RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
← Home·/apps·Coding agent

Tabby

Fully offline

Self-hosted coding agent server with team SSO, audit logs, and dashboards. Enterprise-grade.

Editorial verdict: “Best self-hosted server for teams. SSO + audit logs make it the IT-friendly pick.”

Coding agent
Freemium
Apache-2.0
★ 4.4 / 5
GitHub ★ 23,000
↗ Homepage↗ GitHub↗ Docs

Compatibility at a glance

Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"

§ Runtimes supported
llama-cppopenai-compat
§ OS / platform
linuxmacoswindows
§ Hardware + model hint
Minimum VRAM
16 GB
Recommended starter model
DeepSeek Coder 6.7B Q4_K_M (FIM) + larger for chat
→ Build the rest of the stack with /stack-builder→ Pick a GPU for this app

What it is

Tabby is the coding agent server you pick when you’re not just running local models for yourself, but deploying them to a team of 20 or more. It bridges llama-cpp or any OpenAI-compatible runtime into a single server that handles autocomplete, chat, and model serving, with editor extensions for VS Code, JetBrains, Vim, and Emacs. The real differentiator is enterprise plumbing: SSO, per-user audit logs, and dashboards that let you prove exactly which completions were generated by whom. You’ll want at least 16 GB VRAM and a DeepSeek Coder 6.7B Q4_K_M for fill-in-the-middle, plus a larger model for chat. The tradeoff is that this is more moving parts than a solo Continue setup, and the dashboard features live behind a paid tier.

✓ Strengths

  • +Real team features — SSO, audit logs, dashboards
  • +All-in-one server — model + completion + chat + editor extensions
  • +Strong language coverage on autocomplete

△ Caveats

  • −More moving parts than Continue for solo use
  • −Some advanced features (dashboards) are paid-tier

About the Coding agent category

Editor-integrated or CLI agent that edits code via your model.

§ Other coding agent apps
Aider

Best terminal-native coding agent for local models. Qwen 2.5 Coder 32B is its sweet spot.

Twinny

Best minimal-surface Copilot-replacement that's been Ollama-native since day one.

Cline

Best IDE-integrated agent that fully respects 'all local' as a first-class option.

Continue

Best Copilot replacement that defaults to local. Configurable; pair with Qwen 2.5 Coder.

Where to go from here

Stack Builder →

Pre-filled with this app's recommended use case + budget tier. Get the full rig + runtime + model picks.

Back to /apps →

The full directory — filter by category, runtime, OS, privacy posture, or VRAM.

Runtimes (/tools) →

What this app talks to: Ollama, vLLM, llama.cpp, MLX, LM Studio. The upstream layer.

Community benchmarks →

Did this app work for you on a specific rig? Submit the benchmark — it powers the model + hardware pages.