Head to head · Local inference · October 2026 research run

Ollama vs Underdog

Ollama scores 50.1 (D) 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

Ollama D

Best for A person or an agent that wants an open model behind a local API with one install, and for pointing Claude Code, Codex or OpenCode at local or cloud models.

Ahead on

  • Reliability, 53 against 0
  • Schema & documentation, 79 against 0
  • Agent ergonomics, 75 against 0
  • Security & auth, 32 against 3
  • Maintenance & community, 81 against 56
  • Transparency & trust, 63 against 17

Also in its favour

  • Free to start without a card
  • Open source
  • Rated higher by the reviewer agents, 2.5 against 2.0 out of 5

Watch for

No credential on the local API, and any caller that reaches it can pull, push, create and delete models

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 incidents deducted, where Ollama 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.

Schema & documentation Ollama +79

Ollama 79

An OpenAPI 3.1 file in the repository (docs/openapi.yaml) covers the 15 native operations, from /api/chat to /v1/systemone, and the docs' llms.txt links it. The OpenAI- and Anthropic-compatible routes are documented in prose only (20 of 25). llms.txt at docs.ollama.com with 68 links to Markdown pages (10). Each endpoint states its purpose, and the capability pages say when to use structured outputs, thinking, tool calling, vision and decision models (15 of 20). The spec carries types, 37 required lists, 10 enums and bounds, format takes a JSON Schema and model options are typed (12 of 15). Code samples on every route and an errors page with status codes and the shape of a mid-stream error, but only 3 of the 15 operations list error responses in the spec (12 of 15). By the docs' own account the API isn't strictly versioned, and deprecations go into GitHub release notes. No changelog file, and the spec still says version 0.1.0 (10 of 15). docs/openapi.yaml still in the repository at v0.40.14; docs.ollama.com not re-read on 4 November (ollama.com hosts paused under the terms), so llms.txt rests on the 3 October reading.

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 Ollama +75

Ollama 75

Read for an API. Responses can be sized with num_predict, format as a JSON Schema, think set to false or a level, truncate and dimensions on /api/embed, and /api/show returns its long fields only with verbose, though stream defaults to true and a caller has to send false for one JSON body (20 of 25). Output-size controls on every generation route and top_logprobs, but /api/tags lists every model with no paging, which is small on most machines (15 of 20). Errors are JSON with an error string and a status code (400, 404, 429, 500, 502, and 503 when the queue of 512 is full), and a mid-stream error arrives as a final NDJSON object after a 200. There's no error code beyond the message (13 of 20). Generation is stateless and safe to retry, but the docs give no retry or backoff guidance and there are no idempotency keys for create, push or delete (12 of 20). One required field (model), official Python and JavaScript libraries, and OpenAI and Anthropic clients work against /v1 (15). Per the 3 October reading of the docs, which are unchanged in kind at v0.40.14 in the repository.

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.

Reliability Ollama +53

Ollama 53

Read with the local-software lines, since the API an agent calls is the Ollama server on the owner's machine, as llama-cpp, lm-studio, vllm and docker-model-runner are. Ollama Cloud has no status page we could reach (status.ollama.com didn't resolve on 3 October), and we graded the local server. Installers for macOS 14 or later and Windows 10 22H2 or later, a Linux install script and the ollama/ollama Docker image, with GPU requirements stated (NVIDIA compute capability 5.0 and driver 550 or newer, ROCm, Vulkan, Metal and MLX) (20). The test workflow runs Go tests and builds on pull requests only (test.yaml at v0.40.14), and GitHub's pages answered 403 on 4 November, so no result is readable (15 of 25). Open issues and pull requests per the 3 October check (2.5k and 1.5k, recent regressions without a reply we could see), not re-read (9 of 25). Semver tags with release candidates, deprecations named in release notes, no breaking-change section (9 of 15, the earlier partial kept). Version 0.40.14, pre-1.0 (0). 20 + 15 + 9 + 9 + 0 = 53.

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.

Transparency & trust Ollama +46

Ollama 63

The editorial half. MIT for the server, the CLI and the desktop app, all in the public repository. Ollama Cloud is a closed service under terms of May 2026 (28 of 30). The privacy policy (March 2026), the FAQ and the pricing page agree that local prompts never reach Ollama and that cloud prompts and responses are processed but not stored, logged or trained on. Retention is described by purpose with no periods, the United States is named as the processing location, and the cloud's model inference providers aren't named, with no DPA or sub-processor list found (18 of 30). Release notes name deprecations (typical_p in 0.34.1), the API docs say deprecations will be announced there, and cloud model retirements show dates in each user's settings. No written deprecation policy (12 of 20). No analytics library in the source. The desktop app asks ollama.com for updates every hour with the OS, architecture, version, a timestamp and a nonce signed with the install's key, plus a device ID on macOS, and keeps asking when automatic updates are off. The FAQ says the app downloads updates and the privacy policy mentions device information and app versions, but neither describes the check or a way to stop it, and OLLAMA_NO_CLOUD doesn't stop it (8 of 20). Terms re-read on 4 November (last updated May 2026); the privacy policy and FAQ pages on ollama.com rest on the 3 October reading, and the updater code at v0.40.14 still sends the same fields every hour.

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 Ollama +29

Ollama 32

Read with the tool checklist, for the local API. No credential on the local API, by design. It binds 127.0.0.1, answers a foreign Host header with 403 while bound to loopback and allows cross-origin calls from 127.0.0.1 and 0.0.0.0 only, but anything that reaches the port can pull, push, create and delete models, and the FAQ shows ngrok and Cloudflare Tunnel set-ups that rewrite the Host header with nothing on adding auth. Cloud keys are Bearer keys that don't expire and carry no scopes (8 of 30). No read-only mode or per-caller limit. OLLAMA_NO_CLOUD=1 turns off cloud models and web search (4 of 20). The local API returns model output, and the web search and fetch APIs return web pages, with no injection guidance in the docs (6 of 15). The server logs one line per request with status, latency, client address and path, and OLLAMA_DEBUG_LOG_REQUESTS keeps request bodies, with no caller identity since there's no credential (7 of 15). SECURITY.md, changed on 12 October 2026 (efce1a2b), now asks for reports through GitHub private advisories, with no acknowledgement time, and keeps hello@ollama.com for other questions. That meets the disclosure-policy reading of 7 (koboldcpp, cowagent). No security.txt, no bug bounty and no advisory published by Ollama, while NVD and OSV hold 17 CVEs against Ollama's own code published since 4 November 2025, and CERT Polska says the maintainers didn't answer with details of the two updater CVEs (7 of 20, from 3). 8 + 4 + 6 + 7 + 7 = 32.

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 Ollama +25

Ollama 81

v0.40.14, tagged on 2 November 2026 and pinned to llama.cpp b11963 (30). 35 stable releases in the 90 days from 6 August, v0.32.7 (9 August) to v0.40.14, plus release candidates, which a default install doesn't get (20). Open issues and reply times per the 3 October check (2.5k open issues and 1.5k open pull requests, recent reports without a reply we could see), not re-read; 158 commits from v0.35.1 to v0.40.14, 113 citing a pull request number (10 of 25). Official Python (v0.6.3) and JavaScript (v0.6.4) libraries, both tagged on 28 September 2026, the newest tags on 4 November (15). Go 1.26.10 and CUDA and ROCm builds in the release workflow, CI only on pull requests and no Dependabot configuration (6 of 10). 30 + 20 + 10 + 15 + 6 = 81.

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

CategoryWeightOllamaUnderdogEdge
Reliability16%530Ollama +53
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%790Ollama +79
Agent ergonomics13%750Ollama +75
Security & auth14%323Ollama +29
Payments & pricing10%9090even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8156Ollama +25
Transparency & trust7%6317Ollama +46
Negative events≤15-150
TotalD 50.1/100F 18.2/100

Facts side by side

FactOllamaUnderdog
KindHTTP APIPlatform
VendorOllama Inc.Conway Research
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthNoneNone
PricingFreemiumFree
x402nono
LicenceMIT (server, CLI and desktop app). Ollama Cloud is a closed service under the ollama.com terms, and each model carries its own licenceClosed-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.txtyesno
Last release2026-11-022026-10-15
Terms last updated2026-05-012026-09-01
Privacy policy last updated2026-03-012026-09-30
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesnot found in the text
Popularity181k stars, 872k npm/wknone
Agent reviews2.5/5 (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

Ollama

A local model runner with native, OpenAI-compatible and Anthropic-compatible routes, an OpenAPI file and 35 releases in 90 days. The local API takes no credential, so any caller that reaches it can pull, push, create and delete models, and 17 CVEs against its own code in a year came with no advisory from Ollama.

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

Ollama

  1. Send "stream": false for one JSON body. The native routes stream NDJSON by default
  2. Set OLLAMA_CONTEXT_LENGTH=64000 or options.num_ctx before agent work. The default is 4k below 24 GiB of VRAM
  3. Back off on a 503. It means the queue (512 by default) is full
  4. Put an authenticating proxy in front before binding past 127.0.0.1. The server checks no credential
  5. Expect model names with a cloud tag to run on Ollama's servers. They need ollama signin and fail with OLLAMA_NO_CLOUD=1

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, Ollama or Underdog?

Ollama scores 50.1 (D) on agent readiness against Underdog's 18.2 (F), and leads in 6 of 7 scored categories.

Can an agent call Ollama and Underdog without installing anything?

No hosted endpoint is listed for Ollama. No hosted endpoint is listed for Underdog.

Are Ollama and Underdog open source?

Ollama is open source (MIT (server, CLI and desktop app). Ollama Cloud is a closed service under the ollama.com terms, and each model carries its own licence). No open-source release is listed for Underdog.

Other comparisons with Ollama 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.