overview

A set of nine built-in AutoGPT agents, each focused on a different software task, such as writing backend code, designing interfaces, or managing other agents.

In plain words
What is it for?
Use the agents through AutoGPT command-line commands or its software-development kit to generate code, create architecture diagrams, design interfaces, manage tasks, make Git commits, send email, or refactor code.
Why use it?
It gives you ready-made roles for common development work instead of requiring one general agent to handle every task.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/wiseaidotdev/autogpt/overview
Clone the repo
git clone --depth 1 https://github.com/wiseaidotdev/autogpt
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 924 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00924
Opus 5 $0.00000 $0.00462
Sonnet 5 $0.00000 $0.00185
Haiku 4.5 $0.00000 $0.00092

Measured yesterday against content hash e0062aedcdb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

overview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/src/agents/overview.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Built-in Agents Overview

AutoGPT 0.2 ships with 9 built-in autonomous agents, each specializing in a different domain. They are independently usable via CLI subcommands and composable via the SDK's agents! macro.

Agent Roster

Agent Feature Flag CLI Subcommand Role
GenericGPT cli (default, no subcommand) Autonomous software engineering: reasons, edits files, builds, learns
ManagerGPT gpt autogpt man Task orchestration across all agents
ArchitectGPT gpt autogpt arch System architecture diagram generation
BackendGPT gpt autogpt back Backend source code generation
FrontendGPT gpt autogpt front Frontend UI code generation
DesignerGPT img autogpt design AI image and UI mockup generation
GitGPT git (automatic) Atomic Git commits from agent output
MailerGPT mail (SDK only) Email reading and automated sending
OptimizerGPT gpt (SDK only) Codebase modularization and refactoring

Agent Architecture

Every agent in AutoGPT is built from three composable layers:

┌─────────────────────────────────────────┐
│              Agent Struct               │
│  (e.g. ArchitectGPT, BackendGPT, etc.)  │
├─────────────────────────────────────────┤
│              AgentGPT Core              │
│  persona · behavior · memory · status   │
│  tools · knowledge · planner · context  │
├─────────────────────────────────────────┤
│          ClientType (LLM Client)        │
│  Gemini · OpenAI · Claude · XAI · Co    │
└─────────────────────────────────────────┘

Read the full file on GitHub · 98 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 98 lines · 0 tokens per session scan A e0062aedcdb1

Subscribe to this mod's changes

overview is an agent published in the GitHub repository wiseaidotdev/autogpt (115 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 924 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.