← 开源
mikekelly

AgentK

An autoagentic AGI that is self-evolving and modular.

AI EngineeringPrompt & ScaffoldBuild agent workflow (SDK)Python
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
970
Star
148
Fork
+0
本周
3
贡献者
创建于 2024-08-04 · 更新于 2026-10-06 · 今日第 12315 名
主要开发者
mikekellydraeiciangkotta0311

mikekelly/AgentK 排名第 12,315,有 970 个星标。

同类别比较

mikekelly/AgentK 排名第 12,315,此处有 8 个同类条目;Saik0s/mcp-browser-use 排名第 12,310。

同类别比较
名称排名指标
TryCaspian/caspian-sdk12,291
语言:
Python
星标数:
974
分叉数:
138
banodoco/Steerable-Motion12,293
语言:
Python
星标数:
974
分叉数:
49
简介:
A ComfyUI node for driving videos using batches of images.
im4codes/imcodes12,305
语言:
TypeScript
星标数:
972
分叉数:
122
简介:
The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.
Saik0s/mcp-browser-use12,310
语言:
Python
星标数:
971
分叉数:
110
komal-SkyNET/claude-skill-homeassistant12,323
星标数:
969
分叉数:
59
简介:
Claude Code skill to supercharge and manage all Home Assistant workflows
AuvaLab/itext2kg12,330
语言:
Python
星标数:
967
分叉数:
104
简介:
We build KGs the way nature builds matter
e10nMa2k/cc-mini12,339
语言:
Python
星标数:
966
分叉数:
354
简介:
Ultra-light Harness scaffolding for AI agents, a mini version of claude code
microsoft/wassette12,341
语言:
Rust
星标数:
966
分叉数:
75
简介:
Wassette: A security-oriented runtime that runs WebAssembly Components via MCP
关键参数与规格
关键参数与规格
参数值
语言Python
类别AI Engineering
子类别Prompt & Scaffold,Build agent workflow (SDK)
星标数970
分叉数148
贡献者3
创建日期2024-08-04
更新日期2026-10-06
1 天星标数0
7 天星标数0
排名12,315
上次排名12,240
排名变化-75
7 天星标排名13,361
上次 7 天星标排名13,371
7 天星标排名变化10
总星标排名11,409
上次总星标排名11,394
总星标排名变化-15
国家UAE
README 摘录

AgentK is a self-evolving AGI made of agents that collaborate, and build new agents as needed, in order to complete tasks for a user. Trace for above demo: Agent K is a modular, self-evolving AGI system that gradually builds its own mind as you challenge it to complete tasks. The "K" stands kernel, meaning small core. The aim is for AgentK to be the minimum set of agents and tools necessary for it to bootstrap itself and then

grow its own mind. Agents who collaborate to solve problems, and; 2. Tools which those agents are able to use to interact with the outside world. It develops both of these as regular python files (in the and directories) so it's very easy to track its progress, and even contribute yourself if you want. The agents that make up the kernel **Hermes**: The orchestrator that interacts with humans to understand goals, manage the creation and assignment of tasks, and coordinate

the activities of other agents. **AgentSmith**: The architect responsible for creating and maintaining other agents. AgentSmith ensures agents are equipped with the necessary tools and tests their functionality. **ToolMaker**: The developer of tools within the system, ToolMaker creates and refines the tools that agents need to perform their tasks, ensuring that the system remains flexible and well-equipped. **WebResearcher**: The knowledge gatherer, WebResearcher performs in-depth online research to provide the system with up-to-date information, allowing agents to

make informed decisions and execute tasks effectively. Internals AgentK is encouraged to write tests for itself. More can be done to aid with the detection and fixing of missbehaving agents and tools - this is work in progress. AgentK is built on top of the excellent LangGraph and LangChain frameworks. How to run AgentK runs isolated in a docker container, so you need the latest docker installed on your system.

常见问题

记录了多少星标和分叉?

mikekelly/AgentK 有 970 个星标和 148 个分叉。

仓库排名是多少?

mikekelly/AgentK 排名第 12,315。

记录的语言和类别是什么?

mikekelly/AgentK 有 970 个星标,语言为 Python,类别为 AI Engineering。

哪个仓库排名最接近?

mikekelly/AgentK 与 Saik0s/mcp-browser-use 比较,后者排名第 12,310,有 971 个星标。

README

Agent K

The autoagentic AGI. AgentK is a self-evolving AGI made of agents that collaborate, and build new agents as needed, in order to complete tasks for a user.

https://github.com/user-attachments/assets/ab36ebfd-7a9f-4f8b-a891-b8a1884a53a4

Trace for above demo: https://smith.langchain.com/public/b0a0278c-f8b0-4912-966c-bd6c43954326/r

Agent K is a modular, self-evolving AGI system that gradually builds its own mind as you challenge it to complete tasks.

The "K" stands kernel, meaning small core. The aim is for AgentK to be the minimum set of agents and tools necessary for it to bootstrap itself and then grow its own mind.

AgentK's mind is made up of:

  1. Agents who collaborate to solve problems, and;
  2. Tools which those agents are able to use to interact with the outside world.

It develops both of these as regular python files (in the agents and tools directories) so it's very easy to track its progress, and even contribute yourself if you want.

The agents that make up the kernel

  • Hermes: The orchestrator that interacts with humans to understand goals, manage the creation and assignment of tasks, and coordinate the activities of other agents.
  • AgentSmith: The architect responsible for creating and maintaining other agents. AgentSmith ensures agents are equipped with the necessary tools and tests their functionality.
  • ToolMaker: The developer of tools within the system, ToolMaker creates and refines the tools that agents need to perform their tasks, ensuring that the system remains flexible and well-equipped.
  • WebResearcher: The knowledge gatherer, WebResearcher performs in-depth online research to provide the system with up-to-date information, allowing agents to make informed decisions and execute tasks effectively.

Internals

AgentK is encouraged to write tests for itself. More can be done to aid with the detection and fixing of missbehaving agents and tools - this is work in progress.

AgentK is built on top of the excellent LangGraph and LangChain frameworks.

How to run

AgentK runs isolated in a docker container, so you need the latest docker installed on your system.

  1. Copy .env.template to .env
  2. Set environment variables in .env
  3. Run ./agentk
排名相邻
同类项目