ABrush vs chat-recall: Features, Pricing & Which Is Better (2026)

A side-by-side comparison of ABrush and chat-recall — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.

ABrush

Freemium

AI image generation and editing studio that runs as a panel inside Adobe Photoshop, with 23+ models, ControlNet, LoRA styles and layer-native output.

Photoshop-native panel: Generation, editing and upscaling happen on the open document and land on real layers, with no export-import round trip
23+ models in one panel: Switch between Stable Diffusion, Flux, Qwen Image and others per stage of a piece rather than committing to one provider
Targeted editing: Inpaint or regenerate only the region that needs changing, keeping the rest of the composition untouched
Pro conditioning controls: ControlNet support plus IP-Adapter and reference images for pose, composition and style control
Custom LoRA styles: Load your own LoRA or style models to keep generations consistent with an established look
Generation history: Every generation is saved and recoverable, so artists can return to an earlier variation without regenerating
Shareable presets: Save prompts and settings as presets and share them across a team to reproduce a house style
Commercial-safe data policy: Generated images belong to the user and customer images are not used for model training

A concept artist generating multiple variations of a character directly in the working file and painting over the strongest one
A retoucher fixing a single element of a composite with inpainting rather than regenerating the whole image
A studio distributing a shared preset pack so several artists produce work in a consistent house style
A freelance illustrator using a custom LoRA to keep generated assets on-style with a client's brand
A designer upscaling and cleaning up a low-resolution asset without leaving Photoshop
An agency handling commercial client work that needs assurance the images aren't used for model training

Freemium

Makes every conversation your team has had with AI coding assistants searchable, and flags secrets leaked into those chats.

Unified Conversation Search: Full-text search across the chats, plans, task lists and notes written by five supported AI coding tools, searchable the moment they arrive.
Local Secret Redaction: Passwords and API keys are stripped on your own computer before anything is uploaded; only the last few characters are ever received.
Leaked Key Reporting: Shows every key found, whether it is still live, and how many conversations it appeared in, with support for custom in-house key formats you register.
MCP Server and Recall Tools: Exposes the history to your assistants through an MCP server so they can query past work directly rather than starting cold.
Ranked Action Plan: Derives code findings and a prioritized list of what to fix next, written out as CODE_TASKS.md.
Self-Closing Bug Tasks: Each detected bug becomes a task with a sketched fix, and closes itself once the problem is actually gone.
Config Distribution: Skills and MCP configuration follow you to every machine and to whichever assistant you pick up next, with a per-machine view of what is missing.
Per-Project Rules: Mark a project as a prototype or a live product once, and every assistant that opens it plays by the matching rules.

Credential Incident Response: Find which keys were pasted into assistant conversations, whether they are still valid, and where they spread.
Recovering Past Decisions: Search months of AI conversations to recover a plan or rationale instead of asking the same question again.
Onboarding a New Machine: Sign in on a new laptop and get the full conversation history and every accumulated skill without copying files by hand.
Switching Assistants: Try a different AI coding tool without losing the add-ons and context built up in the previous one.
Team Knowledge Sharing: Share project history selectively with teammates and assign follow-up work from a shared task board.
Security Review Before Shipping: Run the secret monitor and code findings over accumulated history as a pre-release check.