Item detail
github.com

TabbyML/tabby

RepoRadar surfaced TabbyML/tabby — a code repository — into the AI coding assistants section, where it sits at Gold tier with a 'try now' verdict. It is written primarily in Rust. Its strongest signal is workflow potential, scored 9.2 out of 10.

Score8.1
Popularity100.0
Risklow
TierGold
Score breakdown
Usefulness8.3
Novelty6.4
Momentum7.0
Maturity8.9
Open-source/build8.4
Evidence7.2
Workflow potential9.2
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Tabby belongs on RepoRadar because it is one of the rare self-hosted AI coding assistants that genuinely ships a production-grade codebase rather than a thin wrapper around a vendor API. The 33,692-star community is the largest in the self-hosted Copilot category, the OpenAPI interface lets teams integrate Tabby into existing Cloud IDE / VSCode / JetBrains infrastructure without rewriting the

Who should use it

Teams that need a self-hosted AI coding assistant on consumer-grade GPUs without a managed-cloud dependency Engineers integrating AI code completion into existing Cloud IDE / VSCode / JetBrains infrastructure via Tabby's OpenAPI interface Organizations with strict data-residency requirements that cannot ship source code to a managed vendor service Practitioners evaluating open-source Copilot alternatives -- Tabby's 33k+ star community is the largest in the self-hosted category

Who should skip it

Skip TabbyML/tabby if the source repository or demo is inactive, unmaintained, or no longer matches the description shown here.

About this signal

TabbyML/tabby is tracked by RepoRadar as a code repository in the AI coding assistants section. First seen 2026-07-12; the source record was last checked on 2026-07-12. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. TabbyML/tabby leads on workflow potential (9.2) and maturity (8.9); its lowest signal is setup ease (6.4), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The TabbyML/tabby record combines a 8.1/10 composite score with separate popularity (100.0), risk (low), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.

Risk explanation

The `ee/` directory is excluded from the public OSS release -- some enterprise features (single sign-on, audit logging) require a Tabby Cloud subscription or on-prem enterprise license; The headline README 'What's New' entries are 6+ months old (12/12/2025 was the latest as of cycle 466) even though `pushed_at` is 2026-06-30 -- README maintenance lags the actual release cadence; readers should consult the GitHub Releases page for the current feature list; The Avian model provider feature was reverted on 2026-06-30 (PR #4510) -- the provider ecosystem is still consolidating and may shift again before stabilizing.

Evidence links
Closest alternatives / related signals
ai-coding-assistant self-hosted copilot-alternative openapi consumer-gpu apache-2.0 mature-incumbent
Verification record

What RepoRadar actually verified

Discovered

Automated discovery and source capture. Last checked 2026-08-13T20:20:15Z.

No editorial or hands-on review is claimed. This record remains at Discovered.

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

25 dated snapshots retained from 2026-07-12 through 2026-08-13; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.1 current · +0.0 net
Repository momentum5.8 current · -1.2 net
GitHub stars (observed)33,824 current · +132 net
GitHub stars33,824 exact observation
Versionnightly
Last release2023-09-08T01:39:25Z
Maintenancemaintained
Current risklow
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-138.15.833,824lowtry nowmaintained
2026-08-128.15.533,820lowtry nowmaintained
2026-08-118.15.833,820lowtry nowmaintained
2026-08-108.15.033,819lowtry nowmaintained
2026-08-098.15.033,821lowtry nowmaintained
2026-08-088.15.833,822lowtry nowmaintained
2026-08-078.15.833,812lowtry nowmaintained
2026-08-068.17.033,820lowtry nownot recorded
2026-08-058.17.033,820lowtry nownot recorded
2026-08-048.15.833,812lowtry nowmaintained
2026-08-038.15.833,812lowtry nowmaintained
2026-08-028.15.833,807lowtry nowmaintained

Why the record changed

stars changed

Stars changed: 33820 → 33824.

stars changed

Stars changed: 33819 → 33820.

stars changed

Stars changed: 33821 → 33819.

stars changed

Stars changed: 33822 → 33821.

stars changed

Stars changed: 33812 → 33822.

stars changed

Stars changed: 33820 → 33812.

stars changed

Reconstructed from adjacent retained daily snapshots; no upstream cause is inferred. Stars changed: 33812 → 33820.

stars changed

Stars changed: 33807 → 33812.

stars changed

Stars changed: 33805 → 33807.

stars changed

Source-observed stars changed: 33803 → 33805. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Reconstructed from adjacent retained daily snapshots; no upstream cause is inferred. Stars changed: 33801 → 33803.

stars changed

Reconstructed from adjacent retained daily snapshots; no upstream cause is inferred. Stars changed: 33793 → 33801.