- tools: GoogleSearchTool has been removed as Google's Custom Search JSON API is
- adapters: add MiniMax regional (CN) endpoint selection (f1e1944)
- adapters: default MiniMax text models to M3.1 Flash (c31de98)
- adapters: deprecate the AgentStack integration (0d510d9)
- tools: add per-attempt timeout to tool run options (8369752), closes #1640 #1653
- tools: deprecate GoogleSearchTool (3eb123d)
BeeAI Framework by BeeAI (Linux Foundation)
An open-source framework for building production agents in Python and TypeScript, started at IBM Research.
Use it in: API / SDK Works with: MCP Local models Multi-agent
On this page
Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number
What BeeAI Framework does
BeeAI Framework is an agent framework from BeeAI, first released in August 2024. You use it through a Python library and a TypeScript library. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from OpenAI, Anthropic, Google, Amazon Bedrock, Azure and xAI and others. It is used from Python and TypeScript. It is free and open source (Apache-2.0); you pay only for the models it calls.
Key facts
| Maker | BeeAI (Linux Foundation) |
|---|---|
| Type | Agent framework |
| First released | August 2024 |
| License | Apache-2.0 |
| Interfaces | Python library, TypeScript library |
| Main language | Python |
| Open issues and PRs | 7 |
Pricing
BeeAI Framework 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.
Quick answers
- Free to start?Yes
- Open source?Yes (Apache-2.0)
- Where you use itPython library, TypeScript library
- Supports MCP?Yes
- Model providersopenai, anthropic, google, amazon, azure, xai, mistral, any OpenAI-compatible, local
- Subagents / multi-agent?Yes
- Feature comparisonAll agents
- Closest alternativeLangChain · all alternatives
What's new in BeeAI Framework: November 2026 so far
November brought dependency management improvements and several tool updates to the BeeAI Framework. The month focused on better integration configuration and removal of deprecated components.
- GoogleSearchTool has been removed due to API changes.
- MiniMax adapter now supports regional endpoint selection for China.
- Tool execution now supports per-attempt timeouts.
- Memory improvements now include tool calls and results in summarization.
2 releases this month · summarised from the official release notes · all months
Get started with BeeAI Framework
| npm | npm install beeai-framework |
|---|---|
| PyPI | pip install beeai-framework |
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Add-ons for BeeAI Framework: save tokens, add memory and tools
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for BeeAI Framework or for agent frameworks in general. Savings and results depend on your workload.
BeeAI Framework alternatives
Best BeeAI Framework alternatives compared · All agent frameworks and SDKs
| # | 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 |
Claude Agent SDKAnthropic |
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 |
OpenAI Agents SDKOpenAI |
62 | 7.2M | up 4.8% | up 38.9% | 30.8K+21/day | 0.25.02d ago | Free (OSS) | |||
Tools used with BeeAI Framework
What 39 public GitHub projects that depend on BeeAI Framework use with it, from their dependency files.
- python-dotenv48.7%
- Pydantic41.0%
- Uvicorn38.5%
- LangChain35.9%
- dotenv30.8%
- Requests30.8%
- TypeScript28.2%
- Zod28.2%
- OpenAI Python Library28.2%
- PyYAML28.2%
Used far more often here than in AI-built projects overall: what sets BeeAI Framework projects apart.
- Chevron20.5% · 1282.9×
- json-repair20.5% · 71.3×
- yarl20.5% · 55.8×
- tokenizers20.5% · 51.3×
- fsspec20.5% · 45.8×
- jiter20.5% · 45.8×
- LiteLLM23.1% · 40.1×
- orjson23.1% · 39.0×
Ratings from people who use BeeAI Framework
No ratings yet. Used BeeAI Framework? Rate it and say what it is good and bad at.
What changed: recent BeeAI Framework releases
5 stable releases in the last 90 days · Monthly summary · Full changelog
- beeai-framework[transformers] (and [all]) no longer installs torch, peft or
- adapters: report cached token usage in the LangChain chat adapter
- internals: accept any value for a JSON Schema property without a type
- memory: include tool calls and results in the SummarizeMemory prompt
- tools: keep MCP image and audio payloads out of the model text
- deps: install torch, peft and outlines with the transformers extra
Earlier releases
- tools: generate typed schemas for keyword-only parameters
- propagate Python stream errors and cancellation
- adapters: preserve LangChain image content
- adapters: apply LiteLLM proxy response cost reported via _hidden_params
- tools: preserve cache and middleware when cloning file and shell tools
- internals: carry the abort state through AbortController.clone
- infra: port Runnable interface to TypeScript (947cf31)
- memory: add DakeraMemory for persistent cross-session agent memory (f54c898)
- adapters: don't crash the process when a streamed Vercel chat call fails (cd5b5ea)
- adapters: make ChatModel.fromName and clone() work for Amazon Bedrock (f767f79)
- adapters: stop sending the default temperature to OpenAI GPT-5.x/GPT-6 on Amazon Bedrock (874a6ec)
- adapters: use constant-time API key comparison and anchored Bearer strip (d415ccb)
- fix(internals): compare both matrices' column counts in cosineSimilarityMatrix
- feat(memory): add DakeraMemory for persistent cross-session agent memory
- fix(examples): migrate basics_colab and agents_colab notebooks from granite3.3 to granite4.1:8b
- Feat/1479 OpenAI server
- feat(infra): port Runnable interface to TypeScript
- fix(docs): Remove reference to nonexistent docs:fix target
- emitter: keep an unset group_id unset when cloning
- adapters: support Responses API text content parts
- adapters: add default for max_request_body_size field added in mcp 1.29.0
- emitter: propagate errors from emitter
- adapters: propagate error context through _meta on MCP tool errors
- adapters: add streaming support to WatsonxOrchestrateAgent
BeeAI Framework prices over time
BeeAI Framework popularity and usage data
BeeAI Framework was downloaded 7,990 times from npm and PyPI in the week ending Nov 17, 2026, down 30.4% on the week before and up 11.8% over the last 30 days compared with the 30 before. The GitHub repository has 3,461 stars, 26 of them added in the last 30 days. The latest stable release is 0.1.32, published Nov 2, 2026; there were 2 stable releases in the past 30 days.
Download the raw daily series: beeai-framework.csv
Gid Score breakdown
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
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 17, 2026 | Nov 19, 06:24 UTC |
| GitHub stars | Nov 19, 2026 | Nov 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.
BeeAI Framework FAQ
How much does BeeAI Framework cost?
BeeAI Framework is open source and free to use; you pay only for the models and infrastructure it runs on.
Is BeeAI Framework open source?
Yes. BeeAI Framework is open source, released under the Apache-2.0 license.
How popular is BeeAI Framework?
BeeAI Framework was downloaded 7,990 times from npm and PyPI in the week ending Nov 17, 2026, down 30.4% on the week before and up 11.8% over the last 30 days compared with the 30 before. The GitHub repository has 3,461 stars, 26 of them added in the last 30 days. The latest stable release is 0.1.32, published Nov 2, 2026; there were 2 stable releases in the past 30 days.
What is the latest version of BeeAI Framework?
The latest stable release we track is 0.1.32, published on Nov 2, 2026.
What are the alternatives to BeeAI Framework?
The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.
For the makers of BeeAI Framework badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/beeai-framework/)
[](https://agentgid.com/agents/beeai-framework/)
[](https://agentgid.com/agents/beeai-framework/)
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
npm: beeai-framework. PyPI: beeai-framework. GitHub: i-am-bee/beeai-framework. See data sources for how each one is collected.