ag2ai

Drive external CLI coding agents (Claude Code, Codex, OpenCode) as first-class AG2 Agents over the Agent Client Protocol (ACP): point an Agent at a ClaudeCodeConfig / CodexConfig / OpenCodeConfig preset from ag2.acp and ask()/run() it like any agent, with its…

Expose an AG2 `Agent` over the Agent-to-Agent (A2A) protocol so any A2A-compliant client (or another AG2 agent) can call it across process/host boundaries. Wrap the agent with `A2AServer(agent)` and serve it via `build_jsonrpc(...)`, `build_rest(...)`, or…

Add a custom Python tool to an AG2 `Agent` using the `@tool` decorator. Use when the user wants to give an Agent a new capability backed by Python code (API calls, DB queries, computations, file ops). Covers sync and async tools, parameter typing, Pydantic…

Expose an AG2 `Agent` over the AG-UI protocol so a frontend (CopilotKit, custom React/Next.js, or any AG-UI client) can stream responses (text and reasoning), render tool calls, sync shared state, and track sub-task steps. Wraps the agent with…

Compare AG2 agents, models, or prompts to decide which is better. run_variants scores several named agents on one suite and ranks them on a leaderboard (Variants holds a mapping of named Agent instances plus an axis label). run_pairwise with pairwise_judge…

Evaluate, test, and track an AG2 Agent offline. Build a Suite of tasks, run the agent with run_agent, and grade answers with prebuilt scorers (final_answer_matches, tool_called, no_tool_errors, token_budget) or a custom @scorer — including the agent_judge LLM…

Pause an AG2 `Agent` mid-run to collect human input via `context.input()`, or gate a tool call with `approval_required()` middleware. Use when the user wants the agent to ask for confirmation, request missing info (passwords, API keys, data), or have a human…

Persist agent state across runs, shape what the LLM sees per turn, and cap history to fit a context window. Covers `KnowledgeStore` (memory / sqlite / disk / redis), `KnowledgeConfig` (`store=`, `expose_tool=`, `write_event_log=`, `compact=`, `aggregate=`,…

REST and WebSocket endpoint patterns, error handling, and Pydantic schema conventions for the backend

Architecture, directory layout, communication protocol, and conventions for the full-stack multi-agent application

Step-by-step guide to add a new REST or WebSocket endpoint to the backend

Step-by-step guide to add a new agent to the multi-agent team

Step-by-step guide to add a new page or component to the React frontend

How the Code Reviewer agent conducts systematic code reviews with prioritized findings

How the Research Analyst agent conducts research, evaluates sources, and produces structured reports

How to run the Agent Eval Benchmark dataset with ag2 test eval

Persist agent state across runs, shape what the LLM sees per turn, and cap history to fit a context window. Covers `KnowledgeStore` (memory / sqlite / disk / redis), `KnowledgeConfig` (`store=`, `compact=`, `aggregate=`, `bootstrap=`), aggregation strategies…

Monitor an AG2 beta agent's stream — log events, detect repeated tool calls, track token spend, build trigger-driven observers, route observer alerts to the model, and halt on FATAL conditions. Covers `@observer(...)` (stateless), `BaseObserver` (stateful),…

Add a custom Python tool to an AG2 beta `Agent` using the `@tool` decorator. Use when the user wants to give an Agent a new capability backed by Python code (API calls, DB queries, computations, file ops). Covers sync and async tools, parameter typing,…

Expose an AG2 beta `Agent` over the AG-UI protocol so a frontend (CopilotKit, custom React/Next.js, or any AG-UI client) can stream responses, render tool calls, sync shared state, and surface human-input checkpoints. Wraps the agent with `AGUIStream(agent)`…

Pause an AG2 beta `Agent` mid-run to collect human input via `context.input()`, or gate a tool call with `approval_required()` middleware. Use when the user wants the agent to ask for confirmation, request missing info (passwords, API keys, data), or have a…

Intercept the AG2 beta agent loop with `BaseMiddleware` — wrap full turns (`on_turn`), each LLM call (`on_llm_call`), each tool execution (`on_tool_execution`), or each human-input request (`on_human_input`). Use for retry, logging, history trimming, request…

Send images, audio, video, or documents into an AG2 beta `Agent` alongside text. Pass `ImageInput`, `AudioInput`, `VideoInput`, or `DocumentInput` as positional args to `agent.ask(...)`. Use when the user wants the agent to process non-text input — describe a…

Map of AG2 beta capabilities and which sibling skill to reach for. Load first when the user mentions building with AG2 beta (autogen.beta) but the specific feature isn't yet clear — agents, tools, model config, delegation, memory, observers, structured…

Add code execution capability to AG2 agents using LocalCommandLineCodeExecutor or Docker. Use when the user wants agents that can write and run Python code.

Add safety guardrails to AG2 agents using LLMGuardrail and RegexGuardrail. Use when the user wants to enforce safety constraints, filter PII, or redirect off-topic responses.

Wire a Model Context Protocol (MCP) server into AG2 agents using create_toolkit. Use when the user wants to connect external tools via MCP.

Build an AG2 handoff-driven workflow with DefaultPattern, agent handoffs, context variables, and routing. Use when the user wants customer service routing, state-machine workflows, or explicit agent-to-agent transitions.

Build a Retrieval-Augmented Generation (RAG) agent using AG2's RetrieveUserProxyAgent with vector database support. Use when the user wants agents that can query documents or knowledge bases.

Build an AG2 ReasoningAgent that uses tree-of-thought reasoning with beam search, MCTS, or LATS strategies. Use when the user needs advanced reasoning for complex problem solving.

Build a complete web research agent team using AG2 with search tools, web crawling, and structured output. Use when the user wants a practical research or information-gathering workflow.

Scaffold a complete AG2 multi-agent team with agents, tools, group chat configuration, and an entry point. Use when the user wants to create a new multi-agent workflow from scratch.

Use when writing or modifying tests under tests/ — base testcase inheritance, pytest markers, fixtures, in-memory vs real-broker testing, and how to run the suite.

Use when writing or editing documentation under docs/ — page layout, docs_src snippet embedding, snippet tests, link conventions, and FastStream example-code rules.

Use when writing or modifying FastStream library source code under faststream/ — package layout, broker package anatomy, typing rules, configs, and public API conventions.

Use when setting up the FastStream dev environment, running tests/linters/static analysis, managing docker brokers, or preparing a PR.

Use when the user asks what you can do, whether you can do a specific thing (make images, run something on a schedule, read a folder, reach their email), how to make you do it, where in the app to change a setting, or why you can't access something. Covers…

Use when the user wants to read, summarise, extract text/tables from, split, merge, or fill a PDF. Explains when to read a PDF visually vs. extract its text, and how to manipulate PDFs via code execution.

Use when the user asks you to write or reply to an email or message. Produces a ready-to-send draft in their voice, matching their learned tone and formatting preferences.

Use when the user asks you to research a topic, fact-check a claim, compare options, or gather current information from the web. Guides thorough, multi-source research using the search and web-fetch tools.

Applies AG2's official design system and brand guidelines to all generated code, artifacts, UI components, and visual output. Use this skill whenever building web pages, landing pages, dashboards, product UIs, React components, HTML artifacts, presentations,…