← Back to directory

AGNT

Community

The local-first agent operating system for building, running, and improving AI agents, workflows, and autonomous goals.

GitHub source repository ↗

★ 521 Stars Category · Dev Tools Very popular Source revision c129db78ac71

30FMRS · D

Reliability

4/20

Security and permissions

7/20

Maintenance

8/20

Documentation

7/20

Setup experience

4/20

AGNT is a feature-rich local-first agent operating system offering agents, workflows, goals, and plugin system. It emphasizes repeatability and self-improvement, suitable for users needing a persistent AI work platform. With local-first design, data control is strong, but technical knowledge is required for setup and configuration.

Read the FMRS scoring method →

AGNT is a local-first agent operating system, providing a desktop app and self-hostable backend for building, running, evaluating, and evolving AI work. It brings agents, workflows, goals, tools, memory, plugins, evals, traces, messaging, and APIs into one local workspace. AGNT supports 15+ AI providers, 60+ built-in tools, 25+ plugin templates, and is MCP-compatible. Its core execution modes are Agents (for judgment), Workflows (for repeatability), and Goals (for long-running objectives). AGNT is local-first, storing data in SQLite and filesystem, with inspectable traces, costs, and decisions.

Tools

agent

Provides creation, management, and chat with persistent AI workers.

workflow

Provides visual DAG automation workflows for creation, start, stop, and status.

goal

Manages autonomous objectives including planning, execution, evaluation, and rollback.

skill

Manages reusable skills and learning from execution traces.

plugin

Installs, uninstalls, reloads plugins and manages marketplace assets.

widget

Creates and manages custom dashboard widgets.

experiment

Runs evaluations and benchmark tests.

insight

Extracts and views learned insights and memory from runs.

mcp_server

Manages MCP servers and capability discovery.

Setup

Clone the repository: git clone https://github.com/agnt-gg/agnt.git; change directory: cd agnt; install dependencies: npm install; install frontend dependencies: cd frontend && npm install && cd ..; start: npm start. The backend runs at http://localhost:3333.

Fit and risk

Best for

Individual users running AGNT on a personal machine.
Small teams of 2-10 people sharing one backend.
Developers wanting a local agent backend they can inspect and extend.
Automation builders needing visual workflows plus AI judgment.
Power users wanting durable agents instead of throwaway chats.

Not for

Public multi-tenant SaaS.
Hosting unrelated organizations on one shared instance.
Large enterprises with 50+ concurrent users or zero-trust isolation requirements.
Users who only need a hosted chatbot or prompt playground.

Required permissions

Access local filesystem to read code and files.
Execute custom code (JavaScript/Python).
Call external APIs including AI providers.
Send and receive messages (Telegram, Discord, etc.).
Access network to connect to services.

Risks and side effects

Local API on port 3333 might be exposed to network, risking unauthorized access.
Ensure production secrets are changed for secure deployments.
Plugins can contain arbitrary code, so only install from trusted sources.
Browser automation may consume significant resources.

Troubleshooting

Ensure Node.js version is >=18.
Check if port 3333 is occupied.
Verify environment variables like JWT_SECRET are set correctly.
Check log files (e.g., <data-dir>/_logs/) for errors.
For Docker, use --pull always to fetch latest image.

Use cases

Build repeatable automation workflows with AI judgment.

Run long-term autonomous goals like a product launch.

Delegate tasks across multiple agents, tools, and APIs.

Run AI work locally or self-hosted with durable, inspectable traces.

Create reusable skills from execution traces.

Supported clients

Claude DesktopFull support

Related MCP servers

Compare with other MCP servers