lybic-guiagents 0.1.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of lybic-guiagents might be problematic. Click here for more details.

Files changed (101) hide show
  1. lybic_guiagents-0.1.0/LICENSE +201 -0
  2. lybic_guiagents-0.1.0/PKG-INFO +416 -0
  3. lybic_guiagents-0.1.0/README.md +319 -0
  4. lybic_guiagents-0.1.0/desktop_env/__init__.py +1 -0
  5. lybic_guiagents-0.1.0/desktop_env/actions.py +203 -0
  6. lybic_guiagents-0.1.0/desktop_env/controllers/__init__.py +0 -0
  7. lybic_guiagents-0.1.0/desktop_env/controllers/python.py +471 -0
  8. lybic_guiagents-0.1.0/desktop_env/controllers/setup.py +882 -0
  9. lybic_guiagents-0.1.0/desktop_env/desktop_env.py +509 -0
  10. lybic_guiagents-0.1.0/desktop_env/evaluators/__init__.py +5 -0
  11. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/__init__.py +41 -0
  12. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/calc.py +15 -0
  13. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/chrome.py +1774 -0
  14. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/file.py +154 -0
  15. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/general.py +42 -0
  16. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/gimp.py +38 -0
  17. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/impress.py +126 -0
  18. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/info.py +24 -0
  19. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/misc.py +406 -0
  20. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/replay.py +20 -0
  21. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/vlc.py +86 -0
  22. lybic_guiagents-0.1.0/desktop_env/evaluators/getters/vscode.py +35 -0
  23. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/__init__.py +160 -0
  24. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/basic_os.py +68 -0
  25. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/chrome.py +493 -0
  26. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/docs.py +1011 -0
  27. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/general.py +665 -0
  28. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/gimp.py +637 -0
  29. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/libreoffice.py +28 -0
  30. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/others.py +92 -0
  31. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/pdf.py +31 -0
  32. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/slides.py +957 -0
  33. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/table.py +585 -0
  34. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/thunderbird.py +176 -0
  35. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/utils.py +719 -0
  36. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/vlc.py +524 -0
  37. lybic_guiagents-0.1.0/desktop_env/evaluators/metrics/vscode.py +283 -0
  38. lybic_guiagents-0.1.0/desktop_env/providers/__init__.py +35 -0
  39. lybic_guiagents-0.1.0/desktop_env/providers/aws/__init__.py +0 -0
  40. lybic_guiagents-0.1.0/desktop_env/providers/aws/manager.py +278 -0
  41. lybic_guiagents-0.1.0/desktop_env/providers/aws/provider.py +186 -0
  42. lybic_guiagents-0.1.0/desktop_env/providers/aws/provider_with_proxy.py +315 -0
  43. lybic_guiagents-0.1.0/desktop_env/providers/aws/proxy_pool.py +193 -0
  44. lybic_guiagents-0.1.0/desktop_env/providers/azure/__init__.py +0 -0
  45. lybic_guiagents-0.1.0/desktop_env/providers/azure/manager.py +87 -0
  46. lybic_guiagents-0.1.0/desktop_env/providers/azure/provider.py +207 -0
  47. lybic_guiagents-0.1.0/desktop_env/providers/base.py +97 -0
  48. lybic_guiagents-0.1.0/desktop_env/providers/gcp/__init__.py +0 -0
  49. lybic_guiagents-0.1.0/desktop_env/providers/gcp/manager.py +0 -0
  50. lybic_guiagents-0.1.0/desktop_env/providers/gcp/provider.py +0 -0
  51. lybic_guiagents-0.1.0/desktop_env/providers/virtualbox/__init__.py +0 -0
  52. lybic_guiagents-0.1.0/desktop_env/providers/virtualbox/manager.py +463 -0
  53. lybic_guiagents-0.1.0/desktop_env/providers/virtualbox/provider.py +124 -0
  54. lybic_guiagents-0.1.0/desktop_env/providers/vmware/__init__.py +0 -0
  55. lybic_guiagents-0.1.0/desktop_env/providers/vmware/manager.py +455 -0
  56. lybic_guiagents-0.1.0/desktop_env/providers/vmware/provider.py +105 -0
  57. lybic_guiagents-0.1.0/gui_agents/__init__.py +0 -0
  58. lybic_guiagents-0.1.0/gui_agents/agents/Action.py +209 -0
  59. lybic_guiagents-0.1.0/gui_agents/agents/__init__.py +0 -0
  60. lybic_guiagents-0.1.0/gui_agents/agents/agent_s.py +832 -0
  61. lybic_guiagents-0.1.0/gui_agents/agents/global_state.py +610 -0
  62. lybic_guiagents-0.1.0/gui_agents/agents/grounding.py +651 -0
  63. lybic_guiagents-0.1.0/gui_agents/agents/hardware_interface.py +129 -0
  64. lybic_guiagents-0.1.0/gui_agents/agents/manager.py +568 -0
  65. lybic_guiagents-0.1.0/gui_agents/agents/translator.py +132 -0
  66. lybic_guiagents-0.1.0/gui_agents/agents/worker.py +355 -0
  67. lybic_guiagents-0.1.0/gui_agents/cli_app.py +560 -0
  68. lybic_guiagents-0.1.0/gui_agents/core/__init__.py +0 -0
  69. lybic_guiagents-0.1.0/gui_agents/core/engine.py +1496 -0
  70. lybic_guiagents-0.1.0/gui_agents/core/knowledge.py +449 -0
  71. lybic_guiagents-0.1.0/gui_agents/core/mllm.py +555 -0
  72. lybic_guiagents-0.1.0/gui_agents/tools/__init__.py +0 -0
  73. lybic_guiagents-0.1.0/gui_agents/tools/tools.py +727 -0
  74. lybic_guiagents-0.1.0/gui_agents/unit_test/__init__.py +0 -0
  75. lybic_guiagents-0.1.0/gui_agents/unit_test/run_tests.py +65 -0
  76. lybic_guiagents-0.1.0/gui_agents/unit_test/test_manager.py +330 -0
  77. lybic_guiagents-0.1.0/gui_agents/unit_test/test_worker.py +269 -0
  78. lybic_guiagents-0.1.0/gui_agents/utils/__init__.py +0 -0
  79. lybic_guiagents-0.1.0/gui_agents/utils/analyze_display.py +301 -0
  80. lybic_guiagents-0.1.0/gui_agents/utils/common_utils.py +263 -0
  81. lybic_guiagents-0.1.0/gui_agents/utils/display_viewer.py +281 -0
  82. lybic_guiagents-0.1.0/gui_agents/utils/embedding_manager.py +53 -0
  83. lybic_guiagents-0.1.0/gui_agents/utils/image_axis_utils.py +27 -0
  84. lybic_guiagents-0.1.0/lybic_guiagents.egg-info/PKG-INFO +416 -0
  85. lybic_guiagents-0.1.0/lybic_guiagents.egg-info/SOURCES.txt +99 -0
  86. lybic_guiagents-0.1.0/lybic_guiagents.egg-info/dependency_links.txt +1 -0
  87. lybic_guiagents-0.1.0/lybic_guiagents.egg-info/requires.txt +86 -0
  88. lybic_guiagents-0.1.0/lybic_guiagents.egg-info/top_level.txt +2 -0
  89. lybic_guiagents-0.1.0/pyproject.toml +101 -0
  90. lybic_guiagents-0.1.0/setup.cfg +4 -0
  91. lybic_guiagents-0.1.0/setup.py +33 -0
  92. lybic_guiagents-0.1.0/tests/test_aci.py +40 -0
  93. lybic_guiagents-0.1.0/tests/test_app_switching.py +25 -0
  94. lybic_guiagents-0.1.0/tests/test_global_instance.py +48 -0
  95. lybic_guiagents-0.1.0/tests/test_hardware_interface.py +67 -0
  96. lybic_guiagents-0.1.0/tests/test_registry.py +43 -0
  97. lybic_guiagents-0.1.0/tests/test_translator.py +47 -0
  98. lybic_guiagents-0.1.0/tests/test_uielement_base.py +9 -0
  99. lybic_guiagents-0.1.0/tests/test_uielement_linux.py +38 -0
  100. lybic_guiagents-0.1.0/tests/test_uielement_macos.py +54 -0
  101. lybic_guiagents-0.1.0/tests/test_uielement_osworld.py +46 -0
@@ -0,0 +1,201 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright [yyyy] [name of copyright owner]
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
@@ -0,0 +1,416 @@
1
+ Metadata-Version: 2.4
2
+ Name: lybic-guiagents
3
+ Version: 0.1.0
4
+ Summary: An open-source agentic framework that enables AI to use computers like humans and can provide a multi-agent runtime environment as an infrastructure capability
5
+ Author: Lybic Development Team
6
+ Author-email: Lybic Development Team <lybic@tingyutech.com>
7
+ License-Expression: Apache-2.0
8
+ Classifier: Programming Language :: Python :: 3
9
+ Requires-Python: >=3.9, <=3.12
10
+ Description-Content-Type: text/markdown
11
+ License-File: LICENSE
12
+ Requires-Dist: numpy
13
+ Requires-Dist: backoff
14
+ Requires-Dist: pandas
15
+ Requires-Dist: openai
16
+ Requires-Dist: anthropic
17
+ Requires-Dist: fastapi
18
+ Requires-Dist: zhipuai
19
+ Requires-Dist: groq
20
+ Requires-Dist: boto3
21
+ Requires-Dist: uvicorn
22
+ Requires-Dist: paddleocr
23
+ Requires-Dist: paddlepaddle
24
+ Requires-Dist: together
25
+ Requires-Dist: scikit-learn
26
+ Requires-Dist: websockets
27
+ Requires-Dist: tiktoken
28
+ Requires-Dist: pyautogui~=0.9.54
29
+ Requires-Dist: toml
30
+ Requires-Dist: exa_py
31
+ Requires-Dist: black
32
+ Requires-Dist: certifi
33
+ Requires-Dist: pytesseract
34
+ Requires-Dist: google-genai
35
+ Requires-Dist: python-dotenv
36
+ Requires-Dist: Pillow~=11.0.0
37
+ Requires-Dist: fabric
38
+ Requires-Dist: gymnasium~=0.28.1
39
+ Requires-Dist: requests~=2.31.0
40
+ Requires-Dist: pytz~=2024.1
41
+ Requires-Dist: transformers~=4.35.2
42
+ Requires-Dist: torch~=2.5.0
43
+ Requires-Dist: accelerate
44
+ Requires-Dist: opencv-python~=4.8.1.78
45
+ Requires-Dist: matplotlib~=3.7.4
46
+ Requires-Dist: pynput~=1.7.6
47
+ Requires-Dist: psutil~=5.9.6
48
+ Requires-Dist: tqdm~=4.65.0
49
+ Requires-Dist: flask~=3.0.0
50
+ Requires-Dist: requests-toolbelt~=1.0.0
51
+ Requires-Dist: lxml
52
+ Requires-Dist: cssselect
53
+ Requires-Dist: xmltodict
54
+ Requires-Dist: openpyxl
55
+ Requires-Dist: python-docx
56
+ Requires-Dist: python-pptx
57
+ Requires-Dist: pypdf
58
+ Requires-Dist: PyGetWindow
59
+ Requires-Dist: rapidfuzz
60
+ Requires-Dist: pyacoustid
61
+ Requires-Dist: pygame
62
+ Requires-Dist: ImageHash
63
+ Requires-Dist: scikit-image
64
+ Requires-Dist: librosa
65
+ Requires-Dist: pymupdf
66
+ Requires-Dist: chardet
67
+ Requires-Dist: playwright
68
+ Requires-Dist: formulas
69
+ Requires-Dist: pydrive
70
+ Requires-Dist: fastdtw
71
+ Requires-Dist: odfpy
72
+ Requires-Dist: func-timeout
73
+ Requires-Dist: beautifulsoup4
74
+ Requires-Dist: dashscope
75
+ Requires-Dist: google-generativeai
76
+ Requires-Dist: PyYaml
77
+ Requires-Dist: mutagen
78
+ Requires-Dist: easyocr
79
+ Requires-Dist: borb
80
+ Requires-Dist: pypdf2
81
+ Requires-Dist: pdfplumber
82
+ Requires-Dist: wandb
83
+ Requires-Dist: wrapt_timeout_decorator
84
+ Requires-Dist: gdown
85
+ Requires-Dist: azure-identity
86
+ Requires-Dist: azure-mgmt-compute
87
+ Requires-Dist: azure-mgmt-network
88
+ Requires-Dist: docker
89
+ Requires-Dist: loguru
90
+ Requires-Dist: dotenv
91
+ Requires-Dist: pyobjc; platform_system == "Darwin"
92
+ Requires-Dist: pywinauto; platform_system == "Windows"
93
+ Requires-Dist: pywin32; platform_system == "Windows"
94
+ Dynamic: author
95
+ Dynamic: license-file
96
+ Dynamic: requires-python
97
+
98
+ <div align="center">
99
+
100
+ **[English](./README.md) | [中文](./README-zh.md) | [日本語](./README-jp.md)**
101
+
102
+ <br/>
103
+ </div>
104
+
105
+ <p align="center">
106
+ <img src="assets/logo.png" alt="Lybic Logo" width="400"/>
107
+ </p>
108
+ <h1 align="center">
109
+ Lybic GUI Agent: <small>An open-source agentic framework for Computer Use Agents</small>
110
+ </h1>
111
+
112
+ ## What is Lybic GUI Agent?
113
+
114
+ Lybic platform placeholder - comprehensive AI platform for building and deploying intelligent agents
115
+
116
+ Lybic GUI Agent is an open-source framework that enables developers and businesses to create intelligent computer-use agents,mobile-use agents, and intelligent agents that can understand and interact with graphical user interfaces across Windows, macOS, Linux and Android(via lybic Android Sandbox) platforms.
117
+
118
+ <!-- <p align="center"><small>Lybic GUI Agent is based upon the <a href="https://github.com/simular-ai/Agent-S">Agent-S</a> codebase, allowing us to focus on making the best interaction experience with Lybic while maintaining a familiar execution logic.</small></p> -->
119
+
120
+ <div align="center">
121
+
122
+ <p>Skip the setup? Try Lybic GUI Agent in our <a href="https://playground.lybic.cn/">Playground</a> with a few clicks.(Only in the Chinese mainland supported)
123
+
124
+ </div>
125
+
126
+ ## 🥳 Updates
127
+ - [x] **2025/09/09**: We achieved the world's first place in the 50-step length of [OS-world](https://os-world.github.io/)!
128
+ - [x] **2025/08/08**: Released v0.1.0 of [Lybic GUI Agent](https://github.com/lybic/agent) library, with support for Windows, Mac, Ubuntu and Lybic API!
129
+
130
+ ## Table of Contents
131
+
132
+ 1. [💡 Introduction](#-introduction)
133
+ 2. [🛠️ Installation & Setup](#%EF%B8%8F-installation--setup)
134
+ 3. [🚀 Usage](#-usage)
135
+
136
+ ## 💡 Introduction
137
+
138
+ ## ✨ Feature Agentic Lybic Support
139
+
140
+ - **Multiple LLMs providers**: OpenAI, Anthropic, Google, xAI , AzureOpenAI, DeepSeek, Qwen, Doubao, ZhipuGLM
141
+ - **Aggregation Model Provider**: Bedrock, Groq, Monica, OpenRouter, SiliconFlow
142
+ - **RAG**: We support RAG, and this capability is provided as an extension
143
+ - **Cross-Platform GUI Control**: Windows, Linux, macOS, Android Supported
144
+ - **Observability**: Supported
145
+ - **Local Deployment**: Supported
146
+ - **Cloud Sandbox Environment**: Supported
147
+
148
+ <p align="center">🎉 Agents Online Demo</p>
149
+
150
+ [![Our demo](https://img.youtube.com/vi/GaOoYoRKWhE/maxresdefault.jpg)](https://www.youtube.com/watch?v=GaOoYoRKWhE)
151
+
152
+ <p align="center">🎯 Current Results</p>
153
+
154
+ <div align="center">
155
+ <table border="0" cellspacing="0" cellpadding="5">
156
+ <tr>
157
+ <th>Benchmark</th>
158
+ <th>Lybic GUI Agent</th>
159
+ <th>Previous SOTA</th>
160
+ </tr>
161
+ <tr>
162
+ <td>OSWorld Verified (50 step)</td>
163
+ <td><b>57.1%</b></td>
164
+ <td>53.1%</td>
165
+ </tr>
166
+ </table>
167
+ </div>
168
+
169
+ <p align="center">
170
+ <img src="assets/structure.png" alt="Lybic GUI Agent system structure" width="700"/>
171
+ </p>
172
+ <p align="center"><b>Fig. Lybic GUI Agent system structure</b></p>
173
+
174
+ ## 🛠️ Installation & Setup
175
+
176
+ > [!WARNING]
177
+ > To leverage the full potential of Lybic GUI Agent, we support multiple model providers including OpenAI, Anthropic, Gemini, and Doubao. For the best visual grounding performance, we recommend using UI-TARS models.
178
+
179
+ ### Installation
180
+
181
+ You can use [UV](https://docs.astral.sh/uv/getting-started/installation/) (a modern Python package manager) version 0.8.5 for installation:
182
+
183
+ ```bash
184
+ # 1. Install UV if not already installed
185
+ # macOS and Linux
186
+ curl -LsSf https://astral.sh/uv/0.8.5/install.sh | sh
187
+ # Windows
188
+ powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/0.8.5/install.ps1 | iex"
189
+
190
+ # testing uv installation, version should be 0.8.5
191
+ uv --version
192
+
193
+ # 2. Install the python 3.12
194
+ uv python install 3.12.11
195
+
196
+ # 3. Create a virtual environment
197
+ uv venv -p 3.12.11
198
+
199
+ # 4. Activate the virtual environment
200
+ # macOS and Linux
201
+ source .venv/bin/activate
202
+ # Windows
203
+ .venv\Scripts\activate
204
+
205
+ # 5. Install dependencies (using locked versions)
206
+ uv sync
207
+
208
+ # 6. Install the package locally in development mode
209
+ uv pip install -e .
210
+ ```
211
+
212
+ ### API Key Configuration
213
+
214
+ The simplest way to configure API keys is to:
215
+
216
+ 1. Copy `gui_agents/.env.example` to `gui_agents/.env`
217
+ 2. Edit the `.env` file and add your API keys
218
+
219
+ ### Tool Configuration
220
+
221
+ We provide two pre-configured tool settings:
222
+
223
+ - `tools_config_en.json`: Configured for English language models (Gemini, Exa)
224
+ - `tools_config_cn.json`: Configured for Chinese language models (Doubao, bocha)
225
+
226
+ The agent uses `tools_config.json` by default. You can:
227
+
228
+ - Copy either `tools_config_en.json` or `tools_config_cn.json` to `tools_config.json`
229
+ - Or create your own custom configuration
230
+
231
+ If you are using `tools_config_cn.json` and use `pyautogui` backend, the environment variable only `ARK_API_KEY` should be set.
232
+
233
+ If you are using `tools_config_en.json` and use `pyautogui` backend, you should set those 3 environment variables:
234
+
235
+ ```bash
236
+ GEMINI_ENDPOINT_URL=https://generativelanguage.googleapis.com/v1beta/openai/
237
+ GEMINI_API_KEY=your_gemini_api_key
238
+ ARK_API_KEY=your_ark_api_key
239
+ ```
240
+
241
+ ```bash
242
+ # For English models
243
+ cp gui_agents/tools/tools_config_en.json gui_agents/tools/tools_config.json
244
+
245
+ # For Chinese models
246
+ cp gui_agents/tools/tools_config_cn.json gui_agents/tools/tools_config.json
247
+ ```
248
+
249
+ > **Note**: Our recommended configuration uses `doubao-1-5-ui-tars-250428` for `"tool_name": "grounding" or "fast_action_generator"` and `claude-sonnet-4-20250514` or `doubao-seed-1-6-250615` for other tools such as `"tool_name": "action_generator"`. You can customize the model configuration in the tools configuration files. Do not modify the `"tool_name"` in `tools_config.json` file. To change the `"provider"` and `"model_name"` in `tools_config.json` file, see [model.md](gui_agents/tools/model.md)
250
+
251
+ ## 🚀 Usage
252
+
253
+ ### Command Line Interface
254
+
255
+ Run Lybic GUI Agent with python in the command-line interface:
256
+
257
+ ```sh
258
+ python gui_agents/cli_app.py [OPTIONS]
259
+ ```
260
+
261
+ This will show a user query prompt where you can enter your instructions and interact with the agent.
262
+
263
+ ### Options
264
+
265
+ - `--backend [lybic|pyautogui|pyautogui_vmware]`: Specifies the backend to use for controlling the GUI. Defaults to `lybic`.
266
+
267
+ - `--query "YOUR_QUERY"`: Optional, can be input during the runtime; if provided, the agent will execute the query and then exit.
268
+ - `--max-steps NUMBER`: Sets the maximum number of steps the agent can take. Defaults to `50`.
269
+ - `--mode [normal|fast]`: (Optional) Selects the agent mode. `normal` runs the full agent with detailed reasoning and memory, while `fast` mode executes actions more quickly with less reasoning overhead. Defaults to `normal`.
270
+ - `--enable-takeover`: (Optional) Enables user takeover functionality, allowing the agent to pause and request user intervention when needed. By default, user takeover is disabled.
271
+ - `--disable-search`: (Optional) Disables web search functionality. By default, web search is enabled.
272
+
273
+ ### Examples
274
+
275
+ Run in interactive mode with the `lybic` backend:
276
+ ```sh
277
+ python gui_agents/cli_app.py --backend lybic
278
+ ```
279
+
280
+ Run a single query with the `pyautogui` backend and a maximum of 20 steps:
281
+ ```sh
282
+ python gui_agents/cli_app.py --backend pyautogui --query "Find the result of 8 × 7 on a calculator" --max-steps 20
283
+ ```
284
+
285
+ Run in fast mode with the `pyautogui` backend:
286
+ ```sh
287
+ python gui_agents/cli_app.py --backend pyautogui --mode fast
288
+ ```
289
+
290
+ > [!WARNING]
291
+ > The agent will directly control your computer with `--backend pyautogui`. Please use with care.
292
+
293
+ ### Lybic Sandbox Configuration
294
+
295
+ The simplest way to configure Lybic Sandbox is still to edit the `.env` file and add your API keys, as mentioned in the [API Key Configuration](#api-key-configuration) section.
296
+
297
+
298
+ ```bash
299
+ LYBIC_API_KEY=your_lybic_api_key
300
+ LYBIC_ORG_ID=your_lybic_org_id
301
+ LYBIC_MAX_LIFE_SECONDS=3600
302
+ ```
303
+
304
+ > **Note**: If you want to use a precreated Lybic Sandbox in [Lybic Dashboard](https://dashboard.lybic.cn/), you need to set the `LYBIC_PRECREATE_SID` to the precreated Sandbox ID.
305
+
306
+ >
307
+ > ```bash
308
+ > LYBIC_PRECREATE_SID=SBX-XXXXXXXXXXXXXXX
309
+ > ```
310
+
311
+ ### VMware Configuration
312
+
313
+ To use PyAutoGUI with VMware, you need to install [VMware Workstation Pro](https://www.vmware.com/products/desktop-hypervisor/workstation-and-fusion) (on Windows) and create a virtual machine.
314
+
315
+ Next, you need to download the [`Windows-x86.zip`](https://huggingface.co/datasets/xlangai/ubuntu_osworld/resolve/main/Ubuntu-x86.zip) and [`Ubuntu-x86.zip`](https://huggingface.co/datasets/xlangai/ubuntu_osworld/resolve/main/Ubuntu-x86.zip) from Hugging Face. Then unzip them into `./vmware_vm_data/Windows-x86` and `./vmware_vm_data/Ubuntu-x86` directory.
316
+
317
+ Finally, you need to edit the `.env` file and set the `USE_PRECREATE_VM` environment variable to the name of the virtual machine. `USE_PRECREATE_VM` support `Windows` and `Ubuntu` on x86 arch computer.
318
+
319
+ ```bash
320
+ USE_PRECREATE_VM=Ubuntu
321
+ ```
322
+
323
+ ## 🔧 Troubleshooting
324
+
325
+ ### Common Runtime Issues
326
+
327
+ #### 1. API Key Configuration Issues
328
+
329
+ **Problem**: `KeyError` or authentication errors when running the agent.
330
+
331
+ **Solution**:
332
+ - Ensure your `.env` file is properly configured with valid API keys
333
+ - Check that environment variables are set correctly:
334
+ ```bash
335
+ # For English models
336
+ export GEMINI_API_KEY=your_gemini_api_key
337
+ export ARK_API_KEY=your_ark_api_key
338
+
339
+ # For Chinese models
340
+ export ARK_API_KEY=your_ark_api_key
341
+ ```
342
+ - Verify API key permissions and quotas
343
+
344
+ #### 2. Python Environment Issues
345
+
346
+ **Problem**: `ModuleNotFoundError` or package import errors.
347
+
348
+ **Solution**:
349
+ - Ensure you're using Python 3.12.11 as specified
350
+ - Activate the virtual environment:
351
+ ```bash
352
+ # macOS/Linux
353
+ source .venv/bin/activate
354
+ # Windows
355
+ .venv\Scripts\activate
356
+ ```
357
+ - Reinstall dependencies:
358
+ ```bash
359
+ uv sync
360
+ uv pip install -e .
361
+ ```
362
+
363
+ #### 3. Lybic Sandbox Connection Issues
364
+
365
+ **Problem**: `Connection timeout` or `Sandbox creation failed`.
366
+
367
+ **Solution**:
368
+ - Check network connectivity to Lybic servers
369
+ - Verify `LYBIC_ORG_ID` and `LYBIC_API_KEY` are correct
370
+ - Ensure sufficient quota in your Lybic account
371
+ - Try increasing `LYBIC_MAX_LIFE_SECONDS` if sandbox times out
372
+
373
+ #### 4. VMware Backend Issues
374
+
375
+ **Problem**: Virtual machine fails to start or control.
376
+
377
+ **Solution**:
378
+ - Ensure VMware Workstation Pro is properly installed
379
+ - Check that VM files are extracted to correct directories:
380
+ - `./vmware_vm_data/Windows-x86/`
381
+ - `./vmware_vm_data/Ubuntu-x86/`
382
+ - Verify VMware service is running
383
+ - Set correct `USE_PRECREATE_VM` environment variable
384
+
385
+ #### 5. Model Performance Issues
386
+
387
+ **Problem**: Slow response times or poor grounding accuracy.
388
+
389
+ **Solution**:
390
+
391
+ - Use recommended models for better performance:
392
+ - Visual grounding: `doubao-1-5-ui-tars-250428`
393
+ - Action generation: `claude-sonnet-4-20250514`
394
+ - Switch to `--mode fast` for quicker execution
395
+ - Reduce `--max-steps` for shorter tasks
396
+
397
+ ### Getting Help
398
+
399
+ If you encounter issues not covered here:
400
+
401
+ 1. Check the [GitHub Issues](https://github.com/lybic/agent/issues) for similar problems
402
+ 2. Review the [Lybic Documentation](https://lybic.ai/docs)
403
+ 3. Create a new issue with:
404
+ - Your operating system and version
405
+ - Python version and environment details
406
+ - Complete error messages
407
+ - Steps to reproduce the issue
408
+
409
+ ## Stargazers over time
410
+
411
+ [![Stargazers over time](https://starchart.cc/lybic/agent.svg)](https://starchart.cc/lybic/agent)
412
+
413
+ ## License
414
+
415
+ This project is distributed under Apache 2.0 License.
416
+ Therefore, you can modify the source code and release it commercially.