mirror of
https://github.com/tcsenpai/agenticSeek.git
synced 2025-06-04 18:20:09 +00:00
update readme
This commit is contained in:
parent
564a09c96d
commit
9c9824c05e
@ -8,9 +8,9 @@ English | [中文](./README_CHS.md) | [繁體中文](./README_CHT.md) | [Franç
|
||||
# AgenticSeek: Manus-like AI powered by Deepseek R1 Agents.
|
||||
|
||||
|
||||
**A fully local alternative to Manus AI**, a voice-enabled AI assistant that codes, explores your filesystem, browse the web and correct it's mistakes all without sending a byte of data to the cloud. Built with reasoning models like DeepSeek R1, this autonomous agent runs entirely on your hardware, keeping your data private.
|
||||
**A 100% local alternative to Manus AI, this voice-enabled AI assistant autonomously browses the web, writes code, and plans tasks while keeping all data on your device. Powered by advanced reasoning models like DeepSeek R1, it runs entirely on your hardware, ensuring complete privacy and zero cloud dependency.**
|
||||
|
||||
[](https://fosowl.github.io/agenticSeek.html)  [](https://discord.gg/XSTKZ8nP) [](https://x.com/Martin993886460)
|
||||
[](https://fosowl.github.io/agenticSeek.html)  [](https://discord.gg/m37d7XxZ) [](https://x.com/Martin993886460)
|
||||
|
||||
> 🛠️ **Work in Progress** – Looking for contributors!
|
||||
|
||||
|
@ -9,7 +9,7 @@
|
||||
|
||||
**Manus AI 的本地替代品**,它是一个具有语音功能的大语言模型秘书,可以 Coding、访问你的电脑文件、浏览网页,并自动修正错误与反省,最重要的是不会向云端传送任何资料。采用 DeepSeek R1 等推理模型构建,完全在本地硬体上运行,进而保证资料的隐私。
|
||||
|
||||
[](https://fosowl.github.io/agenticSeek.html)  [](https://discord.gg/XSTKZ8nP) [](https://x.com/Martin993886460)
|
||||
[](https://fosowl.github.io/agenticSeek.html)  [](https://discord.gg/m37d7XxZ) [](https://x.com/Martin993886460)
|
||||
|
||||
> 🛠️ **目前还在开发阶段** – 欢迎任何贡献者加入我们!
|
||||
|
||||
|
@ -10,7 +10,7 @@
|
||||
|
||||
**Manus AI 的本地替代品**,它是一個具有語音功能的大語言模型秘書,可以 Coding、訪問你的電腦文件、瀏覽網頁,並自動修正錯誤與反省,最重要的是不會向雲端傳送任何資料。採用 DeepSeek R1 等推理模型構建,完全在本地硬體上運行,進而保證資料的隱私。
|
||||
|
||||
[](https://fosowl.github.io/agenticSeek.html)  [](https://discord.gg/XSTKZ8nP) [](https://x.com/Martin993886460)
|
||||
[](https://fosowl.github.io/agenticSeek.html)  [](https://discord.gg/m37d7XxZ) [](https://x.com/Martin993886460)
|
||||
|
||||
> 🛠️ **目前還在開發階段** – 歡迎任何貢獻者加入我們!
|
||||
|
||||
|
@ -9,7 +9,7 @@
|
||||
|
||||
Une alternative **entièrement locale** à Manus AI, un assistant IA qui code, explore votre système de fichiers, navigue sur le web et corrige ses erreurs, tout cela sans envoyer la moindre donnée dans le cloud. Cet agent autonome fonctionne entièrement sur votre hardware, garantissant la confidentialité de vos données.
|
||||
|
||||
[](https://fosowl.github.io/agenticSeek.html)  [](https://discord.gg/4Ub2D6Fj) [](https://x.com/Martin993886460)
|
||||
[](https://fosowl.github.io/agenticSeek.html)  [](https://discord.gg/m37d7XxZ) [](https://x.com/Martin993886460)
|
||||
|
||||
> 🛠️ **En cours de développement** – On cherche activement des contributeurs!
|
||||
|
||||
|
@ -10,7 +10,7 @@
|
||||
|
||||
**Manus AIの完全なローカル代替品**、音声対応のAIアシスタントで、コードを書き、ファイルシステムを探索し、ウェブを閲覧し、ミスを修正し、データをクラウドに送信することなくすべてを行います。DeepSeek R1のような推論モデルを使用して構築されており、この自律エージェントは完全にハードウェア上で動作し、データのプライバシーを保護します。
|
||||
|
||||
[](https://fosowl.github.io/agenticSeek.html)  [](https://discord.gg/XSTKZ8nP) [](https://x.com/Martin993886460)
|
||||
[](https://fosowl.github.io/agenticSeek.html)  [](https://discord.gg/m37d7XxZ) [](https://x.com/Martin993886460)
|
||||
|
||||
> 🛠️ **進行中の作業** – 貢献者を探しています!
|
||||
|
||||
|
@ -134,10 +134,14 @@ class PlannerAgent(Agent):
|
||||
while not ok:
|
||||
animate_thinking("Thinking...", color="status")
|
||||
self.memory.push('user', prompt)
|
||||
answer, _ = await self.llm_request()
|
||||
agents_tasks = self.parse_agent_tasks(answer)
|
||||
if "NO_UPDATE" in agents_tasks:
|
||||
answer, reasoning = await self.llm_request()
|
||||
print("LLM answer:")
|
||||
print(reasoning)
|
||||
print(answer)
|
||||
print("LLM answer end")
|
||||
if "NO_UPDATE" in answer:
|
||||
return []
|
||||
agents_tasks = self.parse_agent_tasks(answer)
|
||||
if agents_tasks == []:
|
||||
prompt = f"Failed to parse the tasks. Please make a plan within ```json.\n"
|
||||
pretty_print("Failed to make plan. Retrying...", color="warning")
|
||||
@ -156,31 +160,26 @@ class PlannerAgent(Agent):
|
||||
Returns:
|
||||
dict: The updated plan.
|
||||
"""
|
||||
#self.memory.clear()
|
||||
|
||||
last_agent_work = agents_work_result[id]
|
||||
tool_success_str = "success" if success else "failure"
|
||||
pretty_print(f"Agent {id} work {tool_success_str}.", color="success" if success else "failure")
|
||||
next_task = agents_tasks[int(id)][0]
|
||||
if success:
|
||||
return agents_tasks # we only update the plan if last task failed, for now
|
||||
#if success:
|
||||
# return agents_tasks # we only update the plan if last task failed, for now
|
||||
update_prompt = f"""
|
||||
Your goal was : {goal}
|
||||
Your goal is : {goal}
|
||||
You previously made a plan, agents are currently working on it.
|
||||
The last agent working on task: {id}, did the following work:
|
||||
{last_agent_work}
|
||||
But the agent {id} failed with the task.
|
||||
Agent {id} work was a {tool_success_str} according to system interpreter.
|
||||
The agent {id} about to work on task: {next_task}
|
||||
Is the work done for task {id} leading to sucess or failure ? Did an agent fail with a task?
|
||||
If agent work lead to success: answer "NO_UPDATE"
|
||||
If agent work lead might to failure: update the plan.
|
||||
If agent work was good: answer "NO_UPDATE"
|
||||
If agent work is leading to failure: update the plan.
|
||||
plan should be within ```json like before.
|
||||
You need to rewrite the whole plan, but only change the tasks after {id}.
|
||||
Keep the plan as short as the original one if possible.
|
||||
You need to rewrite the whole plan, but only change the tasks after task {id}.
|
||||
Keep the plan as short as the original one if possible. Do not change past tasks.
|
||||
"""
|
||||
print("PROMPT")
|
||||
print(update_prompt)
|
||||
print("END PROMPT")
|
||||
pretty_print("Updating plan...", color="status")
|
||||
plan = await self.make_plan(update_prompt)
|
||||
if plan == []:
|
||||
|
Loading…
x
Reference in New Issue
Block a user