LibreAI / AI Agents / ai-berkshire
// agents · xbtlin/ai-berkshire

ai-berkshire

ai-berkshire is an open-source ai agents project by xbtlin (xbtlin/ai-berkshire on GitHub). It has 16,605 GitHub stars and 2,473 forks, is released under the MIT license, and was last updated on GitHub on 27 September 2026.

AI 时代的伯克希尔:基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code /…

★ 16.6k stars⑂ 2.5k forksMITupdated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
// project facts

Project facts

GitHub stars
16,605
Forks
2,473
License
MIT
Last updated on GitHub
27 September 2026
Category
AI Agents
Listing
Full install guide
Official site
GitHub repo
// how it works

How it works

  1. Define the job

    Research, coding, browsing, or ops — agents work best with a clear goal.

  2. Pick a framework

    From no-code builders to code-first SDKs, match complexity to the task.

  3. Give it tools

    Web search, code execution, and APIs are what make agents useful.

  4. Run and supervise

    Watch the trace, approve consequential actions, iterate.

// features

Why people love it

Human in the loop

Approval gates for actions that matter.

Memory

Long-term memory across sessions, not goldfish chat.

Multi-agent teams

Specialized agents collaborate on bigger jobs.

Tool use

Agents call real tools: browsers, terminals, APIs.

Evaluations

Benchmarks keep agent quality measurable.

Self-hosted

Run agents on your infra with your keys.

Advertisement
// run it

Run it yourself

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/xbtlin/ai-berkshire.git
    cd ai-berkshire
  2. Step 2 — Check the README

    Every project documents its own setup; start with install requirements.

    cat README.md | head -60
  3. Step 3 — Run it

    Follow the project's launch command — Docker, pip, npm, or a binary release.

    # see README for the exact launch command
// use cases

What you can build

  • Automate deep research tasks.
  • Let agents write and test code.
  • Build support bots that actually act.
  • Orchestrate multi-step business ops.
Advertisement
// faq

Questions, answered

Who maintains ai-berkshire?

It is an open-source project at xbtlin/ai-berkshire with 2,473 forks. Check the repo's contributors and recent commits to see how active maintenance is.

Is ai-berkshire free for commercial use?

MIT licensed — use it commercially, no strings attached.

How do I keep them safe?

Sandboxing, approval gates, and least-privilege credentials.

Do I need to code?

Builders exist, but code-first frameworks go further.

What does it cost to run?

Model API bills dominate; self-hosted stacks cut that sharply.

// keep exploring

Similar tools

AI Agents

mastra

Mastra is the modern TypeScript framework for AI-powered applications and agents.

★ 28.5k starsUnknown
View guide →
AI Agents

pest

The elegant testing framework for PHP developers and AI agents.

★ 11.7k starsMIT
View guide →
AI Agents

agent-squad

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

★ 7.8k starsApache-2.0
View guide →
AI Agents

holaOS

Local-first agentic workspace where Claude Code, Codex and a built-in agent share memory, apps and tools.

★ 11.5k starsModified Apache-2.0
View guide →
AI Agents

omnigent

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewrit…

★ 10.4k starsApache-2.0
View guide →
AI Agents

Product-Manager-Skills

Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.

★ 7.2k starsUnknown
View guide →
// alternatives

Alternatives in AI Agents

The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if ai-berkshire is not the right fit.

  • openclaw★ 391.6k

    A personal AI that really does things — on any OS, with your data staying yours.

  • superpowers★ 294.9k

    An agentic skills framework & software development methodology that works.

  • ECC★ 275.2k

    Agent harness optimization system with skills, memory and security for Claude Code, Codex and more

  • hermes-agent★ 252.0k

    The agent that grows with you — a Python framework for adaptive AI agents.

  • deepseek-harness★ 245.5k

    DeepSeek's plugin-based agent harness where everything is a plugin.

// more in agents

More in AI Agents

Nearby AI Agents projects in the catalogue, closest in stars to ai-berkshire — keep exploring the shelf either side of it.

  • mcp-toolbox★ 16.6k

    Google's MCP Toolbox for Databases - give agents safe, structured access to your data

  • memvid★ 16.6k

    A serverless, single-file memory layer for AI agents - replace complex RAG pipelines

  • weaviate★ 16.9k

    Vector search plus structured filtering in one database.

  • RagaAI-Catalyst★ 16.2k

    Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic syst…

  • openwiki★ 17.0k

    A CLI that writes and maintains agent-ready docs for your codebase.

  • Pipecat★ 16.2k

    Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community

Get ai-berkshire

Free and open — grab the source, star the repo, and start creating.