部署本项目需要具备一定的基础：Linux基础、需要安装好Anaconda/Miniforge（Python可以不装好，直接新建虚拟环境的时候装好即可），如果不装Anaconda或者Miniforge，只装过Python，需要确保Python是3.12（目前官网是这么推荐的），如果你没玩过Ollama，建议玩玩，参考链接：使用ollama本地跑大模型
其实步骤非常简单，只需要按照官网一步一步来即可！
我的电脑遇到了个小问题，可以参考如下链接的方式一解决：
git报错：error: RPC failed； curl 16 Error in the HTTP2 framing layer
如果想要使用本地的Ollama，可以使用以下配置：
# Global LLM configuration
[llm]
model = "qwq:32b"
base_url = "http://localhost:11434/v1"
api_key = "ollama"
max_tokens = 4096
temperature = 0.7
# Optional configuration for specific LLM models
[llm.vision]
model = "qwq:32b"
base_url = "http://localhost:11434/v1"
api_key = "ollama"
说明：
1、本地 Ollama 不需要 API Key，但是api_key参数需要填写“ollama”;
2、model名直接使用ollama list可以查看到，比如我拥有的模型是：
(base) ☁ ~ ollama list
NAME ID SIZE MODIFIED
qwq:32b cc1091b0e276 19 GB 25 hours ago
deepseek-r1:32b 38056bbcbb2d 19 GB 3 weeks ago
deepseek-r1:14b ea35dfe18182 9.0 GB 3 weeks ago
llama3:70b be39eb53a197 39 GB 10 months ago
llama2-chinese:13b 990f930d55c5 7.4 GB 14 months ago
需要改成自己对应的模型（PS：上面的qwq不行…继续往下看先…）
运行关键步骤：
(open_manus) ☁ OpenManus [main] ⚡ python main.py
INFO [browser_use] BrowserUse logging setup complete with level info
INFO [root] Anonymized telemetry enabled. See https://docs.browser-use.com/development/telemetry for more information.
Enter your prompt (or 'exit' to quit):
输入你的prompt：分析最近3个月AI相关的重要开源项目，并提供star排名
可以发现，3分钟后报了超时！但是程序程序依然在跑…
官网说需要使用千问的模型：
https://github.com/mannaandpoem/OpenManus/issues/85
难道我这新出的不算？！
我把模型改成了deepseek-r1:14b，报错了：
Enter your prompt (or 'exit' to quit): 分析最近3个月AI相关的重要开源项目，并提供star排名
2025-03-08 10:43:17.290 | WARNING | __main__:main:15 - Processing your request...
2025-03-08 10:43:17.291 | INFO | app.agent.base:run:137 - Executing step 1/30
2025-03-08 10:43:17.342 | ERROR | app.llm:ask_tool:262 - API error: Error code: 400 - {'error': {'message': 'registry.ollama.ai/library/deepseek-r1:14b does not support tools', 'type': 'api_error', 'param':
None, 'code': None}}
2025-03-08 10:43:18.368 | ERROR | app.llm:ask_tool:262 - API error: Error code: 400 - {'error': {'message': 'registry.ollama.ai/library/deepseek-r1:14b does not support tools', 'type': 'api_error', 'param':
None, 'code': None}}
2025-03-08 10:43:19.736 | ERROR | app.llm:ask_tool:262 - API error: Error code: 400 - {'error': {'message': 'registry.ollama.ai/library/deepseek-r1:14b does not support tools', 'type': 'api_error', 'param':
None, 'code': None}}
2025-03-08 10:43:21.249 | ERROR | app.llm:ask_tool:262 - API error: Error code: 400 - {'error': {'message': 'registry.ollama.ai/library/deepseek-r1:14b does not support tools', 'type': 'api_error', 'param':
None, 'code': None}}
2025-03-08 10:43:23.572 | ERROR | app.llm:ask_tool:262 - API error: Error code: 400 - {'error': {'message': 'registry.ollama.ai/library/deepseek-r1:14b does not support tools', 'type': 'api_error', 'param':
None, 'code': None}}
那就是我模型的问题？！
继续尝试下载了小的qwen模型
再下载个qwen2.5模型：
ollama run qwen2.5:14b
再重新执行OpenManus项目，发现已经跑起来了：
跑了20分钟后就报API error:Request timed out了：
此时，可以根据提示，执行playwright install命令：
(open_manus) ☁ OpenManus [main] ⚡ playwright install
Downloading Chromium 131.0.6778.33 (playwright build v1148) from https://playwright.azureedge.net/builds/chromium/1148/chromium-mac-arm64.zip
121.6 MiB [====================] 100% 0.0s
Chromium 131.0.6778.33 (playwright build v1148) downloaded to /Users/shaonaiyi/Library/Caches/ms-playwright/chromium-1148
Downloading Chromium Headless Shell 131.0.6778.33 (playwright build v1148) from https://playwright.azureedge.net/builds/chromium/1148/chromium-headless-shell-mac-arm64.zip
77.5 MiB [====================] 100% 0.0s
Chromium Headless Shell 131.0.6778.33 (playwright build v1148) downloaded to /Users/shaonaiyi/Library/Caches/ms-playwright/chromium_headless_shell-1148
Downloading Firefox 132.0 (playwright build v1466) from https://playwright.azureedge.net/builds/firefox/1466/firefox-mac-arm64.zip
81.6 MiB [====================] 100% 0.0s
Firefox 132.0 (playwright build v1466) downloaded to /Users/shaonaiyi/Library/Caches/ms-playwright/firefox-1466
Downloading Webkit 18.2 (playwright build v2104) from https://playwright.azureedge.net/builds/webkit/2104/webkit-mac-13-arm64.zip
69.5 MiB [====================] 100% 0.0s
Webkit 18.2 (playwright build v2104) downloaded to /Users/shaonaiyi/Library/Caches/ms-playwright/webkit-2104
Downloading FFMPEG playwright build v1010 from https://playwright.azureedge.net/builds/ffmpeg/1010/ffmpeg-mac-arm64.zip
1.1 MiB [====================] 100% 0.0s
FFMPEG playwright build v1010 downloaded to /Users/shaonaiyi/Library/Caches/ms-playwright/ffmpeg-1010
(open_manus) ☁ OpenManus [main] ⚡
附配置文件：
# Global LLM configuration
[llm]
# model = "qwq:32b"
model = "qwen2.5:14b"
base_url = "http://localhost:11434/v1"
api_key = "ollama"
max_tokens = 4096
temperature = 0.7
# Optional configuration for specific LLM models
[llm.vision]
# model = "qwq:32b"
model = "qwen2.5:14b"
base_url = "http://localhost:11434/v1"
api_key = "ollama"
再来一个任务尝试，prompt如下：
打开edge浏览器，搜索“邵奈一”，打开他的CSDN博客，查找他最新发布的两篇文章，并在当前文件夹新建一个txt文件，将结果写入到此文件中
其实并没有生成相应的文件。。。
更新：博客发布的短短几个小时内，官网仓库又更新了不少地方，此时可以使用git pull拉取最新代码，然后继续尝试。
显示如下：
(base) ☁ OpenManus [main] ⚡ git pull
remote: Enumerating objects: 112, done.
remote: Counting objects: 100% (45/45), done.
remote: Compressing objects: 100% (28/28), done.
remote: Total 112 (delta 25), reused 21 (delta 17), pack-reused 67 (from 2)
Receiving objects: 100% (112/112), 430.62 KiB | 171.00 KiB/s, done.
Resolving deltas: 100% (40/40), completed with 3 local objects.
From https://github.com/mannaandpoem/OpenManus
d9e6e9a..5694a5e main -> origin/main
Updating d9e6e9a..5694a5e
Fast-forward
.github/ISSUE_TEMPLATE/config.yaml | 4 +
.github/ISSUE_TEMPLATE/request_new_features.md | 14 +++
.github/ISSUE_TEMPLATE/show_me_the_bug.md | 25 +++++
.github/PULL_REQUEST_TEMPLATE.md | 17 +++
.github/workflows/build-package.yaml | 33 ++++++
.github/workflows/pre-commit.yaml | 26 +++++
.github/workflows/stale.yaml | 23 ++++
.pre-commit-config.yaml | 8 +-
README.md | 42 ++++---
README_zh.md | 40 ++++---
app/agent/toolcall.py | 2 +-
app/config.py | 2 +-
app/llm.py | 8 +-
app/logger.py | 2 +-
app/tool/file_saver.py | 2 -
assets/community_group.jpg | Bin 0 -> 222392 bytes
assets/community_group_10.jpg | Bin 172852 -> 0 bytes
assets/community_group_9.jpg | Bin 169484 -> 0 bytes
config/config.example.toml | 2 +-
examples/japan-travel-plan/japan_travel_guide_instructions.txt | 62 +++++++++++
examples/japan-travel-plan/japan_travel_handbook.html | 124 +++++++++++++++++++++
examples/japan-travel-plan/japan_travel_handbook_mobile.html | 255 +++++++++++++++++++++++++++++++++++++++++++
examples/japan-travel-plan/japan_travel_handbook_print.html | 162 +++++++++++++++++++++++++++
examples/pictures/japan-travel-plan-1.png | Bin 0 -> 168010 bytes
examples/pictures/japan-travel-plan-2.png | Bin 0 -> 36336 bytes
examples/readme.md | 14 +++
main.py | 3 +
run_flow.py | 19 ++--
setup.py | 3 +-
29 files changed, 835 insertions(+), 57 deletions(-)
create mode 100644 .github/ISSUE_TEMPLATE/config.yaml
create mode 100644 .github/ISSUE_TEMPLATE/request_new_features.md
create mode 100644 .github/ISSUE_TEMPLATE/show_me_the_bug.md
create mode 100644 .github/PULL_REQUEST_TEMPLATE.md
create mode 100644 .github/workflows/build-package.yaml
create mode 100644 .github/workflows/pre-commit.yaml
create mode 100644 .github/workflows/stale.yaml
create mode 100644 assets/community_group.jpg
delete mode 100644 assets/community_group_10.jpg
delete mode 100644 assets/community_group_9.jpg
create mode 100644 examples/japan-travel-plan/japan_travel_guide_instructions.txt
create mode 100644 examples/japan-travel-plan/japan_travel_handbook.html
create mode 100644 examples/japan-travel-plan/japan_travel_handbook_mobile.html
create mode 100644 examples/japan-travel-plan/japan_travel_handbook_print.html
create mode 100644 examples/pictures/japan-travel-plan-1.png
create mode 100644 examples/pictures/japan-travel-plan-2.png
create mode 100644 examples/readme.md
(base) ☁ OpenManus [main] ⚡
Prompt：
编写一份关于OpenManus教学的一天课程大纲，要求有基础、有进阶、有实战三部分，要求大纲中每一小节要有包含的所讲的内容，要求生成后在当前路径下提供一个word文档。
