Ag2 Overview
- 34 installs
- 8 repo stars
- Updated July 27, 2026
- ag2ai/ag2-skills
ag2-overview is a Claude Code skill that maps AG2 beta capabilities and routes to the right sibling skill for building agents.
About
This skill is a capability map of AG2 beta (autogen.beta), an async, protocol-driven agent framework, and an index of which sibling skill to reach for. A developer loads it first when a request mentions building with AG2 beta but the specific feature is not yet clear. It covers the three setup prerequisites (provider extra, API key, install check) and a table mapping user intents to skills like ag2-quickstart, ag2-add-custom-tool, and the network skills.
- Index of AG2 beta capabilities and which sibling skill to load next
- Covers the three prerequisites: provider extra, API key, and install sanity-check
- Maps user intents to the right specialised AG2 skill
Ag2 Overview by the numbers
- 34 all-time installs (skills.sh)
- Ranked #8,855 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 1, 2026 (Skillselion catalog sync)
ag2-overview capabilities & compatibility
Free skill; building agents requires an LLM provider API key.
- Capabilities
- agent framework index · skill routing · onboarding
- Works with
- openai · anthropic
- Use cases
- orchestration · documentation
- Pricing
- Bring your own API key
What ag2-overview says it does
AG2 beta (`autogen.beta`) is an async, protocol-driven agent framework.
Anything you build with AG2 needs three things in place.
npx skills add https://github.com/ag2ai/ag2-skills --skill ag2-overviewAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 34 |
|---|---|
| repo stars | ★ 8 |
| Last updated | July 27, 2026 |
| Repository | ag2ai/ag2-skills ↗ |
What it does
Orient in AG2 beta and pick the right sibling skill when the specific feature to build is not yet clear.
Who is it for?
Developers starting with AG2 beta who do not yet know which feature skill they need.
Skip if: Projects not built on AG2 beta (autogen.beta).
When should I use this skill?
The user mentions building with AG2 beta (autogen.beta) but the specific feature is not yet clear.
What you get
The developer picks the correct AG2 skill and has the three setup prerequisites in place.
By the numbers
- 3 required setup steps (provider extra, API key, sanity-check)
- routes to a dozen-plus sibling AG2 skills
Files
AG2 Beta — capability map
AG2 beta (autogen.beta) is an async, protocol-driven agent framework. The full reference docs live under website/docs/beta/. This skill is the index of sibling skills that cover the common build paths.
When to use
Read this file first when a request mentions "AG2 beta", "autogen.beta", or building agents in this repo and you don't yet know which feature is needed. Use the table below to pick the right specialised skill, then load that skill's SKILL.md for the recipe.
Before you start
Anything you build with AG2 needs three things in place. Get these right once and the rest of the skills run cleanly:
1. Install the right provider extra — pip install "ag2[openai]", ag2[anthropic], ag2[gemini], etc. The *Config class will raise ImportError: ... requires optional dependencies without it. Run the install before delivering code. If you cannot run commands, state the exact pip install command. This is a required step. 2. Set the matching API key — OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY (or GOOGLE_API_KEY). Loading from a project-root .env via from dotenv import load_dotenv; load_dotenv() is the common pattern. 3. Sanity-check the install — python -c "import sys, autogen; print(sys.executable, autogen.__version__)". If you have multiple Python environments, this confirms which ag2 your script will actually import.
Full per-provider table (install + env var + config class) lives in ag2-quickstart → "Prerequisites".
Pick the right skill
| User intent | Skill | What it covers |
|---|---|---|
Build an Agent from scratch, pick a model | ag2-quickstart | Agent, ModelConfig, ask() / reply.ask() chaining, providers, env vars |
| Give the Agent a custom Python tool | ag2-add-custom-tool | @tool, sync/async, ToolResult, Context, Inject, Variable, Depends |
| Use shipped tools (web search, code exec, MCP, etc.) | ag2-use-builtin-tools | WebSearchTool, WebFetchTool, CodeExecutionTool, MCPServerTool, ImageGenerationTool, MemoryTool, FilesystemToolkit, DuckDuckSearchTool, ExaToolkit, TavilySearchTool |
| Run shell commands from an agent | ag2-shell-tool | SandboxShellTool + LocalEnvironment (any provider), provider-side ShellTool (OpenAI Responses), sandboxing (allowed/blocked/ignore/readonly) |
| Get typed Pydantic / dataclass output | ag2-structured-output | response_schema=, ResponseSchema, @response_schema, PromptedSchema, reply.content(), retries |
| Multi-agent: parallel subtasks or named delegates | ag2-subagent-delegation | tasks=TaskConfig(), run_subtasks(parallel=True), Agent.as_tool(), persistent_stream |
| Pause for human input or gate a tool with approval | ag2-hitl | context.input(), hitl_hook, approval_required() middleware |
| Logging, retry, history-trim, custom interception | ag2-middleware | BaseMiddleware, LoggingMiddleware, RetryMiddleware, HistoryLimiter, TokenLimiter, tool middleware |
| Test agents and tools | ag2-testing | TestConfig, mocking LLM responses, simulating ToolCallEvent |
| Evaluate / benchmark an agent offline, CI gate, scorers | ag2-evaluation | Suite, run_agent, final_answer_matches / tool_called / agent_judge, @scorer, RunResult, TestConfig, evaluate_traces, diff().regressions |
| Compare models / prompts — leaderboard or head-to-head | ag2-eval-comparison | run_variants (Variants({name: Agent}, axis=...)), run_pairwise + pairwise_judge (win-rate, Wilson CI, flips, κ), human_pairwise |
| Persistent memory across runs, history compaction, assembly | ag2-knowledge-and-memory | KnowledgeStore, KnowledgeConfig, WorkingMemoryAggregate, AssemblyPolicy, SlidingWindowPolicy, TokenBudgetPolicy, TailWindowCompact, SummarizeCompact |
| Observability, alerts, halts | ag2-observers-and-alerts | BaseObserver, TokenMonitor, LoopDetector, EventWatch, CadenceWatch, AlertPolicy, HaltEvent |
| Send images / audio / video / PDFs in | ag2-multimodal-input | ImageInput, AudioInput, VideoInput, DocumentInput, FilesAPI |
| Web frontend via the AG-UI protocol | ag2-ag-ui | AGUIStream, FastAPI mount, CopilotKit |
| Serve an agent as an MCP server (server side) | ag2-mcp | MCPServer, stdio / HTTP, prompts, resources, SessionConfig, AskContext |
| Expose an agent over the A2A protocol | ag2-a2a | A2AServer, build_jsonrpc / build_rest / build_grpc, AgentCard, A2AConfig (consume remote) |
| Realtime voice / live audio (talking agent, STT, TTS) | ag2-live | LiveAgent, GeminiRealTimeConfig / OpenAIRealTimeConfig, SoundDeviceRecorder / Player, OpenAITranscriber, TTSObserver |
| OpenTelemetry traces / metrics | ag2-telemetry | TelemetryMiddleware, GenAI semconv attributes, content capture |
Multi-agent networks
Whenever two or more agents need to interact, load `ag2-network-quickstart` first — the network is the standard multi-agent pattern in AG2 beta. It covers the Hub setup and the two 2-party channel adapters (consulting for strict 1Q1R and conversation for free-form). After the quickstart, route to the right deep-dive:
| User intent | Skill | What it covers |
|---|---|---|
| N-party round-robin / fixed turn order | ag2-network-discussion | discussion adapter, ORDERING_ROUND_ROBIN knob, can_send probe pattern, view-window sizing |
Declarative orchestration / TransitionGraph / GroupChat migration | ag2-network-workflow | workflow adapter, TransitionGraph.sequence / .round_robin, Handoff, ToolCalled, ContextEquals, context_vars, 8 cookbook patterns, classic-GroupChat migration |
| Rate limits, access policy, expectations, audit, capability tracking | ag2-network-governance | Rule (AccessBlock / LimitsBlock / RateBlock / InboxBlock), Expectations, audit log + AUDIT_KIND_*, task observation, Resume.observed |
| Custom envelope handlers, view policies, peer discovery, the LLM-facing network tools | ag2-network-tools-and-views | adapter-owned say + the five NetworkPlugin tools (delegate / peers / channels / tasks / context), agent_client.on_envelope, ViewPolicy (FullTranscript / WindowedSummary / NamedWindowedSummary), skill_md peer discovery, full Envelope / EV_* reference |
Not a network task: if the user has one agent recursively spawning its own sub-tasks (via run_subtask / run_subtasks(parallel=True)) or calling another agent as a lightweight tool, use `ag2-subagent-delegation` — no hub, no registry, no channels. The network is for distinct, registered agents collaborating through a shared hub.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What three things does every AG2 build need?
The right provider extra installed, the matching API key set, and a sanity-check of the install.
Where do two or more agents interacting start?
Load ag2-network-quickstart, the standard multi-agent pattern in AG2 beta.