v0.2.2 · Latest Linux & macOS MIT

Your AI tools,
amplified.

NEXUS sits beneath your AI CLIs — routing micro-tasks to local hardware, sharing instructions with configured tools, and showing local routing and cost metrics. A desktop Companion is in development.

120+ tokens/sec local

12+ built-in personas

4 configured CLI interfaces

One command to install

$ curl -sSL https://raw.githubusercontent.com/canoo/agent-nexus/main/install.sh | bash

Downloads pre-built binary + clones repo to ~/.config/nexus

Get started → View on GitHub · 5 ★

zsh — nexus

~ $ nexus

⚡ NEXUS Framework Manager v0.1.1

──────────────────────────────────

▸ Install NEXUS

Configure

Health Check

Uninstall NEXUS

j/k: navigate • enter: select • q: quit

──────────────────────────────────

NEXUS ▸ task: generate commit message

NEXUS ▸ routing to local compute plane

NEXUS ▸ delegate → qwen2.5-coder:1.5b [supervisor band]

NEXUS ▸ ✓ complete [4.2s] [0 cloud tokens used]

~ $

Your tools, connected · see compatibility ↓

🔌

Bring your own tools

Claude Code, Antigravity (agy), Kiro, and Gemini CLI today. More integrations are coming — see the compatibility section.

🖥️

Bring your own models

Cloud APIs, local Ollama, or both. Route tasks to the right tier based on complexity, not vendor lock-in.

🔗

One config, every tool

Shared instructions and personas for configured tools. Broader tool projection is planned.

📊

Observe everything

View NEXUS routing metrics and optional Tokscale aggregates. Companion activity will remain a separate source.

What NEXUS does

One framework. Every AI tool.

⚡ Expert Orchestrator

The right specialist for every task.

NEXUS acts as the brain between your AI CLI and every specialist agent. Before doing any work, it scans your persona registry for the right expert — and asks if none exists.

NEXUS ▸ task: design auth schema
NEXUS ▸ scanning persona registry...
NEXUS ▸ delegate → engineering-backend-architect
NEXUS ▸ DONE. context preserved.

🧠 Persona Registry

12+ built-in specialists.

From backend architect to TUI developer to mobile builder. Each persona has precise trigger words, allowed tools, and domain expertise. Define your own in minutes.

backend-architect bubbletea-tui code-reviewer frontend-dev git-workflow mobile-builder + more

🖥️ Local Compute Plane

Route micro-tasks to your GPU.

The nexus-ollama MCP server routes structured tasks — commit messages, lint fixes, test scaffolds — to local Ollama models. Deep work stays in the cloud. Boilerplate doesn't.

Supervisor (1.5B)

120+ t/s

commit, boilerplate, tests

Logic (3B)

~75 t/s

lint-fix, refactor

🔗 One Config, Every Tool

Define once. Sync everywhere.

A single NEXUS install symlinks your personas and routing rules into Claude Code, Gemini/Antigravity, and Kiro. Broader configuration projection is planned. Update the persona file once — all tools see it instantly.

Claude Code Gemini / agy Kiro CLI

🔌 MCP Tools

Automatic local delegation.

Six tools available via Model Context Protocol. Your AI CLI calls them transparently — no context switching, no copy-paste.

ollama_commit_msg ollama_lint_fix ollama_logic_refactor ollama_boilerplate ollama_test_scaffold ollama_health

📊 Observability Dashboard

See what your AI stack costs.

Session logging, model routing decisions, cloud vs local spend — all surfaced in the TUI. Optional Tokscale integration brings in local CLI usage aggregates while keeping them separate from NEXUS routing savings.

Session #47  qwen2.5-coder:1.5b  4.2s   $0.00
Session #46  claude-3-7-sonnet   12.1s  $0.031
Session #45  llama3.2:3b         3.1s   $0.00
──────────────────────────────────────────────
Month:  Cloud $2.41  ·  Local $0.00  ·  Saved ~$8.20

Persona Registry

Built-in specialists. Ready to deploy.

Each persona is a .md file that loads into any AI CLI via NEXUS. Swap them out, compose your own, or pull community personas from the marketplace (v0.4.0).

⚡

Expert Orchestrator

agents-orchestrator.md

The brain. Routes every task to the right specialist before picking up a tool.

trigger: any task

🏗️

Backend Architect

engineering-backend-architect.md

Scalable system design, database architecture, API development, cloud infra.

trigger: architect, design schema, API

🎨

Frontend Developer

engineering-frontend-developer.md

Astro, React, Vue, Svelte, Tailwind. Components, pages, layouts, DX.

trigger: build UI, component, page

📲

Mobile App Builder

engineering-mobile-app-builder.md

Native iOS/Android and cross-platform frameworks. App store to device.

trigger: mobile, iOS, Android, app

⬛

TUI Specialist

bubbletea-tui.md

Go terminal UIs with Bubbletea v2, Bubbles v2, and Lipgloss. Multi-screen flows.

trigger: TUI, terminal UI, bubbletea

🔍

Code Reviewer

engineering-code-reviewer.md

PR review, quality gates, security patterns, and constructive critique.

trigger: review, audit, check PR

🚀

DevOps / CI Agent

engineering-devops-ci-agent.md

CI/CD pipelines, containerisation, infrastructure automation, deployment.

trigger: CI, deploy, pipeline, Docker

🌿

Git Workflow Master

engineering-git-workflow-master.md

Atomic commits, branching strategy, clean history, PR hygiene.

trigger: commit, branch, rebase, merge

🔥

Firebase Agent

engineering-firebase-agent.md

Firestore, Auth, Functions, Hosting, and the full Firebase / GCP stack.

trigger: Firebase, Firestore, Auth

🗺️

Dev Roadmap

engineering-dev-roadmap.md

Project planning, issue triage, milestone scoping, and roadmap execution.

trigger: roadmap, planning, milestone

🧭

Onboarding Guide

onboarding-guide.md

First-run setup, hardware detection, model selection, and symlink verification.

trigger: setup, onboard, install NEXUS

🧪

UI Tester

ui-tester-agent.md

Playwright automation, screenshot capture, visual QA, regression testing.

trigger: test UI, screenshot, Playwright

Learn how personas work → · Browse vault on GitHub ↗

Local LLM Performance

Real numbers. Real hardware.

Benchmarks measured via JSON-RPC against the MCP server on an RTX 3050 Mobile (4GB VRAM). Every task type, every model, actual throughput.

Speed Benchmarks

RTX 3050 / 4GB VRAM

Model	Band	t/s
qwen2.5:0.5b <0.5 GB	micro	228–261
qwen2.5-coder:1.5b ~1.2 GB	supervisor	~122
gemma2:2b ~1.5 GB	supervisor	~84
llama3.2:3b ~2.0 GB	logic	~73
qwen2.5:3b ~2.0 GB	logic	~72
qwen:4b ~3.0 GB	logic	~28
qwen2.5:7b ~4.7 GB	heavy	~10

supervisor band logic band heavy band (12GB+ VRAM)

Hardware Presets

Full guide →

Hardware	VRAM	Speed
RTX 3050 Mobile	4 GB	70–120 t/s
M3 Base	8 GB UM	45–50 t/s
RTX 3060 / 4060	8 GB	40–60 t/s
M3 Pro 18GB	18 GB UM	25–30 t/s
RTX 4060 Ti 16GB	16 GB	35–55 t/s
RTX 4090	24 GB	30–70 t/s
RTX 5090	32 GB	61–100 t/s
M3 Max 48GB	48 GB UM	18–35 t/s
M3 Max 96GB	96 GB UM	8–20 t/s

Supervisor model: commit-msg, boilerplate, test scaffolds · Logic model: lint-fix, code refactor

MCP Test Results · RTX 3050 · Default Config

✓

ollama_commit_msg

qwen2.5-coder:1.5b · ~4.5s

Clean conventional commit

✓

ollama_boilerplate

qwen2.5-coder:1.5b · ~7s

Reasonable Express+Zod scaffold

✓

ollama_test_scaffold

qwen2.5-coder:1.5b · ~3s

Correct describe/it blocks

⚠

ollama_lint_fix

llama3.2:3b · ~6.5s

Fixed most errors; edge case garble

✓

ollama_logic_refactor

llama3.2:3b · ~3s

Nested loops → filter+map

✓

ollama_health

— · instant

Lists all available models

Roadmap

Where NEXUS is headed.

Every milestone is tracked on GitHub. Pick an issue and open a PR — contributions welcome.

v0.1.x — Foundation

Released

· Interactive TUI (Go/Bubbletea v2) — install, configure, health check, uninstall
· Persona registry (12+ built-in specialists)
· nexus-ollama MCP server with 6 delegation tools
· Symlink architecture — one config for every AI CLI
· Linux and macOS support

v0.2.0 — Observability

Released

· Session logging — which model, how long, estimated cost (#9)
· TUI dashboard — live view of routing decisions and model usage (#10)
· Cost tracker — cloud vs local spend; "what this would have cost" estimation (#11)

v0.2.1 — Tokscale Integration

Released

· Optional adapter for local Tokscale model and cost aggregates (#22)
· Usage & Cost Dashboard that keeps Tokscale data separate from NEXUS routing savings (#23)
· Health checks and graceful degradation when Tokscale is not installed (#24, #25)
· Thanks to Tokscale and its contributors for upstream multi-tool usage ingestion

v0.2.2 — Stability sprint

Released

· SQLite-only task log
· Fresh-install and Claude Code MCP fixes
· Toolchain updates and zero MCP audit vulnerabilities

v0.3.0 — Desktop Companion Private Preview

In Progress

· Explicit consent, pause/resume, and private browser activity
· Chrome/Edge native host with Linux/macOS desktop controls
· Project memory and routing foundations; browser and packaging verification pending

v0.3.1 — Universal Sync Layer

Planned

· Broader configuration projection across tools
· Machine-readable readiness and adoption workflows
· Shared CLI/desktop interfaces; package extraction proposed

v0.4.0 — Ecosystem

Planned

· Cross-tool persona sync — NEXUS format → Gemini YAML, Claude MD, Kiro steering (#15)
· Persona composition — combine traits from multiple personas (#16)
· Plugin system — extensible MCP tools via YAML/JSON specs (#17)

v1.0.0 — Stable Release

Future

· Windows support, Docker, Homebrew (#18)
· Stable API — frozen interfaces, semantic versioning, migration guide (#20)

View milestones on GitHub → · Good first issues ↗

Live from GitHub

Recent Activity

View all commits ↗

Commits

Contributors

Use with

Know what works. Help build what’s next.

The CLI stays available to agents and scripts. The Companion adds an approachable desktop interface, starting with explicit privacy controls.

NEXUS CLI & local compute

Available in v0.2.2 on Linux and macOS. Installer, configuration and delegation checks run in CI; this is not a claim of live testing against every vendor release.

Claude Code

Available

Instructions, personas and MCP setup

Antigravity · agy

Available

Primary Google runtime with shared config & routing

Gemini CLI

✕ Replaced

Legacy CLI replaced by agy; shares configuration

Kiro

Available

Steering instructions and MCP setup

Ollama

Available

Local model delegation

Gemini CLI deprecation: Google officially deprecated Gemini CLI in favor of Antigravity CLI (agy). NEXUS supports shared configurations for backwards compatibility while directing new workflows to agy. See the Google transition announcement and our v0.2.0 changelog.

Companion · v0.3.0 private preview

In development, not released. Chrome and Edge adapters have unit and privacy-contract coverage. Real-browser, native-host, desktop-runtime and packaging validation are still pending.

Chrome · preview

Edge · preview Firefox, Safari, Windows and desktop detection: later, unverified

ChatGPT

Preview

Selected-tab activity

Claude

Preview

Selected-tab activity

Gemini

Preview

Selected-tab activity

Microsoft Copilot

Preview

copilot.microsoft.com activity

Perplexity

Preview

Selected-tab activity

Coming · help us verify it

Planned configuration integrations. These tools are not yet verified with NEXUS, and their logos do not promise current support.

Codex

Coming

NEXUS configuration integration

Cursor

Coming

NEXUS configuration integration

GitHub Copilot

Coming

Coding-tool configuration

Windsurf

Coming

NEXUS configuration integration

Cline

Coming

NEXUS configuration integration

Continue.dev

Coming

NEXUS configuration integration

Community

Contribute to NEXUS

Contribution guide →

NEXUS is shaped by developers testing integrations, hardening platform support, and improving documentation. Big thanks to our community contributors:

Blake Saunders @blakesaunders

Claude Code loading and fresh-install MCP registration

Matt Van Horn @mvanhorn

TUI home directory handling and documentation cleanup

anakinMango @anakinMango

macOS installer compatibility and checksum verification

Help test integrations with your tools, report compatibility results, or improve guides.

Good First Issues ↗ Discord Community ↗

Get started now

Ship with the right expert
every time.

One install for supported tools. No Go toolchain needed.


curl -sSL https://raw.githubusercontent.com/canoo/agent-nexus/main/install.sh | bash

Read the docs → Star on GitHub ★

Your AI tools, amplified.

Bring your own tools

Bring your own models

One config, every tool

Observe everything

One framework. Every AI tool.

The right specialist for every task.

12+ built-in specialists.

Route micro-tasks to your GPU.

Define once. Sync everywhere.

Automatic local delegation.

See what your AI stack costs.

Built-in specialists. Ready to deploy.

Real numbers. Real hardware.

Where NEXUS is headed.

Recent Activity

Know what works. Help build what’s next.

NEXUS CLI & local compute

Claude Code

Antigravity · agy

Gemini CLI

Kiro

Ollama

Companion · v0.3.0 private preview

ChatGPT

Claude

Gemini

Microsoft Copilot

Perplexity

Coming · help us verify it

Codex

Cursor

GitHub Copilot

Windsurf

Cline

Continue.dev

Contribute to NEXUS

Ship with the right expertevery time.

Built with

NEXUS

Companion preview

This site

Your AI tools,
amplified.

Ship with the right expert
every time.