Amy by Jellyfish vs Proto-Mind: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of Amy by Jellyfish and Proto-Mind — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
Amy by Jellyfish
Jellyfish
An always-on AI talent sourcer for staffing agencies that turns client briefs into searches, evidence-backed matches, outreach and managed replies.
Key features
- Client Brief Translation: Turns hiring conversations, job descriptions and hiring-manager tradeoffs into a living search plan, separating must-haves from flexible requirements.
- Search Beyond LinkedIn: Researches GitHub, Google Scholar, open-source projects, technical communities and the open web to find candidates who are not in the same database everyone else uses.
- Evidence-Backed Matching: Explains every match with role-specific evidence — technical depth, relevant scale, leadership, current intent — that recruiters can review and challenge.
- Multi-Channel Outreach Sequences: Runs personalized email, LinkedIn connections, follow-ups and InMail on a scheduled cadence, personalized from the candidate's own work.
- Candidate Inbox Management: Reads replies, answers routine questions, summarizes threads and routes qualified candidates to the right recruiter.
- Hiring-Manager Coordination: Keeps progress and evidence ready to share so recruiters do not rebuild context before every client update.
- Adjustable Autonomy: Run the full workflow on autopilot or keep approval gates on candidates, messages or client updates, changeable at any time.
- Feedback Learning Loop: Every hiring-manager decision and recruiter note reshapes the next search, improving match quality over time.
Best for
- Agency Sourcing Desk Coverage: Keep searches, inboxes and follow-ups moving across roles, markets and time zones without adding sourcer headcount.
- Hard-to-Fill Technical Roles: Find engineers and researchers through their GitHub, publications and community work when job titles and resumes miss them.
- Client Intake to Shortlist: Convert a fresh client brief into a qualified, evidence-backed candidate shortlist without manual Boolean search cycles.
- Outreach at Volume: Run personalized multi-touch sequences across many candidates while keeping each message grounded in that person's actual work.
- Reply Triage: Hand routine candidate questions and scheduling back-and-forth to the agent so recruiters only handle qualified conversations.
- Client Reporting: Produce weekly hiring-manager updates with the evidence and pipeline state already attached.
Proto-Mind
VIRENCORE
A native macOS floating workspace that keeps AI conversations, project memory, files and live voice together on your Mac.
Key features
- Floating Cube Workspace: Hover the cube to reveal the workspace and click to pin it, or move away to hide it while tasks keep running in the background.
- Per-Conversation Model Routing: Each chat picks its own model and account — ChatGPT with Codex access, supported model APIs, or a local Ollama model.
- Editable Project Memory: Notes, decisions and preferences stay attached to a project and carry into later conversations, and you can review, change or remove any of them.
- Live Voice Control: Speak to open a project, steer a running task or send new work, and add a correction while the task is still going.
- Detachable Companion Windows: Pull out and resize a browser, a file or a second conversation so reference material sits beside the work.
- Explicit Mac Access: Codex can work with files and run commands only after you turn Mac access on; screen control additionally requires Codex Desktop's signed Computer Use helper.
- Local Data Storage: Conversation history and saved memory live on your Mac, and cloud processing happens only when you choose a cloud model or voice.
- Open Source Beta: The macOS installer and the Apache 2.0 source are both published, so the workspace can be inspected and built from source.
Best for
- Long-Running Project Work: Keep a website or client project's decisions in project memory so each session resumes instead of re-explaining the brief.
- Brief to Deliverable: Have the agent read a client brief and save a proposal document, then open it in a companion window next to the conversation.
- Parallel Task Execution: Start several tasks across different models at once and check back on them without blocking the conversation you are in.
- Hands-Free Steering: Dictate a correction or open a project by voice while your hands are busy elsewhere on the Mac.
- Privacy-Sensitive Drafting: Run a local Ollama model so conversation content never leaves the machine.
- Model Comparison: Put the same question to a Codex route and a local model in adjacent windows to compare the answers side by side.