AiRecMark/AI Tools/Coding Agents/Sourcery (Sourcery)

Sourcery

verified v2026.9 Tier 2 Contender

AI code review and refactoring for GitHub, GitLab and IDEs

VENDOR: Sourcery LICENSE: Proprietary / SaaS SECURITY: Standard cloud security LAST BENCHMARK: Verified 2026-09-17
Launch Sourcery arrow_forward
Empirical Performance Audit

Macro Intelligence Index

83.4 /100 Beta Tier
Relative Velocity
#13 of 55
Archive record
5 recorded features
Source: sourcery.ai
Output quality
score.dims.quality
source: archive
Output Quality & Reliability (Weighted 25%) 84.0%
correctness and consistency of primary task output. AiRecMark rubric v2
Feature Depth & Integrations (Weighted 20%) 82.0%
breadth of integrations, APIs, and advanced capabilities. AiRecMark rubric v2
Onboarding & Usability (Weighted 15%) 85.0%
onboarding friction, UI clarity, and workflow ergonomics. AiRecMark rubric v2
Runtime Performance & Latency (Weighted 20%) 82.0%
latency, throughput, and stability under load. AiRecMark rubric v2
Price-to-Value Efficiency (Weighted 20%) 84.0%
capability delivered per pricing tier dollar. AiRecMark rubric v2
Low-Level Verification

Quantitative Technical Specification

ISO/IEC 25010 Ref
terminal Runtime & Core Shell
AI Code Review

Line-by-line reviews with summaries and diagrams of code changes.

Source: Sourcery · Verified 2026-09-17
hub Context Indexing Engine
Security Scanning

Repo security scans from 3 repos (free) to 200+ repos with daily scans (Team).

Source: Sourcery · Verified 2026-09-17
device_hub Protocol Specification
Custom Review Rules

Define custom review rules from the Pro tier up.

Source: Sourcery · Verified 2026-09-17
smart_toy Model Agility & Routing
Repo Analytics

Repository analytics included with the Team plan.

Source: Sourcery · Verified 2026-09-17
Market Positioning Matrix

Direct Competitor Radar & Alternatives

Open Full Matrix open_in_new
Tool & Version Score Primary Sweet Spot Entry Pricing Action
S
Sourcery (Current)
83.4 AI Code Review $12/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

“Sourcery stands out for full features free for public repos. AI code review and refactoring for GitHub, GitLab and IDEs anchors its proposition, and AiRecMark's five-dimension audit lands it at 83.4/100 — a pragmatic default for python & JS Teams Shipping via PR Review.”
— AiRecMark Senior Systems Architecture Committee
  • Full features free: for public repos
  • Per-seat pricing with: 20% annual discount
  • Works in IDE,: GitHub and GitLab
  • Best Fit: Python & JS Teams Shipping via PR Review
warning Institutional Trade-offs & Headwinds
  • ! Security scans capped: on lower tiers
  • ! Per-seat model adds: up for large orgs
  • ! :
  • ! 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 $12 user

Free for open source repos · Pro $12/seat/mo · Team $24/seat/mo · Enterprise custom

Verified 2026-09-17 · sourcery.ai
Enterprise Custom

Dedicated infrastructure, security review, and compliance support.

TCO MODEL NOTE: Official pricing: Free for open source repos · Pro $12/seat/mo · Team $24/seat/mo · Enterprise custom. Verified via sourcery.ai (2026-09-17); overages and enterprise terms bill per the official pricing page.
Archive Record

Recorded Metadata

ARCHIVE SNAPSHOT snapshot 2026-09-17
OFFICIAL SOURCE Source: sourcery.ai
PRICING CHECKED Snapshot 2026-09-17
SCORING MODEL v2-5dim
RECORDED FEATURES AiRecMark Editorial
Category Standing

Ecosystem Gravity

Category Rank #13 of 55
Best For Best for: Python & JS Teams Shipping via PR Review
Sources: Official docs, sourcery.ai, community signals N=5 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.