AiRecMark/AI Tools/Coding Agents/Kilo (Kilo (Anaconda))
RANK #10 IN CODING AGENTS

Kilo

verified v2026.9 Tier 2 Contender

Open-source VS Code coding agent (Kilo Code) with 500+ models

VENDOR: Kilo (Anaconda) • LICENSE: Proprietary / SaaS • SECURITY: Standard cloud security • LAST BENCHMARK: Verified 2026-09-15
Launch Kilo arrow_forward
Empirical Performance Audit

Macro Intelligence Index

84 /100 Beta Tier
Relative Velocity
#10 of 55
84/100 composite
Archive record
4 recorded features
Source: kilo.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%) 84.0%
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%) 82.0%
latency, throughput, and stability under load. AiRecMark rubric v2
Price-to-Value Efficiency (Weighted 20%) 86.0%
capability delivered per pricing tier dollar. AiRecMark rubric v2
Low-Level Verification

Quantitative Technical Specification

ISO/IEC 25010 Ref
terminal Runtime & Core Shell
Agent modes

Ask/Architect/Code/Debug plus custom modes.

Source: Kilo · Verified 2026-09-15
hub Context Indexing Engine
500+ models

BYOK Anthropic/OpenAI/Google or local Ollama.

Source: Kilo · Verified 2026-09-15
device_hub Protocol Specification
Cloud agents

Pay-per-second cloud runs and code review.

Source: Kilo · Verified 2026-09-15
smart_toy Model Agility & Routing
Kilo Pass

Credit subscriptions $19-199/mo with bonuses.

Source: Kilo · 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
K
Kilo (Current)
84 Agent modes $15/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

“Kilo stands out for mIT-licensed OSS across VS Code/JetBrains/CLI. Open-source VS Code coding agent (Kilo Code) with 500+ models anchors its proposition, and AiRecMark's five-dimension audit lands it at 84/100 — a pragmatic default for bYOK Open-Source Agent Users.”
— AiRecMark Senior Systems Architecture Committee
verified Verified Strategic Strengths
  • ✓ MIT-licensed OSS across: VS Code/JetBrains/CLI
  • ✓ Gateway bills at: exact provider cost — no markup
  • ✓ Kilo Auto Free: routes to free models without a card
  • ✓ Best Fit: BYOK Open-Source Agent Users
warning Institutional Trade-offs & Headwinds
  • ! 5% fee on: credit purchases
  • ! Cloud agents billed: per second ($0.33-1.20/hr)
  • ! :
  • ! 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 $15 user

Free & OSS (BYOK) · Teams $15/user/mo · Kilo Pass credits $19-199/mo · Enterprise custom

Verified 2026-09-15 · kilo.ai
Enterprise Custom

Dedicated infrastructure, security review, and compliance support.

SSO / SAML & audit controls
TCO MODEL NOTE: Official pricing: Free & OSS (BYOK) · Teams $15/user/mo · Kilo Pass credits $19-199/mo · Enterprise custom. Verified via kilo.ai (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: kilo.ai
PRICING CHECKED Snapshot 2026-09-15
SCORING MODEL v2-5dim
RECORDED FEATURES AiRecMark Editorial
Category Standing

Ecosystem Gravity

Category Rank #10 of 55
Best For Best for: BYOK Open-Source Agent Users
Sources: Official docs, kilo.ai, 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.