AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

ai artificial-intelligence autonomous-agents gpt-4 openai python

Go to file

merwanehamadi 9ede17891b Add 'Debug simple typo with guidance' challenge (#65 ) Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>		2023-07-07 13:50:53 -07:00
.github	fix	2023-07-06 00:08:49 -04:00
.vscode	init agbenchmark	2023-06-18 11:14:54 -04:00
agbenchmark	Add 'Debug simple typo with guidance' challenge (#65 )	2023-07-07 13:50:53 -07:00
agent	submodule remove	2023-07-06 00:14:40 -04:00
.env.example	moving run agent to tests & agnostic run working	2023-06-30 10:50:54 -04:00
.flake8	Add static linters ci (#45 )	2023-07-02 16:14:49 -04:00
.gitignore	Add basic memory challenge (#57 )	2023-07-05 23:32:28 -04:00
.gitmodules	local runs, home_path config, submodule miniagi (#50 )	2023-07-04 10:23:00 -07:00
.python-version	Add static linters ci (#45 )	2023-07-02 16:14:49 -04:00
LICENSE	init agbenchmark	2023-06-18 11:14:54 -04:00
README.md	local runs, home_path config, submodule miniagi (#50 )	2023-07-04 10:23:00 -07:00
config.json	Fix home_path, local mini-agi run works (#64 )	2023-07-06 18:00:45 -07:00
mypy.ini	Add retrieval challenge test + run tests on CI pipeline (#51 )	2023-07-04 18:28:00 -04:00
poetry.lock	Integrate with gpt engineer (#47 )	2023-07-03 14:53:28 -04:00
pyproject.toml	Add 'Debug simple typo with guidance' challenge (#65 )	2023-07-07 13:50:53 -07:00
regression_tests.json	Add 'Debug simple typo with guidance' challenge (#65 )	2023-07-07 13:50:53 -07:00

README.md

Auto-GPT Benchmark

A repo built for the purpose of benchmarking the performance of agents far and wide, regardless of how they are set up and how they work

Scores:

Scoring of agents will go here. Both overall and by category.

Integrated Agents

Auto-GPT
gpt-engineer
mini-agi
smol-developer