Your AI Coding Agent That Doesn't Hide What It's Doing

NanoAgent works inside a real repository while keeping you in control — understand a codebase, plan a change, edit files, run validation, review a diff, and automate reviews from the same toolchain you already use. Every action is visible and reviewable.

$ curl -fsSL https://raw.githubusercontent.com/rizwan3d/NanoAgent/master/scripts/install.sh | bash
PS> irm https://raw.githubusercontent.com/rizwan3d/NanoAgent/master/scripts/install.ps1 | iex
$ npm install -g nanoai-cli
$ pnpm add -g nanoai-cli
$ bun add -g nanoai-cli
$ ext install rizwan3d.nanoagent

Docked tool window drives the local nanoai CLI over ACP.

Extensions ▸ Manage Extensions ▸ search “NanoAgent”

Docked tool window drives the local nanoai CLI over ACP.

Windows · macOS · Linux (x64 / arm64)

Verify with SHA256SUMS + build attestation.

nanoai
NanoAgent running in a terminal
Why NanoAgent

Power-user features, nothing hidden

Built for practical engineering work: real symbols, version-controlled memory, scriptable runs, and a sandbox for anything sensitive.

Comparison

How NanoAgent compares

See what makes NanoAgent different from other AI coding tools.

Feature NanoAgent Codex Claude Code OpenCode Kilo Code GitHub Copilot Aider
Local-first
Repo memory
VS Code extension
Visual Studio
JetBrains plugin ✓ (ACP)
CI code reviews
15+ AI providers
ACP protocol
Sandboxed execution
Open source
LSP
Direct shell & background terminals
Subagents & orchestration
Local codebase indexing
Memory, audit & hooks
SDK to embed in your app

Yes · Partial · No

Provider choice

Use the model that fits your budget & policy

From subscription sign-in to API-key providers to fully local models — NanoAgent adapts to what you already pay for.

Quickstart

Up and running in two steps

Install, then let NanoAgent walk you through provider setup on first launch — or preseed it with environment variables.

1

Install the CLI

# install
curl -fsSL https://raw.githubusercontent.com/rizwan3d/NanoAgent/master/scripts/install.sh | bash

# start
nanoai
# install
irm https://raw.githubusercontent.com/rizwan3d/NanoAgent/master/scripts/install.ps1 | iex

# start
nanoai
2

Pick a provider & go

Launch and let onboarding walk you through setup — or preseed it and skip straight to a run:

# launch — onboarding walks you through provider setup
nanoai
# headless setup via environment variables
export NANOAGENT_PROVIDER="openai"
export NANOAGENT_MODEL="gpt-5-5"
export NANOAGENT_THINKING="on"
export NANOAGENT_API_KEY="PASTE_NEW_ROTATED_KEY_HERE"

nanoai -p "Say hello in one short line" --yes
SDK for .NET

Embed NanoAgent in your own app

The NanoAgent SDK ships on NuGet. Add the package, point it at your provider, and drive the same agent — profiles, permissions, memory, and all — from inside your application.

# add the SDK to your project
dotnet add package NanoAgent

# or in your .csproj
<PackageReference Include="NanoAgent" Version="*" />

Ship with an agent that keeps you in control.

Local-first. Reviewable. Open source under Apache-2.0.