Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

AG2

A community-driven continuation of the original AutoGen codebase, maintained as an open-source multi-agent framework.

Agent frameworks and SDKs Multi-agent frameworkOpen source · Apache-2.0Free to start

Use it in: API / SDK Works with: MCP Local models Multi-agent

Price
Free (OSS)
free and open source
Popularity
#26 in Frameworks
Gid Score 38 / 100 · #26 of 50 ranked frameworks and SDKs
Trend
Growing fast
downloads up 38.0% over 30 days · down 4.6% last week
Development
Actively updated
latest 1.3.2, 5d ago
Community
5,076 GitHub stars
56.2K package downloads a week

Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number

What AG2 does

AG2 is a multi-agent framework from AG2, first released in November 2024. You use it through a Python library. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from OpenAI, Anthropic and Google. It is used from Python. It is free and open source (Apache-2.0); you pay only for the models it calls.

Key facts

MakerAG2
TypeMulti-agent framework
First releasedNovember 2024
LicenseApache-2.0
InterfacesPython library
Main languagePython
Open issues and PRs85

Pricing

AG2 is open source and free to use; you pay only for the models and infrastructure it runs on.

Checked Nov 4, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (Apache-2.0)
  • Where you use itPython library
  • Supports MCP?Yes
  • Model providersopenai, anthropic, google, local
  • Subagents / multi-agent?Yes
  • Feature comparisonAll agents
  • Closest alternativeLangChain · all alternatives

What's new in AG2: November 2026 so far

Full monthly summary

November brought sandbox backend options, improved token tracking and message handling, and better support for browser-based MCP hosts. The release focused on reliability, correctness, and expanded deployment flexibility.

  • New sandbox backends: E2B cloud sandboxes and boxd Linux microVMs now available for SandboxShellTool and SandboxCodeTool.
  • Token accounting fixed: cache reads and writes are now tracked separately and correctly counted within prompt tokens.
  • Message integrity restored: message chunks no longer run together, and more content survives including text, blobs, and tool result structure.
  • MCP Apps work with browser hosts: removed POST redirects and added CORS support with documentation.

3 releases this month · summarised from the official release notes · all months

AgentGid articles about AG2

All guides

Get started with AG2

PyPIpip install ag2

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Add-ons for AG2: save tokens, add memory and tools

All agent tooling

Listed because each tool documents support for AG2 or for agent frameworks in general. Savings and results depend on your workload.

Compare AG2 with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
1
LangChainLangChain
79 41.1M up 5.7% down 2.7% 150K+76/day 1.5.22d ago Free (OSS)
2
LangGraphLangChain
75 20.1M up 5.5% up 29.2% 45.1K+48/day 1.2.23yesterday Free (OSS)
3
AI SDKVercel
68 47.2M up 3.9% up 38.4% 28.1K+30/day 7.0.1772d ago Free (OSS)
4 64 29.3M up 5.9% up 37.6% 8,588+9/day 0.2.185yesterday Free (OSS)
5
MastraMastra
63 3.7M up 14.9% up 49.9% 29.6K+23/day 1.84.02d ago Free (OSS)
6 62 7.2M up 4.8% up 38.9% 30.8K+21/day 0.25.02d ago Free (OSS)

Tools used with AG2

All tools

What 39 public GitHub projects that depend on AG2 use with it, from their dependency files.

  1. OpenAI Python Library76.9%
  2. python-dotenv71.8%
  3. Pydantic69.2%
  4. NumPy66.7%
  5. Pillow66.7%
  6. FastAPI66.7%
  7. aiohttp64.1%
  8. LangChain61.5%
  9. pandas61.5%
  10. Requests59.0%

Used far more often here than in AI-built projects overall: what sets AG2 projects apart.

  1. Asyncer48.7% · 3046.8×
  2. jsonref53.8% · 1122.5×
  3. DiskCache53.8% · 336.8×
  4. mpmath51.3% · 229.1×
  5. FlatBuffers46.2% · 222.0×
  6. docstring-parser43.6% · 209.7×
  7. Docker Python53.8% · 177.2×
  8. IPython46.2% · 169.8×

Ratings from people who use AG2

No ratings yet. Used AG2? Rate it and say what it is good and bad at.

  1. Release GitHub Releases

    AG2 1.3.2 released

    prompt_tokens is the whole input, including cache reads and writes;; cache_read_input_tokens and cache_creation_input_tokens are parts of it, never additions;; total_tokens >= prompt_tokens + completion_tokens.

    AG2
  2. Release GitHub Releases

    AG2 1.3.1 released

    New sandbox backends for SandboxShellTool and SandboxCodeTool: E2BEnvironment (ag2.extensions.e2b) runs them in E2B cloud sandboxes, and ag2.extensions.boxd runs them on boxd Linux microVMs.; MCP Apps work with browser-based hosts: /mcp no longer redirects…

    AG2

What changed: recent AG2 releases

13 stable releases in the last 90 days · Monthly summary · Full changelog

1.3.2
  • prompt_tokens is the whole input, including cache reads and writes;
  • cache_read_input_tokens and cache_creation_input_tokens are parts of it, never additions;
  • total_tokens >= prompt_tokens + completion_tokens.
  • Messages stay separate. Before, every message chunk of a turn was joined into one string, so two messages ran together ("Let me check.Done.").
  • More content survives. Text and blob resources, resource links, and the structure of tool results are no longer dropped.
  • Sessions close cleanly. A session left open when the event loop shuts down no longer fails with asynchronous generator is already running, so ClaudeCodeConfig and the other client configs work…
1.3.1
  • New sandbox backends for SandboxShellTool and SandboxCodeTool: E2BEnvironment (ag2.extensions.e2b) runs them in E2B cloud sandboxes, and ag2.extensions.boxd runs them on boxd Linux microVMs.
  • MCP Apps work with browser-based hosts: /mcp no longer redirects POST and the CORS preflight, and the docs include a CORS recipe.
  • Extended prompt-cache writes are reported separately: Usage.cache_creation_extended_input_tokens counts OpenAI 12h and Anthropic 1h writes, which are priced differently.
  • XAIConfig accepts safety_identifier and guidelines.
  • Fixes for the AG-UI final reply after ToolResult(..., final=True), OpenAI-compatible streamed tool calls without an index, Gemini 3 thought_signature errors, recursive find_files patterns on…
  • ag2.eval, ag2/agent.py, ag2/extensions and most core modules are now checked with strict mypy.
Earlier releases
1.3.0
  • Mistral realtime TTS sends a reply's text over one connection per reply. Documentation.
  • Gemini's automatic_continuation controls resumption of responses that reach the per-request token limit. Documentation.
  • MCP's max_sse_event_size configures the maximum accepted event size for tool results. Documentation.
  • TrackingConfig captures the complete ordered model input for each call. Documentation.
  • A2A reconnect recovery, artifact reconciliation, and cancellation racing completion. Client guide.
  • Local command cleanup now stops child processes on cancellation, timeout, and close. Local Shell.
1.2.2
  • Timeouts for code that can hang: @tool(timeout=...) limits each function tool call, and timeout= on stream subscribers, @observer, BaseObserver, LoopDetector and TokenMonitor limits each callback.
  • Anthropic SDK 2.x support, plus new AnthropicConfig options: a typed speed and open_telemetry to configure or disable the SDK's own OpenTelemetry spans.
  • OpenAIDecisionsConfig accepts question_instructions (strings, ag2 inputs or SDK parts), appended to the agent prompt.
  • A2UI v1.0 updated to the current spec, including callAgentFunction / agentFunctionResponse and renderer capabilities.
  • New Glasser paid-data toolkit extension.
  • More accurate token usage: Anthropic continuation tokens, Gemini thinking tokens and xAI reasoning tokens are now counted, and OpenAI cache_write_tokens maps to cache_creation_input_tokens.
1.2.1
  • Mistral voice for ag2.live: offline and realtime speech-to-text (MistralTranscriber, MistralRealtimeTranscriber) and text-to-speech (MistralTTSConfig, MistralStreamingTTSConfig), on top of…
  • OpenAIResponsesConfig accepts a reasoning option for effort and summaries.
  • New search toolkits: FirecrawlToolkit and KeenableSearchToolkit.
  • New compaction_verifier extension: measures whether a CompactStrategy makes the agent's next actions worse, not just how many tokens it saves.
  • TypeSafe can locate objects in images: ResponseSchema(BoundingBox) sends a Box question.
  • ACP and the network layer keep multimodal input parts instead of flattening them to text.
1.2.0
  • OpenAI Decisions API support with OpenAIDecisionsConfig and shared decision schemas using the Question marker.
  • A2A servers can run on multiple replicas, with cacheable agent cards, opt-in input media type validation, and configurable push notification URL validation.
  • Anthropic cache diagnostics and explicit API keys for OpenAI voice configs.
  • Ollama API keys, custom HTTP clients, tool names, and fixes for duplicate streaming tool-call IDs.
  • Fixes for MCP discovery, knowledge stores, evaluation suite loading, skills, A2UI, and network graph loading.
  • docs(ag-ui): update CopilotKit quickstart for the AG-UI 1.0 sample

AG2 prices over time

Token prices of OpenAI modelsnewest OpenAI model in each family, output price per 1M tokens
OpenAI FlagshipOpenAI Mini

AG2 popularity and usage data

AG2 was downloaded 56.2K times from PyPI in the week ending Nov 17, 2026, down 4.6% on the week before and up 38.0% over the last 30 days compared with the 30 before. The GitHub repository has 5,076 stars, 83 of them added in the last 30 days. The latest stable release is 1.3.2, published Nov 15, 2026; there were 5 stable releases in the past 30 days.

Downloads per dayPyPI, 7-day average 8,035/day
GitHub starsrunning total 5,076

Download the raw daily series: ag2.csv

Gid Score breakdown

Adoption39
Community29
Attention—
Momentum69

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 17, 2026Nov 19, 06:24 UTC
GitHub starsNov 19, 2026Nov 19, 06:26 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

AG2 FAQ

How much does AG2 cost?

AG2 is open source and free to use; you pay only for the models and infrastructure it runs on.

Is AG2 open source?

Yes. AG2 is open source, released under the Apache-2.0 license.

How popular is AG2?

AG2 was downloaded 56.2K times from PyPI in the week ending Nov 17, 2026, down 4.6% on the week before and up 38.0% over the last 30 days compared with the 30 before. The GitHub repository has 5,076 stars, 83 of them added in the last 30 days. The latest stable release is 1.3.2, published Nov 15, 2026; there were 5 stable releases in the past 30 days.

What is the latest version of AG2?

The latest stable release we track is 1.3.2, published on Nov 15, 2026.

What are the alternatives to AG2?

The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.

For the makers of AG2 badges, corrections

Add a live badge to your README or site:

AgentGid: #26 in Frameworks Gid Score: 38/100 downloads: 56.2K/week ▲38% 30d

[![AgentGid: #26 in Frameworks](https://agentgid.com/badges/ag2-rank.svg)](https://agentgid.com/agents/ag2/)
[![Gid Score: 38/100](https://agentgid.com/badges/ag2-score.svg)](https://agentgid.com/agents/ag2/)
[![downloads: 56.2K/week ▲38% 30d](https://agentgid.com/badges/ag2-downloads.svg)](https://agentgid.com/agents/ag2/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

PyPI: ag2. GitHub: ag2ai/ag2. See data sources for how each one is collected.