v1.0 · Works with Claude Code, Cursor, OpenCode & more

Turn Your Agents into a
Self-Evolving Team

DeepVista CLI connects your coding agents to a shared knowledge base — so they don't just execute, but learn, remember, and build on past work.

$curl -sSL https://raw.githubusercontent.com/DeepVista-AI/deepvista-cli/main/install.sh | bash

Or view on GitHub →

Your ideas. Never lost.

Capture insights mid-session with a single line. DeepVista stores them in your knowledge base, ready to search and synthesize later.

deepvista notes
$ deepvista notes +quick "Tobi Lütke: the company is a tool to amplify what you love" ✓ Note saved to knowledge base id: note_7d3f9a indexed: semantic + full-text
One consolidated skill

One install.
All capabilities.

The deepvista skill installs to your agent's skill directory. Reference files load on demand.

Notes
Quick capture — one-liners or full structured notes, instantly indexed.
Cards
Knowledge cards — create, search, pin, edit across all your captured content.
Vistabase
Implicit memory from chat sessions — read-only, auto-accumulated context.
Skills
Structured AI workflows — list, run, export, discover, and install.
Chat
Conversational AI agent with full access to your knowledge base.
Auto-Capture
Silently saves facts, decisions, insights as you work with any agent.
Use cases

Use Cases

Copy a prompt, paste it in your agent, and let DeepVista handle the rest.

Use Case 01

Podcast Note Capture

Transform podcast insights into structured knowledge through guided discussion.

Paste this prompt in your agent.
I just listened to the Lenny's Podcast episode with Brian Chesky about founder mode. Objectives: 1. Discuss the episode together (1 question at a time, maximum 2 questions). 2. Capture a summary, key insights, and main takeaways. 3. Save the final insights to DeepVista as a note titled "Brian Chesky – Founder Mode".
Use Case 02

ICP Clarity Session

Sharpen your ideal customer profile through structured self-discovery.

Paste this prompt in your agent.
I want to sharpen my understanding of our ideal customer profile (ICP). Before we start: Search my DeepVista knowledge base for any existing notes, decisions, or context related to our customers, target segments, or ICP. Objectives: 1. Discuss my ICP together — ask me 1 question at a time, maximum 2 questions — to surface what I already know and what I'm uncertain about. 2. Synthesize a clear ICP summary covering: who they are, what problem they have, why they choose us, and what makes them a great fit vs. a bad fit. 3. Save the final ICP to DeepVista as a note titled "Ideal Customer Profile – [Company/Product Name]".
Use Case 03

Customer Call Capture

Extract key decisions and insights from customer conversations.

Paste this prompt in your agent.
I want to capture the key decisions and insights from a recent customer call. Before we start: Search my DeepVista knowledge base for any existing notes related to this customer, their company, or past interactions. Objectives: 1. Discuss the call together — ask me 1 question at a time, maximum 2 questions — to surface what was decided, what surprised you, and what it means for the product or business. 2. Synthesize a clear call summary covering: who you spoke with, what problem they shared, what was decided or committed to, and what the key insight or next step is. 3. Save the final summary to DeepVista as a note titled "Customer Call with [Company Name]".
Workflow Templates

Skill Patterns

Build these workflows in the DeepVista web app, then invoke them through your agent with a single prompt.

Research synthesis

Pull insights from your knowledge base and synthesize them into actionable research.

Search my KB for [topic] and run my Research Synthesis Skill

Idea evaluation

Test new ideas against proven mental models you've captured.

Evaluate this idea against my founder frameworks: [idea]

Weekly review

Reflect on your week with AI-assisted pattern recognition.

Run my weekly review — surface pinned cards and capture key learnings

Interview debrief

Extract insights from customer conversations automatically.

I just finished a user interview. Run my Interview Debrief Skill

Decision memo

Make better decisions by leveraging everything you've learned.

Help me think through this decision using my knowledge base: [decision]

Competitive analysis

Synthesize competitive intel from your accumulated knowledge.

Run a competitive analysis on [company/space] using everything I've captured
CLI Reference

Command Reference

The agent handles all of this for you, but here it is for reference.

CommandDescription
deepvista auth login
Open browser for authentication
deepvista auth login --code <code>
Paste code from browser
deepvista auth status
Check authentication state
deepvista auth logout
Clear credentials

Install with OpenClaw

Just paste this prompt into your agent

Paste this prompt in your agent.

Install DeepVista CLI. Visit cli.deepvista.ai for docs. Install command: curl -sSL https://raw.githubusercontent.com/DeepVista-AI/deepvista-cli/main/install.sh | bash. Requires Python 3.12+. If Python 3.12 isn't available, install it first. After install, run "deepvista auth login" and share the URL with me so I can authenticate.

Uninstall

To remove DeepVista CLI from your system

$curl -sSL https://raw.githubusercontent.com/DeepVista-AI/deepvista-cli/main/uninstall.sh | bash

$ deepvista auth login

Your knowledge base.
Your agent. Your edge.

Drop one note. Watch it become structured execution.

Get Early AccessRead the Docs