Conclave
Conclave app icon
Native Windows app — not Electron

One workstation for
every AI model.

Conclave is a native Windows app that combines a full IDE with a real debugger, a multi-provider AI chat, agent teams, persistent project memory, scheduled automations, and 140+ MCP plugins.

Free. Run local models with Ollama or free NVIDIA NIM — zero API cost. Or bring your own keys. Your conversations never touch our servers.

Launching soon for Windows 10 & 11 · Free forever with your own keys

Conclave
+ New Chat
🔌 Plugins
🧠 Skills
⏱ Automations
📁 Conclave
📁 Web app
Ship checklist
Marketing copy
Conclave
A council of AI agents that build, review, and ship together
🛠
Build a project
Scaffold and develop a new app from scratch
📖
Review my code
Get feedback on quality, bugs, and best practices
📚
Explain a codebase
Understand architecture, patterns, and key files
What you get

Built for the way you actually work.

Native, not Electron

Cold-starts in under a second. Memory footprint that doesn't embarrass itself on an 8 GB machine. Behaves like a real Windows app — proper window snapping, multi-monitor, no Chromium baggage.

🔀

Every AI model, side by side

Claude, GPT, Gemini, Groq, Kimi, Copilot — all configured in one place. Sign in with Claude, ChatGPT, or Copilot directly, no API key required. Pin a model to an automation. Switch on the fly.

🦙

Local & free models, first-class

Run any Ollama model locally — Llama, Qwen, DeepSeek, Mistral — fully offline, zero API cost, your data never leaves the machine. Or use NVIDIA NIM's free hosted tier. Conclave treats them as equals to the paid providers.

⌨️

Chat mode and full IDE mode

Need a quick answer? Chat mode is your ChatGPT replacement. Building something? IDE mode gives you a multi-tab editor, integrated terminal, git source control, and a real debugger with breakpoints. One toggle. Same app.

🧠

Persistent memory system

Four layers of memory: per-project facts in .conclave/memory.md, a live code knowledge graph of every file and call, long-term archives you can semantically search, and shared team memory for Quorum. Your AI actually remembers your project.

🐞

Built-in debugger & LSP

F5, F9, F10, F11 — set breakpoints in the gutter, step through code, inspect state. Real Debug Adapter Protocol, real language servers for completions and diagnostics. Plus Open VSX extension marketplace for everything else.

👥

Team Mode & Quorum

Spin up multiple specialized agents (researcher, coder, reviewer) that work in parallel — same-provider runs collapse for speed, cross-provider runs fan out. Or run the same prompt across three models and compare answers side by side.

🔍

Code intelligence suite

Built-in slash commands for the work you actually do: /health, /perf, /predict, /scan, /audit, /translate, /timemachine, /architect, /design, /resolve, /compare, and more.

Auto-checkpoints & safe edits

Every risky turn snapshots your workspace before touching it. Diff preview with per-hunk accept/reject before applying. Five permission modes from Ask Permissions to Plan Mode to Autopilot. One-click undo, always.

🧩

140+ verified plugins

Connect your AI to GitHub, Linear, Gmail, Stripe, Notion, your database, and dozens of other services. Curated MCP marketplace with OAuth handled for you. Per-server trust prompts. Install in one click.

Scheduled automations

"Every morning at 9, summarize my open PRs." "Every Friday, audit the codebase." Backed by Windows Task Scheduler — automations fire on schedule even when Conclave is closed. Results land in a tagged chat for review.

🤖

Background agents & Autopilot

Kick off long-running tasks with /background and keep working. Autopilot loops through planning, tool use, and self-correction with live phase tracking. Auto-fix detects errors in tool output and offers one-click repair.

🔒

Privacy by default

Conclave never sees your conversations. Your data goes directly from your machine to the AI provider you picked. API keys are DPAPI-encrypted and bound to your Windows account. Telemetry is opt-in. Export or delete all data anytime.

🪄

Skills, presets & custom slash commands

Pre-built personas — Security Reviewer, REST API Builder, WPF Expert, and dozens more — that specialize the AI for the task. Or write your own skills and slash commands and reuse them across projects.

🎙

Voice, screenshots & computer use

Push-to-talk voice input with Whisper. Paste or drop screenshots straight into chat. Built-in computer-use tools let agents take screenshots and drive your mouse and keyboard for desktop automation.

Why Conclave

A different shape of product.

1

You're not locked into one AI vendor

Most AI tools pick a side — Cursor is Claude+GPT, Codex is OpenAI-only, Claude Code is Claude-only. Conclave runs every major model in the same app. When the next one drops, you add a key and it works. No waiting for your tool to catch up.

2

One app, two modes

Most people use ChatGPT Desktop for quick questions and Cursor or VS Code for coding — and lose context switching between them. Conclave morphs between a simple chat view and a full IDE depending on what you're doing. Same conversations, same models, same everything.

3

Made for Windows specifically

Cursor, Windsurf, ChatGPT Desktop, Claude Desktop — all Electron. They run on Windows but were built for Mac and feel like it. Conclave is native WPF on .NET 8. It belongs on a Windows machine.

4

Your data stays yours

Bring your own API keys. Your conversations go directly from your machine to whichever AI provider you chose. Conclave never sees them. We don't have a server to subpoena, breach, or sell your data from — because we don't have a server.

5

You can run it for $0

Most "AI workstations" require a paid subscription before you can type a word. Conclave runs end-to-end on free options: install Ollama and pull Llama, Qwen, or DeepSeek for fully offline inference, or use NVIDIA NIM's free hosted models. No credit card, no usage caps, no telemetry on your prompts.

Power tools

Slash commands for the work you actually do.

/health
0–100 grade across 7 dimensions of code quality.
/perf
Find performance anti-patterns before they ship.
/predict
AI-predicted bugs before you write the test.
/scan
Dependency vulnerability scan with remediation.
/audit
Deep blockchain connectivity audit (Cosmos, EVM, privacy chains).
/translate
Port a file to another language, faithfully.
/timemachine
Explain why code was written, line by line, from git history.
/architect
Plan with a big model, implement with a fast one.
/design
Drop a UI screenshot, get working code.
/resolve
AI-assisted merge conflict resolution.
/compare
Run the same prompt across two models, see both answers.
/codemap
Visual architecture map of your repo.
/semanticdiff
Diff explanation in plain English, not red and green.
/branch
Fork a conversation to try a different path.
/pin
Pin files to the context across every turn.
/background
Run a long task detached. Keep working.
/compact
Auto-prune long conversations without losing thread.
/pr
Generate a pull request description from your current diff.
Comparison

How Conclave stacks up.

Cursor Windsurf ChatGPT Desktop Claude Desktop Conclave
Native (not Electron)
Multi-provider AIpartialpartial✓ All major
Full IDE with debuggerpartialpartial
Simple chat modepartialpartial
Agent orchestrationpartialpartial✓ Team & Quorum
Persistent project memorypartialpartialpartialpartial✓ 4-layer
Code knowledge graph
Plugin marketplacepartial✓ 140+ MCP
Scheduled automations
Auto-checkpoints & undopartialpartial
Local models (Ollama)partialpartial✓ First-class
Runs free, no subscription
BYOK (no vendor lock-in)partialpartial

Stop juggling AI tools.

One native Windows app. Every major AI model. Run it free with local Ollama or NVIDIA NIM — or bring your own keys.

Get Early Access

Launching soon · Be first in line