AiRecMark/AI Tools/Coding Agents/Tabby (TabbyML)
RANK #17 IN CODING AGENTS

Tabby

verified v2026.9 Tier 2 Contender

Self-hosted, open-source code completion with a cloud option

VENDOR: TabbyML • LICENSE: Proprietary / SaaS • SECURITY: Standard cloud security • LAST BENCHMARK: Verified 2026-09-15
Launch Tabby arrow_forward
Empirical Performance Audit

Macro Intelligence Index

82.6 /100 Beta Tier
Relative Velocity
#17 of 55
82.6/100 composite
Archive record
4 recorded features
Source: www.tabbyml.com
Output quality
score.dims.quality
source: archive
Output Quality & Reliability (Weighted 25%) 80.0%
correctness and consistency of primary task output. AiRecMark rubric v2
Feature Depth & Integrations (Weighted 20%) 76.0%
breadth of integrations, APIs, and advanced capabilities. AiRecMark rubric v2
Onboarding & Usability (Weighted 15%) 84.0%
onboarding friction, UI clarity, and workflow ergonomics. AiRecMark rubric v2
Runtime Performance & Latency (Weighted 20%) 84.0%
latency, throughput, and stability under load. AiRecMark rubric v2
Price-to-Value Efficiency (Weighted 20%) 90.0%
capability delivered per pricing tier dollar. AiRecMark rubric v2
Low-Level Verification

Quantitative Technical Specification

ISO/IEC 25010 Ref
terminal Runtime & Core Shell
Self-hosted completion

OSS server with IDE plugins.

Source: Tabby · Verified 2026-09-15
hub Context Indexing Engine
Answer engine

Context-aware Q&A over your repos.

Source: Tabby · Verified 2026-09-15
device_hub Protocol Specification
Data connectors

Index private docs and contexts.

Source: Tabby · Verified 2026-09-15
smart_toy Model Agility & Routing
Pochi cloud

Usage-based cloud agent product.

Source: Tabby · Verified 2026-09-15
Market Positioning Matrix

Direct Competitor Radar & Alternatives

Open Full Matrix open_in_new
Tool & Version Score Primary Sweet Spot Entry Pricing Action
T
Tabby (Current)
82.6 Self-hosted completion $19/user Selected
CU
Cursor
94.2 Forked VS Code Agent $20/user/mo Compare vs
WI
Windsurf
91.8 Realtime Collaborative IDE Free / $15 Pro Compare vs
GI
GitHub Copilot
88.1 Enterprise Compliance $10/mo Compare vs
CL
Claude Code
86.1 Terminal & CI/CD Pipelines $17/mo Compare vs
Institutional Synthesis

Analyst Consensus Verdict

“Tabby stands out for free self-hosted community edition. Self-hosted, open-source code completion with a cloud option anchors its proposition, and AiRecMark's five-dimension audit lands it at 82.6/100 — a pragmatic default for self-Hosting & Privacy Teams.”
— AiRecMark Senior Systems Architecture Committee
verified Verified Strategic Strengths
  • ✓ Free self-hosted community: edition
  • ✓ Your code never: leaves your infra
  • ✓ Answer engine +: inline chat beyond completion
  • ✓ Best Fit: Self-Hosting & Privacy Teams
warning Institutional Trade-offs & Headwinds
  • ! Requires GPU ops: for good latency
  • ! Cloud annual card: prices look templated — verify before purchase
  • ! :
  • ! Scope: Editorial assessment based on public information; hands-on retest pending.
Total Cost of Ownership

Commercial Tiers

Transparent
Free $0 forever

Entry tier for evaluation and light individual use.

Entry evaluation tier
Most Deployed
Pro $19 user

Community free self-hosted (≤5 users) · Team $19/seat/mo · Cloud pay-per-token ($20 free credits/mo)

Verified 2026-09-15 · tabbyml.com
Enterprise Custom

Dedicated infrastructure, security review, and compliance support.

SSO / SAML & audit controls
TCO MODEL NOTE: Official pricing: Community free self-hosted (≤5 users) · Team $19/seat/mo · Cloud pay-per-token ($20 free credits/mo). Verified via tabbyml.com (2026-09-15); overages and enterprise terms bill per the official pricing page.
Archive Record

Recorded Metadata

ARCHIVE SNAPSHOT snapshot 2026-09-15
OFFICIAL SOURCE Source: www.tabbyml.com
PRICING CHECKED Snapshot 2026-09-15
SCORING MODEL v2-5dim
RECORDED FEATURES AiRecMark Editorial
Category Standing

Ecosystem Gravity

Category Rank #17 of 55
Best For Best for: Self-Hosting & Privacy Teams
Sources: Official docs, tabbyml.com, community signals N=4 recorded attributes
shield_with_heart AIRECMARK EMPIRICAL PROTOCOL v2.4 • Independent, un-sponsored deterministic evaluation clusters.
All benchmarks executed in sandboxed hypervisors with standardized token latency meters.