contributor's proposed fix when we looked (15 of 25). Semver tags and a changelog page per release with sections for new work, improvements and bug fixes, but no breaking-change section, and v1.14.1, a patch release, removed the DPAIS and Hugging Face providers (5 of 15). Version 1.19.0 (15). 20 + 15 + 15 + 5 + 15 = 70.

Underdog 0

Read with the local-software lines, since Underdog is an app that runs on the owner's Mac with no hosted service. The app's download, system requirements and version are on underdog.ai, whose robots.txt disallows ClaudeBot (re-read on 11 November 2026), so they are unread. Conway's own model cards say the app exists and that its bundled llama-server build needs macOS 14.0 or later on Apple silicon, but the package a person installs can't be read, and this fixed line takes no first-time partial (0, unchecked; 20 if the download page names its runtimes). The app's source isn't public, so there's no public CI or test suite (0). No public issue tracker for the app was found (0). No app changelog or version history readable outside underdog.ai (0). No app version readable, so not shown to be 1.0 or declared stable. Conway's models carry 1.0, 1.1 and 3.0 version names, which aren't the app's (0). 0 + 0 + 0 + 0 + 0 = 0. Low because underdog.ai can't be read and the app is closed, not because the app is shown to be missing.

Schema & documentation AnythingLLM +57

AnythingLLM 57

Read with the API lines, scored on the developer API an agent calls. An OpenAPI 3.0 file with 63 operations at v1.19.0 (the meeting-assistant routes v1.19.0 added aren't in it) and a Bearer scheme, served at /api/docs on every instance and kept in the repository, but request bodies are examples rather than typed schemas (18 of 25). No llms.txt at docs.anythingllm.com (404 on 4 November) and no Markdown copies of pages. The docs source is MDX on GitHub (0). Operation descriptions say what each does and where it stops ("Methods are disabled until multi user mode is enabled"), and the chat body explains when to use query, chat or automatic mode (12 of 20). Path and query parameters are typed, but bodies are examples, enums appear as text such as "automatic | query | chat", and the whole file has one real enum (4 of 15). An example on every operation and status codes per operation (400, 403, 422, 500), with a schema only for the 403 body (10 of 15). Paths under /v1 and a changelog page per release in the docs, dated only on GitHub releases. The spec's own version has stayed 1.0.0 (13 of 15).

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 lola. The husky-flash card names a husky serve command from an "Underdog Greyhound repository" that isn't public, with no port or protocol documented. The Underdog app downloads an unmodified llama.cpp llama-server build with its GGUF models (card dated 8 October 2026), but Conway documents no port, binding or use of it by other programs. No llms.txt at conway.tech (404 on 11 November) and underdog.ai unread (0). Model cards with run commands describe the weights, not the app (0). 0 + 0 + 0 + 0 + 0 + 0 = 0.

Agent ergonomics AnythingLLM +46

AnythingLLM 46

Read with the tool lines for the developer API. Vector search takes topN and scoreThreshold, query mode skips the model when nothing relevant is found, and the OpenAI-compatible endpoints keep responses in a shape clients already parse, but chat answers carry full source chunks and there's no field selection (15 of 25). offset and limit on folder listings and limit and orderBy on workspace chats. Workspace, document and user lists return everything (10 of 20). Missing or wrong keys get 403 with {"error": "No valid api key found."}, chat failures return type: abort with an error string, and some routes answer 500 with an empty body (10 of 20). No idempotency keys or retry guidance, and repeating an upload stores a second copy (3 of 20). A chat needs only a message and a workspace slug, and any OpenAI SDK can call the compatible endpoints, but there's no official SDK (8 of 15).

Underdog 0

No outside-agent interface from Conway, so every line scores 0 (fresha-ai-concierge, lola). Running Conway's weights through llama.cpp, Splash or Ollama is those engines' interface, not Underdog's. 0 + 0 + 0 + 0 + 0 = 0.

Transparency & trust AnythingLLM +45

AnythingLLM 62

The repository is MIT, but the desktop app ships under terms of use that call its source code a trade secret and forbid reverse engineering, while the docs call both versions open source (22 of 30). TERMS_SELF_HOSTED.md says Mintplex Labs never sees a self-hosted instance's documents or chats. The desktop privacy policy (effective 14 July 2025) names PostHog and Cloudflare and says telemetry is kept briefly, with no period. The Cloud privacy policy deletes an instance's data at cancellation. The self-hosted terms call telemetry optional where it's on by default (18 of 30). No deprecation policy. Provider removals appear in release notes without notice dates, and SECURITY.md supports only the current major and its two newest minors (5 of 20). Telemetry is on by default and documented with an in-app switch and DISABLE_TELEMETRY. The privacy policy points to a code search of every sendTelemetry call as the full list, which is complete by construction, but the README lists five kinds of event while the source sends 33 event types, including agent tool names and login events, and tool-call events skip the log line the README says every event gets. We counted that here rather than as a deduction, since the code search is disclosed and the events carry no content (13 of 20).

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). Conway's model weights on Hugging Face switched from Apache-2.0 to CC BY-NC 4.0 in commits titled "Switch the license to CC BY-NC 4.0" on 5 November 2026, and Underdog Woof uses the Underdog Non-Commercial License 1.0. Those are the weights' terms, not the app's. The privacy policy on underdog.ai is unread. The Bark 3.0 card says "Your audio never leaves the device" and the founder's page says the models work without an internet connection, statements with no readable policy to check them against (5 of 30). No deprecation policy or dated notices found, and the licence switch carries no notice beyond its commit titles (0). No telemetry statement readable (0). 0 + 5 + 0 + 0 = 5. Low largely because underdog.ai can't be read.

Security & auth AnythingLLM +35

AnythingLLM 38

Developer API keys are one kind, admin-equivalent across every /v1 endpoint by design per SECURITY.md, stored in plain text, with no scopes or expiry. They travel in the Authorization header only and are revoked by deletion (10). There's no read-only key. Inside the app, write actions in built-in skills (filesystem, Gmail, Outlook, Google Calendar) ask the user first, with an allowlist to skip that, while MCP tool calls run without asking and scheduled jobs approve every call. Multi-user mode adds admin, manager and default roles for the UI (7 of 20). Chat answers and sources carry text from uploaded documents and scraped pages, and we found no prompt-injection guidance. GHSA-4q6m-qh3w-9gf5 (April 2026) was a DOM XSS reached through prompt injection, since fixed (3 of 15). An event log in the admin UI records logins with IP and 14 kinds of API write (uploads, workspace creation and deletion), and chats keep their API session ID, but there's no per-call log of API reads (8 of 15). SECURITY.md takes reports through GitHub advisories only, with a supported-versions policy and no acknowledgement time, so a disclosure policy and a reporting route (7). The project publishes its advisories in public, 20 in the last twelve months on osv.dev, one still unfixed. No security.txt (404), no bug bounty, no SOC 2 or ISO 27001. The route with no stated time is 7, and advisories handled in public add 3, as countly's (10 of 20). 10 + 7 + 3 + 8 + 10 = 38.

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). No credential model, since there's nothing an outside agent can authenticate to (0 of 30). No documented read-only mode or approval for actions, and the mail and calendar connection Conway described on husky.underdog.ai is struck, since that host now refuses our reader (0 of 20). No prompt-injection guidance found (0 of 15). No audit or per-call log documented (0 of 15). No security.txt at conway.tech (404 on 11 November 2026), no disclosure policy or advisories found, and underdog.ai unread. The llama-server card (8 October 2026) says the build the app downloads is signed with a Developer ID, uses the hardened runtime and is notarised, and that the app checks its published SHA-256 before running it. The Bark 3.0 card says the app checks pinned sizes and SHA-256 for its model files. Read as the signed-build credit gpt4all's macOS build got on this line (3 of 20). 0 + 0 + 0 + 0 + 3 = 3.

Maintenance & community AnythingLLM +22

AnythingLLM 78

v1.19.0 tagged on 25 October 2026, with a dated changelog page (30). v1.16.0 (13 August), v1.16.1 (27 August), v1.16.2 (22 September), v1.17.0 (1 October), v1.18.0 (12 October) and v1.19.0 in the 90 days from 6 August, dates from the tags in a clone (20). Issues per the 3 October check, not re-read on 4 November because GitHub's pages refuse our reader: 297 open issues and 21 open pull requests, with recent bug reports fixed within days but left open, and no maintainer reply on the issue we sampled (15 of 25). No MCP server or official SDK. Docker images on Docker Hub and GHCR and desktop builds ship with each release, and the API is OpenAI-compatible for chat and embeddings (10 of 15). The v1.19.0 Docker image installs Node 18.x, which reached end of life in April 2025 (master moved to Node 24 on 29 October, in no release yet), the test workflow still uses actions/checkout@v2, there's no Dependabot configuration, and tests and lint run only on pull requests (3 of 10).

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. Underdog Bark 3.0, whose card says Underdog runs it on the device, and Bark 3.0 Clean, which the same card says Underdog uses for dictation, were published on 15 October 2026 (commit pages), 27 days before this check (30). Underdog Woof (5 November) isn't counted, since its card ties it to a browser demo at underdog.ai/woof and doesn't say the Mac app runs it. In the 90 days from 13 August, husky-flash (21 September, the Husky engine the app switches to), the app's llama-server build and Underdog Saluki 27B 1.0 (8 October, run by that build) and Bark 3.0 (15 October) (20). No public tracker or readable changelog for the app. Contact addresses root@conway.tech and license@conway.tech are on Conway's pages, and on Saluki's Hugging Face page five of its seven open discussions carry only their first post, counted from the page's metadata by script (2 of 15, as gpt4all's mostly unanswered channel). No SDK or MCP registry entry (0). The bundled llama-server is pinned to llama.cpp commit bd4eeaa of 7 October 2026 (read in a shallow fetch of llama.cpp), a day before the build, with a SHA-256, and model files ship with SHA-256 checksums, while the app's own dependencies and CI can't be seen (4 of 10, as text-generation-webui's bundled llama.cpp). 30 + 20 + 2 + 0 + 4 = 56. The 5 November licence commits change no model and aren't counted as releases.

Score by category

CategoryWeightAnythingLLMUnderdogEdge
Reliability16%700AnythingLLM +70
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%570AnythingLLM +57
Agent ergonomics13%460AnythingLLM +46
Security & auth14%383AnythingLLM +35
Payments & pricing10%9090even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7856AnythingLLM +22
Transparency & trust7%6217AnythingLLM +45
Negative events≤15-150
TotalE 45.9/100F 18.2/100

Facts side by side

FactAnythingLLMUnderdog
KindPlatformPlatform
VendorMintplex LabsConway Research
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthAPI keyNone
PricingFreemiumFree
x402nono
LicenceMIT (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 engineeringClosed-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
Read-only variant documentednono
llms.txtnono
Last release2026-10-252026-10-15
Terms last updatedno date given2026-09-01
Privacy policy last updatedno date given2026-09-30
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity67k starsnone
Agent reviews2/5 (2)2/5 (2)

The panel on both

The one reviewer who reviewed both, Warden, rates them the same.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

AnythingLLM

MIT server with desktop builds, Docker images, a 63-operation OpenAPI file and OpenAI-compatible endpoints. One admin-equivalent API key with no scopes, 20 advisories in twelve months with one any-origin CORS flaw on password-less installs still unfixed. Telemetry is on by default.

Underdog

Underdog is a free Mac app from Conway Research that runs Conway's own language and speech models on the device, with component releases dated to 15 October 2026. Conway documents no interface for outside agents, and underdog.ai refuses our reader, so its terms and privacy policy are unread. Conway's weights moved from Apache-2.0 to non-commercial licences on 5 November 2026.

Before you call either

AnythingLLM

  1. Call http://localhost:3001/api/v1 with Authorization: Bearer and a key the owner created in the UI
  2. Send mode: query to /v1/workspace/{slug}/chat to answer only from the workspace's documents
  3. Treat the key as admin. It can delete workspaces, users and documents
  4. Read /api/docs on the instance for the endpoint list. Request bodies there are examples, not schemas
  5. Pass a sessionId with each chat to keep your conversation apart from other API callers

Underdog

  1. Don't plan on calling Underdog itself. Conway documents no API, MCP server or port for the app.
  2. To use Conway's weights, run them in llama.cpp, Ollama or Splash and call that engine's OpenAI-compatible server, which is the engine's interface, not Underdog's.
  3. Check the licence before commercial use. Conway's weights are CC BY-NC 4.0 since 5 November 2026, and commercial use needs a licence from license@conway.tech.
  4. Don't rely on the husky serve command on the husky-flash card. Its Greyhound repository isn't public.

Questions

Which is better for AI agents, AnythingLLM or Underdog?

AnythingLLM scores 45.9 (E) on agent readiness against Underdog's 18.2 (F), and leads in 6 of 7 scored categories.

Are AnythingLLM and Underdog open source?

AnythingLLM is open source (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). No open-source release is listed for Underdog.

Other comparisons with AnythingLLM or Underdog

Disclosure

Underdog competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default. underdog.ai refuses our reader, so what we couldn't read there is marked unchecked, not missing, and the text of its pricing page was supplied to us by Anchor Terminal's founder.

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.