An agentic coding tool that works in your terminal.
Tabby
Self-hosted open-source AI coding assistant.
SharkScore
#70 in Coding
Why it scores 47.6
Tabby has a SharkScore of 47.6/100, ranked #70 of 102 in Coding (updated 2026-11-18).
Each part compares Tabby with other listings in Coding. Evidence covers 87% of the score's weight.
- Adoption
- 47 · 30%
- User reviews
- no data · 25%
- Maintenance
- 23 · 20%
- Trust & transparency
- 80 · 15%
- Momentum
- no data · 10%
Paying never changes this score. How ranking works · method v2026-11-18.2
RankShark review of Tabby
Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review
We were not paid for this review.
As of 2026-11-18, Tabby is a free, open-source, self-hosted AI coding assistant; its docs list Docker, Homebrew and Hugging Face Space deployment. [E2]
Tabby is described in its documentation as an open-source, self-hosted AI coding assistant for code completion. The current homepage instead describes finding failure patterns in AI agents and turning them into evaluation cases and graders. [E1, E2]
Key features
- Self-hosted code completion. The vendor describes Tabby as a way for teams to set up their own LLM-powered code-completion server. · docs
- Model compatibility. The vendor says Tabby is compatible with coding models including CodeLlama, StarCoder and CodeGen, and that users can combine preferred models. · docs
- IDE/editor extensions. The vendor says Tabby provides IDE/editor extensions and describes streaming, cancellation and adaptive caching for completions. · docs
- Model serving. The vendor says Tabby parses relevant code into Tree Sitter tags to provide prompts. · docs
- Agent evaluation. The vendor’s homepage says it identifies failure patterns across agent runs and turns them into evaluation cases and graders. · home page
Pros
Cons
- The supplied pages describe different product scopes: the docs focus on coding assistance, while the homepage focuses on evaluating AI agents. · home page, docs
- No public prices found on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.
- No release in the last 180 days (latest: v0.32.0 on 2026-01-25).
Pricing
No public prices found on the pages we checked.
Checked 18 Nov 2026
- Free plan
- The docs describe Tabby as free and open-source; usage limits are not stated. · docs
- Free trial
- Not stated (checked 18 Nov 2026)
- Trains on customer data
- Not stated (checked 18 Nov 2026)
- Data retention
- Not stated (checked 18 Nov 2026)
- Data regions
- Not stated (checked 18 Nov 2026)
- Data processing agreement
- Not stated (checked 18 Nov 2026)
- AI models used
- The docs name CodeLlama, StarCoder and CodeGen as compatible coding LLMs. · docs
- API
- The docs link to API references and API documentation. · docs
- SDKs
- Not stated (checked 18 Nov 2026)
- Webhooks
- Not stated (checked 18 Nov 2026)
- Platforms
- The docs list Docker, Homebrew and Hugging Face Space among installation options. · docs
- Security claims
- No security certification stated (checked 18 Nov 2026)
What we measured
- GitHub stars · now
- 33,933
- Latest release · now
- v0.32.0 on 2026-01-25
- Tranco traffic rank · list of the day
- #438,845
How we tested · sources
- Hourly uptime and response-time checks of the product's URL.
- Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
- We did not sign up, pay, or use the product as a customer.
- home page: https://www.tabbyml.com/ · fetched 18 Nov 2026
- docs: https://tabby.tabbyml.com/docs/welcome/ · fetched 18 Nov 2026
Something wrong? Report an error with a public link that shows it; corrections re-run the review.
Top alternatives to Tabby
See all- 74.5AgentPaid · from $17/mo
- 73.7
Open-source AI coding agent for the terminal.
AgentOpen source · from $10/mo - 71.7
Google's open-source AI agent for the terminal.
AgentOpen source - 71.3
Open-source platform for AI software development agents.
AgentOpen source · from $500/mo