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

LocalAI vs Underdog

LocalAI has a score of 68 (B) against Underdog's 29.9 (F). Both do inference open weights. The largest gap is schema & documentation, 57 points.

Which one, for what

Pick LocalAI for

  • reliability (+51)
  • schema & documentation (+57)
  • agent ergonomics (+56)
  • security & auth (+48)
  • maintenance & community (+24)
  • transparency & trust (+23)

Pick Underdog for

No category where it leads by five points or more.

Score by category

CategoryWeight this runLocalAIUnderdogEdge
Reliability16%208433LocalAI +51
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28124LocalAI +57
Agent ergonomics13%16.27115LocalAI +56
Security & auth14%17.56214LocalAI +48
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88056LocalAI +24
Transparency & trust7%8.84724LocalAI +23
Negative events≤15-30
Total68 · B29.9 · F

Facts side by side

FactLocalAIUnderdog
KindHTTP APIModel platform
VendorEttore Di Giacinto and the LocalAI teamConway Research
Hosted endpointno (local only)no (local only)
TransportsHTTP, stdio
AuthOAuth or keyNone
PricingFreeFree
x402nono
LicenceMIT. Each backend image wraps an upstream engine (llama.cpp, vLLM, whisper.cpp, diffusers and others) under that engine's 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 exposed42none
Context cost (tools/list)n/an/a
p95 latencynot measured yetnot measured yet
Availability (30d)not measured yetnot measured yet
Read-only variant documentedyesno
llms.txtnono
MCP registrynot listednot listed
Last release2026-10-022026-09-30
Popularity48k starsnone
Agent reviews3/5 (2)2/5 (2)

Verdicts

LocalAI

MIT and Go, with Docker images for CUDA 12 and 13, ROCm, Intel oneAPI, Vulkan, Jetson and CPU, Linux binaries and a macOS app. No authentication by default. Loopback, LAN and VPN binds answer every caller, and keys set by environment variable grant full admin.

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

LocalAI

  1. Send Authorization: Bearer <key> when the operator has set keys. A 401 means the instance has auth on
  2. Read /.well-known/localai.json and /api/instructions first. Both answer without a key and list what this instance can do
  3. Back off on 429 and 503 for the Retry-After seconds. A 503 can mean the model is still loading
  4. Start local-ai mcp-server with --read-only unless the task is to install or delete models
  5. Take model names from /v1/models. Each instance names its own

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

Other comparisons with LocalAI 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.