The decision
Should you choose Kerlig?
Kerlig earns a shortlist for Mac power users who value native shortcuts and provider choice more than a managed subscription. It is a weaker fit for mixed-device teams or people who do not want to manage API keys, local models, permissions, and variable token costs.
Best for
Mac users writing across many applications; Bring-your-own-model buyers.
Choose something else if
Windows, Linux, or mobile-first workflows; Teams wanting fully managed AI billing
Evidence
Editorial research pending · 8.0/10
Pricing checked
From $49 · 2026-08-26
Free access is available, with limits.
No permanent free plan was documented; Kerlig offers a downloadable trial and a 14-day money-back guarantee. Verify the current trial boundary.
In this guide
Short answer
Kerlig is worth considering for Mac users who want AI rewriting, drafting, translation, and document chat without moving text through browser tabs. Its one-time license and bring-your-own-model design can be economical. The trade-off is ownership: you manage model keys, token costs, permissions, model selection, and the privacy policy of every provider you connect.
Best for
- Mac users writing across many applications
- Bring-your-own-model buyers
- People preferring a one-time desktop license
Look elsewhere if
- Windows, Linux, or mobile-first workflows
- Teams wanting fully managed AI billing
- Sensitive use without provider review
What Kerlig verifiably does
Kerlig documents global shortcuts, selected-text actions in any Mac application, proofreading, replies, custom presets, tone-of-voice settings, document and webpage chat, vision, deep research, citations, more than 350 hosted models, and local models through Apple Foundation Models, Ollama, and LM Studio. Team packaging adds CLI deployment and support.
Important limitations
Kerlig is macOS-only and requires accessibility-style integration with the desktop workflow. Selected text and attachments may contain sensitive information. Kerlig says messages go directly to chosen AI providers and history is encrypted on the Mac, but each external provider has its own retention and training terms. License price excludes hosted-model usage, and vendor claims about model count or lifetime updates can change.
Pricing snapshot
Kerlig displays Basic at $49 once for one Mac, Pro at $79 once for two Macs, and Team at $297 once for ten seats. The displayed deal language and included update period can change. Hosted model tokens are separate; local Apple Foundation Models, Ollama, or LM Studio can avoid provider token charges. Reviewed August 26, 2026.
A fair buyer test
Use a trial on 50 real but non-sensitive writing tasks: email replies, proofreading, Jira tickets, translations, summaries, and document questions. Compare edit acceptance, meaning changes, shortcut friction, token spend, local-model quality, permission scope, history deletion, and total time against your current assistant.
Final verdict
Kerlig earns a shortlist for Mac power users who value native shortcuts and provider choice more than a managed subscription. It is a weaker fit for mixed-device teams or people who do not want to manage API keys, local models, permissions, and variable token costs.
This is a research-based assessment, not a claim of hands-on product testing. Product, pricing, privacy, security, and usage claims were checked against the first-party sources below on August 26, 2026. Verify current terms and run the proposed test with approved data before adoption.
Transparency
How this guide was checked
Editorial accountability
Who checked this guide
- Evaluation type
- Hands-on evaluation
- Last materially checked
- Evidence
- 4 listed sources
Hands-on testing is identified explicitly. Research-based coverage uses cited product documentation and other named sources; it does not imply every paid plan was used. Read the full methodology.
Editorial freshness
Pricing and material product claims were checked August 26, 2026.
Review evidence
What this guidance is based on
- Editorial basis
- Current first-party product, pricing, help, security, privacy, and terms documentation
- Review type
- Research-based product assessment
- Material review date
- August 26, 2026
- Buyer test
- Controlled workflow test with output, correction, cost, permission, and ownership checks
Important limits
- • DiscoverAI did not complete the proposed long-term paid deployment for this research-based review.
- • Features, prices, limits, security controls, privacy terms, and usage rights can change; verify the linked first-party pages before purchase.
Standardized benchmark coverage
How this review maps to the research benchmark
Citation accuracy
Not applicableThe reviewed workflow does not produce source-grounded research answers, so a citation score would be misleading.
Read protocol v2026.10-v1 →Thematic analysis
Not applicableThe reviewed workflow is not qualitative evidence analysis, so a thematic-analysis score would be misleading.
Read protocol v2026.10-v1 →Eligibility is not a product score. DiscoverAI publishes results only after output collection, blinded adjudication, reproducibility checks, and severe-error review.
Open the optional evaluation worksheet
Reusable trial worksheet
Test Kerlig before you commit
Turn this review’s buyer test into evidence. Your entries autosave only in this browser and are never added to shared shortlist links.
Confirm the tool meets every must-have workflow and stakeholder requirement.
Review starting point: Mac users writing across many applications; Bring-your-own-model buyers; People preferring a one-time desktop license
Run the same representative work you would use in production; do not score a polished demo.
Review starting point: Use a trial on 50 real but non-sensitive writing tasks: email replies, proofreading, Jira tickets, translations, summaries, and document questions. Compare edit acceptance, meaning changes, shortcut friction, token spend, local-model quality, permission scope, history deletion, and total time against your current assistant.
Calculate the effective cost per accepted result, including usage, review, corrections, and required add-ons.
Review starting point: Kerlig displays Basic at $49 once for one Mac, Pro at $79 once for two Macs, and Team at $297 once for ten seats. The displayed deal language and included update period can change. Hosted model tokens are separate; local Apple Foundation Models, Ollama, or LM Studio can avoid provider token charges. Reviewed August 26, 2026.
Define an acceptance threshold, test known answers and edge cases, and record every correction.
Review starting point: Editorial quality signals: features 4.1/5; AI quality 4.0/5. Validate these signals in your own work.
Verify what data enters the product, who can access it, how long it is retained, and whether it trains models.
Review starting point: Use approved low-risk data first. Check roles, consent, deletion, subprocessors, model-training settings, and the contract—not only the marketing page.
Test the real handoffs, permissions, failure states, and export path your team depends on.
Review starting point: OpenAI, Anthropic, Google, OpenRouter, Ollama, LM Studio
Record training, governance, reliability, accessibility, ownership, and change-management risks before rollout.
Review starting point: Mac-only; Model usage costs are separate; Privacy depends partly on selected providers
Loading saved worksheet… · private to this device or your optional account
Community evidence
How verified users put Kerlig to work
Structured, editor-moderated experience—not star ratings. This complements our independent review and never changes its score.
No approved community evidence yet. Be the first verified user to contribute.
Sources and verification
Product details and claims were checked against the following primary sources.
Frequently asked questions
How much does Kerlig cost?
Kerlig currently displays one-time prices of $49 for Basic, $79 for Pro, and $297 for a ten-seat Team license. Model tokens may cost extra.
Does Kerlig require an AI subscription?
Kerlig supports your own provider API keys and local models. Hosted provider usage is billed separately under those providers' terms.
Does Kerlig work on Windows?
No. Kerlig is presented as a native macOS application supporting Apple Silicon and Intel Macs on macOS 12 or later.
Does Kerlig send text to its own servers?
Kerlig says messages are sent directly to selected AI providers and stored encrypted on the Mac. Verify app permissions and each provider's current privacy terms.
Recommended tool
Use Kerlig if this workflow fits your team
Native selection-and-shortcut workflow
Tools mentioned in this article
Kerlig
A Mac-native, bring-your-own-model writing assistant available in any app
Kerlig offers selection-based writing, document chat, local models, and hundreds of model choices for a one-time license, but buyers must budget separate tokens and understand macOS permissions and provider data paths.
TypingMind
A bring-your-own-key AI workspace for chatting with multiple model providers
TypingMind unifies multiple AI APIs in a local-first interface, but API spend, browser storage, optional cloud services, and provider policies determine its real value and privacy.
Grammarly
Writing assistance for proofreading, clarity, tone, rewriting, and team communication
Grammarly supports proofreading, clarity, tone, rewriting, and generative drafting across common writing surfaces; this profile is a research-based buyer guide, not a hands-on scorecard.
Read next
