aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2026-01-08 16:54:31 +01:00
Code Issues Packages Projects Releases Wiki Activity
1,277 Commits 1 Branch 0 Tags
6c043d19c108357277c4d278dcde9c1b6171d08a
Go to file
Clone
Open with VS Code Open with VSCodium Open with Intellij IDEA
Download ZIP Download TAR.GZ Download BUNDLE
Auto-GPT-Bot 6c043d19c1 PolyGPT-20230901082141
2023-09-01 08:21:42 +00:00
.github
Tic tac toe challenge (#345)
2023-08-31 20:45:31 -07:00
.vscode
Adding Auto-GPT-Turbo (#322)
2023-08-19 11:32:38 -07:00
agbenchmark
Tic tac toe challenge (#345)
2023-08-31 20:45:31 -07:00
agent
Updating Turbo (#343)
2023-08-31 07:09:41 -04:00
backend
adding backend and a basic ui (#309)
2023-08-27 03:18:30 -04:00
frontend @ c6a9572bed
update frontend hash, run.sh
2023-08-28 19:55:44 -07:00
notebooks
working bar and radar charts (#221)
2023-07-31 12:22:38 +01:00
reports
PolyGPT-20230901082141
2023-09-01 08:21:42 +00:00
.env.example
Update .env.example (#298)
2023-08-12 19:52:15 -07:00
.flake8
Cleanup skill tree (#287)
2023-08-10 16:29:58 -07:00
.gitignore
Updated ignore
2023-08-29 15:47:35 +02:00
.gitmodules
Update Turbo (#324)
2023-08-23 14:39:20 -07:00
.pre-commit-config.yaml
AUTO-25: Add the ability to run multiple categories and to skip categories (#270)
2023-08-07 12:29:00 +01:00
.python-version
Add static linters ci (#45)
2023-07-02 16:14:49 -04:00
json_to_base_64.py
Push reports to google drive (#167)
2023-07-18 09:17:45 -07:00
LICENSE
init agbenchmark
2023-06-18 11:14:54 -04:00
mypy.ini
Add all agent protocol tests (#260)
2023-08-06 09:52:46 -07:00
poetry.lock
Support agent protocol (#337)
2023-08-30 19:44:39 -07:00
pyproject.toml
Support agent protocol (#337)
2023-08-30 19:44:39 -07:00
README.md
adding backend and a basic ui (#309)
2023-08-27 03:18:30 -04:00
run.sh
update frontend hash, run.sh
2023-08-28 19:55:44 -07:00
send_to_googledrive.py
Fix linter 2 (#319)
2023-08-16 16:56:02 -07:00
server.py
Tic tac toe challenge (#345)
2023-08-31 20:45:31 -07:00

README.md

Auto-GPT Benchmarks

Built for the purpose of benchmarking the performance of agents regardless of how they work.

Objectively know how well your agent is performing in categories like code, retrieval, memory, and safety.

Save time and money while doing it through smart dependencies. The best part? It's all automated.

Scores:

Screenshot 2023-07-25 at 10 35 01 AM

Ranking overall:

Detailed results:

Screenshot 2023-07-25 at 10 42 15 AM

Click here to see the results and the raw data!!

More agents coming soon !

Description
No description provided
Readme MIT 81 MiB
Languages
JavaScript 68.5%
Python 18.3%
Jupyter Notebook 8.3%
Dart 3.4%
C++ 0.4%
Other 0.8%