Inference & serving
TabbyAPI
A Python, OpenAI-compatible local inference server built around ExLlamaV3. The maintainers describe it as a hobby project rather than a production service.
Overview
Research summary
TabbyAPI exposes locally running models through an API that follows OpenAI-compatible conventions. The reviewed implementation uses ExLlamaV3 as its inference backend and provides the serving layer that other applications or agent clients can connect to. Its role is to load and serve suitable models, not to define an autonomous coding workflow or provide model weights under its own license.
Deployment requires compatible hardware, model artifacts, and backend configuration; API compatibility should still be checked against the specific client features being used. The README explicitly describes the project as hobby-oriented and not intended for production workloads, which is an important operational limitation rather than an inference from commit activity. TabbyAPI is AGPL licensed.
The separately maintained ExLlamaV3 engine and individual model checkpoints have their own licensing and compatibility requirements.
Repository summary
- Stars
- 1,392
- Open issues
- Unavailable
- Last push
- 2026-09-13
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Version
- Unavailable
Recorded catalogue figures. View repository data and provenance →
Classification
Pricing & services
Paid services unknown
Whether the provider offers paid products or services has not been established.
Licence scope
Implementation
Recorded implementation details and interfaces for TabbyAPI.
Implementation details
Python FastAPI server using the ExLlamaV3 inference backend
- Languages
- Python
- Repository type
- source
Recorded interfaces and capabilities
Licence scope
Repository
Repository snapshots, release information and recorded maintenance signals.
Repository snapshot
- Stars
- 1,392
- Open issues
- Unavailable
- Last push
- 2026-09-13
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Archived
- Not recorded
Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).
Maintenance and provenance
- Catalogue snapshot
- 2026-10-06
- Stars source
- Recorded fallback
- Last push source
- Recorded fallback
Documentation
Recorded references and research provenance for this entry.
Recorded sources 6
- https://github.com/theroyallab/tabbyAPI Project page · Linked repository · Research reference
- https://github.com/theroyallab/tabbyAPI/blob/main/README.md Research reference
- https://github.com/theroyallab/tabbyAPI/blob/main/LICENSE Research reference
- https://github.com/stars/angelcervera/lists/ai Research reference
- https://raw.githubusercontent.com/theroyallab/tabbyAPI/HEAD/README.md Research reference
- https://discord.com/api/v10/invites/sYQxnuD7Fj?with_counts=false&with_expiration=true Research reference
Research metadata
- Research date
- 2026-09-16
- Catalogue snapshot
- 2026-10-06
Community & social 1 channels
Communities
- DiscordThe Royal Lab (shared community)Official
Link details for Discord — The Royal Lab (shared community)
- Access
- Public
- Last checked