Skip to main content

Get Cohort

One installer. Five minutes to your first AI agent session.
Everything runs on your machine. Your data never leaves.

OPEN SOURCE
FREE PRO ENTERPRISE

pip install

CLI
zero dependencies

For developers who already have Python. Lightweight core with only two dependencies. Full control over your setup.

# Recommended — full server + MCP tools
$ pip install "cohort[server]"
# Library only (MCP client, no server)
$ pip install cohort
# Everything including dev tools
$ pip install "cohort[all]"
# Run the setup wizard
$ python -m cohort setup
  • [OK] Same software, same features
  • [OK] Python 3.11+ required
  • [OK] Works on Windows, macOS, Linux
  • [OK] CLI + MCP server
  • [OK] Web dashboard included
View on PyPI
RECOMMENDED
FREE PRO ENTERPRISE

Windows

1-Click
~19 MB download

Download, install, launch. The setup wizard handles everything -- GPU detection, model download, configuration. No terminal required.

  • [OK] Embedded Python (no install needed)
  • [OK] Setup wizard detects your GPU
  • [OK] Downloads best model for your hardware
  • [OK] System tray icon (runs in background)
  • [OK] Web dashboard in your browser
  • [OK] Start Menu + Desktop shortcuts
  • [OK] Optional auto-start with Windows
Windows 10+ · 64-bit · v0.4.12
Windows Download COMING SOON
FREE PRO ENTERPRISE

Docker

Container
isolated environment

For teams and CI/CD pipelines. Pre-built container with everything included.

$ docker compose up
  • [OK] Same software, same features
  • [OK] Dockerfile + docker-compose included
  • [OK] Works on any Docker host
  • [OK] GPU passthrough supported
View on GitHub

What Happens After You Install

The Windows installer gets you to a working AI agent session in three steps. No terminal, no configuration files, no manual downloads.

1

Launch Cohort

Click the desktop shortcut or find Cohort in the Start Menu. A system tray icon appears and your browser opens to the dashboard.

2

Setup Wizard Runs Automatically

On first launch, the wizard detects your GPU, installs the AI engine (Ollama), and downloads the best model for your hardware. You'll see progress bars for everything -- the model is 5-8 GB depending on your GPU.

3

Start Your First Session

The dashboard is ready. Create a channel, pick your agents, and start a discussion. Contribution scoring, loop prevention, and executive briefings all work out of the box. After the first setup, Cohort runs entirely offline.

System Requirements

Cohort runs AI models locally on your hardware. Here's what you need.

Minimum

  • OS
    Windows 10 (64-bit)
  • RAM
    16 GB
  • Disk
    15 GB free
  • GPU
    CPU-only mode available

Recommended

  • OS
    Windows 11
  • RAM
    32 GB
  • Disk
    25 GB free (SSD)
  • GPU
    NVIDIA with 8+ GB VRAM
[*] About GPU requirements

An NVIDIA GPU dramatically speeds up AI inference (10-30x faster than CPU). The setup wizard automatically detects your GPU and selects the right model. Without a GPU, Cohort still works -- it just uses CPU inference, which is slower but fully functional.

What's in the Box

The same open-source software, packaged for convenience. Nothing is hidden, nothing is locked.

CohortSetup.exe (~19 MB)
  [OK] Python 3.13 -- embedded runtime (you don't need Python installed)
  [OK] Cohort 0.4.12 -- same package as pip install cohort[server]
  [OK] Web Dashboard -- browser-based UI on localhost
  [OK] System Tray App -- background launcher, one-click open
  [OK] Setup Wizard -- GPU detection + model download
  [OK] Agent Configs -- pre-configured AI agent personas
First-run download (~5-8 GB, one time only)
  [OK] AI Model -- auto-selected for your GPU
  [OK] Ollama -- local AI inference engine

Ready to run AI agents locally?

Your agents. Your hardware. Your data.

Windows Download COMING SOON View Source on GitHub

Apache 2.0 Licensed · The installer and the pip package ship identical software · VirusTotal Verified