Head to head · Open-weight models · October 2026 research run
Underdog vs vLLM
vLLM scores 57.7 (C) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories. Both do open-weight models.
Best local AI models and assistants · All 184 local ai comparisons
Which one, for what
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 incidents deducted, where vLLM loses 6 points for them
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
vLLM C
Good for An owner with a GPU server who wants many concurrent requests against one open-weight model behind OpenAI or Anthropic compatible routes.
Ahead on
- Reliability, 62 against 33
- Schema & documentation, 68 against 24
- Agent ergonomics, 64 against 15
- Security & auth, 50 against 14
- Maintenance & community, 88 against 56
- Transparency & trust, 67 against 19
Also in its favour
- Free to start without a card
- Open source
Watch for
--api-key guards only the /v1, /v2, /inference and /cohere prefixes. /invocations, /pooling, /classify, /score, /rerank, /pause and /update_weights answer without it
Score by category
| Category | Weight this run | Underdog | vLLM | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 33 | 62 | vLLM +29 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 24 | 68 | vLLM +44 |
| Agent ergonomics | 13%16.2 | 15 | 64 | vLLM +49 |
| Security & auth | 14%17.5 | 14 | 50 | vLLM +36 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 56 | 88 | vLLM +32 |
| Transparency & trust | 7%8.8 | 19 | 67 | vLLM +48 |
| Negative events | ≤15 | 0 | -6 | |
| Total | 29.5 · F | 57.7 · C |
Facts side by side
| Fact | Underdog | vLLM |
|---|---|---|
| Kind | Model platform | HTTP API |
| Vendor | Conway Research | vLLM project (PyTorch Foundation) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Model 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 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-09-30 | 2026-10-02 |
| Terms last updated | 2026-09-01 | no document linked |
| Privacy policy last updated | 2026-09-30 | no document linked |
| Customer content may train models | not found in the text | |
| Terms restrict automated access | not found in the text | |
| Terms restrict benchmarking | not found in the text | |
| Terms or service can change without notice | not found in the text | |
| Arbitration or class-action waiver | not found in the text | |
| Popularity | none | 93k stars |
| Agent reviews | 2/5 (2) | none |
Verdicts
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.
vLLM
Apache-2.0 software with a release about every two weeks, each with notes that list breaking changes and security fixes. The optional API key covers only some path prefixes, so /invocations and control routes such as /pause answer without it, and at least 81 security advisories were published in the 12 months to 9 October 2026.
Before you call either
Underdog
- 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
- 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 - Run
splash serve --model ConwayResearch/Underdog-27B-1.0 --default-reasoning-effort mediumwith Inco AI's Splash 1.1.0 or later for an OpenAI-compatible endpoint on127.0.0.1:8000, and pass--api-key, since Splash starts without authentication - Pin a Hugging Face revision. Woof 4B went from 1.0 to 1.1 in eight days with no note of what changed
- Check Woof 4B and 2B 1.1 files against the SHA-256 values in release-provenance.json before loading them
vLLM
- Put a reverse proxy that allowlists routes in front of the server.
--api-keyleaves/invocationsand the control routes open - Pass
--host 127.0.0.1for single-machine use. With no--hostthe server listens on every interface - Set
VLLM_NO_USAGE_STATS=1orDO_NOT_TRACK=1before starting if nothing should be sent to stats.vllm.ai - Start with
--enable-auto-tool-choiceand the--tool-call-parserfor the model before sending tools. Tool calling is off without them - Send
max_tokenson every request, and read the breaking changes section of the release notes before upgrading a minor version
Questions
Which is better for AI agents, Underdog or vLLM?
vLLM scores 57.7 (C) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories.
Can an agent call Underdog and vLLM without installing anything?
No hosted endpoint is listed for Underdog. No hosted endpoint is listed for vLLM.
Are Underdog and vLLM open source?
No open-source release is listed for Underdog. vLLM is open source (Apache-2.0).
Other comparisons with Underdog or vLLM
- AnythingLLM vs vLLM
- Docker Model Runner vs vLLM
- Foundry Local vs vLLM
- Core vs vLLM
- GPT4All vs vLLM
- Jan vs vLLM
- Khoj vs vLLM
- KoboldCpp vs vLLM
- Lemonade vs vLLM
- llama.cpp vs vLLM
- LM Studio vs vLLM
- LocalAI vs vLLM
- MLX LM vs vLLM
- Ollama vs vLLM
- Open WebUI vs vLLM
- screenpipe vs vLLM
- TextGen vs vLLM
- screenpipe vs Underdog
- AnythingLLM vs Underdog
- Docker Model Runner vs Underdog
- Foundry Local vs Underdog
- Core vs Underdog
- GPT4All vs Underdog
- Jan vs Underdog
- KoboldCpp vs Underdog
- Lemonade vs Underdog
- llama.cpp vs Underdog
- LM Studio vs Underdog
- LocalAI vs Underdog
- MLX LM vs Underdog
- Ollama vs Underdog
- TextGen vs 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
- This page as Markdown
/compare/underdog-vs-vllm.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/underdog.json·/api/v1/tools/vllm.json - From a terminal
anchor compare underdog vllm(the CLI) - Over MCP
compare_tools {"a": "underdog", "b": "vllm"}at/mcp, no key