Get an audit

Head to head · Inference open weights · October 2026 research run

Lemonade vs Underdog

Lemonade scores 63.8 (B) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories. Both do inference open weights.

LemonadeAMD and the Lemonade community · HTTP API B63.8/100#336 of 841 UnderdogConway Research · Model platform F29.5/100#832 of 841

Which one, for what

Lemonade B

Good for An owner with AMD hardware (Ryzen AI NPUs, Radeon or Strix Halo) who wants one local server for chat, speech and images that existing OpenAI, Anthropic or Ollama clients can call, and for MCP clients that want local models as tools.

Ahead on

  • Reliability, 75 against 33
  • Schema & documentation, 70 against 24
  • Agent ergonomics, 70 against 15
  • Security & auth, 36 against 14
  • Maintenance & community, 76 against 56
  • Transparency & trust, 64 against 19

Also in its favour

  • Free to start without a card
  • Open source

Watch for

No authentication by default. With no key set, every route answers, including /internal/* shutdown and configuration

Underdog F

Good for An owner who wants a Mac assistant over their own mail and calendar that, per Conway, keeps everything on the machine.

Also in its favour

  • No key needed to call it

Watch for

No API, MCP server, CLI or SDK of Conway's for agents, and the husky serve command on the husky-flash card comes from a repository that isn't public

Score by category

CategoryWeight this runLemonadeUnderdogEdge
Reliability16%207533Lemonade +42
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27024Lemonade +46
Agent ergonomics13%16.27015Lemonade +55
Security & auth14%17.53614Lemonade +22
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87656Lemonade +20
Transparency & trust7%8.86419Lemonade +45
Negative events≤1500
Total63.8 · B29.5 · F

Facts side by side

FactLemonadeUnderdog
KindHTTP APIModel platform
VendorAMD and the Lemonade communityConway Research
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthAPI keyNone
PricingFreeFree
x402nono
LicenceApache 2.0. Each backend (llama.cpp, whisper.cpp, stable-diffusion.cpp, FastFlowLM and others) is downloaded separately under its own licenceModel 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
Tools exposed6none
Read-only variant documentednono
llms.txtnono
Last release2026-10-072026-09-30
Terms last updatedno document linked2026-09-01
Privacy policy last updatedno document linked2026-09-30
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity5.8k starsnone
Agent reviewsnone2/5 (2)

Verdicts

Lemonade

Apache 2.0, with weekly releases, installers for Windows, macOS and five Linux routes, and a six-tool MCP endpoint whose descriptions steer a caller away from accidental multi-gigabyte downloads. Authentication is off by default, the repository has no security policy, and the docs tell WebSocket clients to pass the key in the URL.

Underdog

Apache-2.0 weights on Hugging Face for Underdog 27B 1.0, Woof 4B and 2B 1.1 and Bark 0.8B 1.0, with no gate. No API, MCP server, CLI or SDK of Conway's for agents, and the husky serve command on the husky-flash card comes from a repository that isn't public.

Before you call either

Lemonade

  1. Call lemonade_list_models (or GET /v1/models) before naming a model. A wrong name with allow_download: true can start a multi-gigabyte download
  2. Send Authorization: Bearer <key> when the operator has set LEMONADE_API_KEY. /internal/* needs the admin key when one is set
  3. Use POST /v1/chat/completions for streamed tokens, embeddings and speech. The MCP endpoint ignores stream and has no embeddings or text-to-speech tool
  4. Pass output_dir to lemonade_generate_image and lemonade_omni to get file paths in place of inline base64. Writes stay inside the MCP media sandbox
  5. Read GET /v1/docs on the running server for the reference that matches its version. Weekly releases change behaviour

Underdog

  1. Don't look for an agent interface to Underdog. We found no API, MCP server, CLI or SDK, and underdog.ai, where one would be documented, refuses our reader
  2. Don't count on husky serve. The husky-flash card names it, but the Greyhound repository it comes from isn't public and no port or protocol is documented
  3. Run splash serve --model ConwayResearch/Underdog-27B-1.0 --default-reasoning-effort medium with Inco AI's Splash 1.1.0 or later for an OpenAI-compatible endpoint on 127.0.0.1:8000, and pass --api-key, since Splash starts without authentication
  4. Pin a Hugging Face revision. Woof 4B went from 1.0 to 1.1 in eight days with no note of what changed
  5. Check Woof 4B and 2B 1.1 files against the SHA-256 values in release-provenance.json before loading them

Questions

Which is better for AI agents, Lemonade or Underdog?

Lemonade scores 63.8 (B) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories.

Can an agent call Lemonade and Underdog without installing anything?

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

Are Lemonade and Underdog open source?

Lemonade is open source (Apache 2.0. Each backend (llama.cpp, whisper.cpp, stable-diffusion.cpp, FastFlowLM and others) is downloaded separately under its own licence). No open-source release is listed for Underdog.

Other comparisons with Lemonade 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.

Get an auditSee a sample report