WHAT NEW IN X11.01 SUN

X 上的 AI 合集档案 · 22 个合集 · 63,170 条

gpt-6VIDEO

9 个仓库让 GPT-6 Astra 能控浏览器、写代码、跑任务

按「编排—执行—验证」分层列出 LangGraph、AutoGen、OpenHands、Promptfoo、Langfuse 等 9 个仓库,构成围绕 Astra 的 agent 架构。

Lummox
@Lummox_eth16 天前收录原推发布于 2026.10.14
Lummox @Lummox_eth原推发布于 2026.10.14
在 X 上打开原推

GitHub makes GPT 6 Astra dangerously capable AI that controls browsers, writes code, executes tasks only with these 9 repos 01 langchain-ai/langgraph ▸ https://github.com/langchain-ai/langgraph → checkpointed workflows that let agents pause, resume and recover instead of losing everything after one failed step THE AGENT IS DOING 5 JOBS AT ONCE 02 microsoft/autogen ▸ https://github.com/microsoft/autogen → multiagent conversations that distribute work between specialized agents 03 pydantic/pydantic-ai ▸ https://github.com/pydantic/pydantic-ai → typed dependencies, validated outputs and structured tool interfaces so workers return usable results THE MODEL CANNOT TOUCH REAL SOFTWARE 04 ComposioHQ/composio ▸ https://github.com/ComposioHQ/composio → authenticated tool integrations for letting agents interact with external applications 05 browser-use/browser-use ▸ https://github.com/browser-use/browser-use → browser automation for navigating websites, filling forms and completing web tasks THE AGENT CAN PLAN BUT CANNOT SHIP 06 All-Hands-AI/OpenHands ▸ https://github.com/All-Hands-AI/OpenHands → coding agents that operate inside development environments with files, commands and repositories 07 e2b-dev/E2B ▸ https://github.com/e2b-dev/E2B → isolated cloud sandboxes for executing generated code without direct host access THE OUTPUT LOOKS RIGHT BUT IS WRONG 08 promptfoo/promptfoo ▸ https://github.com/promptfoo/promptfoo → automated evaluations and adversarial tests that expose failures before deployment 09 langfuse/langfuse ▸ https://github.com/langfuse/langfuse → traces model calls, tool execution, costs and evaluations so you can inspect what actually happened the architecture I’d build around GPT 6 Astra these are independent building blocks that require integration, not a ready made stack the real advantage comes from making the system recoverable, observable and capable of doing actual work a smarter model can solve a harder problem a better execution system can finish the job when the first attempt fails

这条是引用着另一条写的:x.com/lummox_eth/status/2100288151897981255

x.com/lummox_eth/status/2110377694609215960采集于 2026.10.15 10:51