You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Codeflash is an AI optimization tool that automatically improves the performance of your Python code while maintaining its correctness.
14
+
[Codeflash](https://www.codeflash.ai) is a general purpose optimizer for Python that automatically improves the performance of your Python code while maintaining its correctness.
15
+
It uses advanced LLMs to generate multiple optimization ideas for your code, tests them to be correct and benchmarks them for performance. It then creates merge-ready pull requests containing the best optimization found, which you can review and merge.
- Optimize an entire existing codebase by running `codeflash --all`
19
+
- Automate optimizing all __future__ code you will write by installing Codeflash as a GitHub action.
20
+
- Optimize a Python workflow end-to-end by tracing the workflow.
6
21
7
-
## Features
22
+
Codeflash is used by top engineering teams at [Pydantic](https://github.com/pydantic/pydantic/pulls?q=is%3Apr+author%3Amisrasaurabh1+is%3Amerged), [Langflow](https://github.com/langflow-ai/langflow/issues?q=state%3Aclosed%20is%3Apr%20author%3Amisrasaurabh1), [Albumentations](https://github.com/albumentations-team/albumentations/issues?q=state%3Amerged%20is%3Apr%20author%3Akrrt7%20OR%20state%3Amerged%20is%3Apr%20author%3Aaseembits93%20) and many others to ship performant, expert level code.
23
+
24
+
Codeflash is great at optimizing AI Agents, Computer Vision algorithms, numerical code, backend code or anything else you might write with Python.
8
25
9
-
- Automatically optimizes your code using AI
10
-
- Maintains code correctness through extensive testing
11
-
- Opens a pull request for each optimization
12
-
- Continuously optimizes your codebase through CI
13
-
- Dynamically optimizes your real workflows through tracing
14
26
15
27
## Installation
16
28
@@ -19,38 +31,44 @@ To install Codeflash, run:
19
31
```
20
32
pip install codeflash
21
33
```
22
-
34
+
Add codeflash as a development time dependency if you are using package managers like uv or poetry.
23
35
## Quick Start
24
36
25
-
1. Configure Codeflash for your project:
26
-
```
27
-
codeflash init
28
-
```
29
37
30
-
2. Optimize a function:
38
+
1. To configure Codeflash for a project, at the root directory of your project where the pyproject.toml file is located, run:
- It will ask you a few questions about your project like the location of your code and tests
43
+
- Ask you to generate an [API Key](https://app.codeflash.ai/app/apikeys) to access Codeflash's LLMs
44
+
- Install a [GitHub app](https://github.com/apps/codeflash-ai/installations/select_target) to open Pull Requests on GitHub.
45
+
- Ask if you want to setup a GitHub actions which will optimize all your future code.
46
+
- The codeflash config is then saved in the pyproject.toml file.
34
47
35
-
3. Optimize your entire codebase:
48
+
2. Optimize your entire codebase:
36
49
```
37
50
codeflash --all
38
51
```
52
+
This can take a while to run for a large codebase, but it will keep opening PRs as it finds optimizations.
53
+
54
+
## Documentation
55
+
For detailed installation and usage instructions, visit our documentation at [docs.codeflash.ai](https://docs.codeflash.ai)
56
+
57
+
## Demo
39
58
40
-
## Getting the Best Results
41
59
42
-
To get the most out of Codeflash:
60
+
- Optimizing the performance of new code for a Pull Request through GitHub Actions. This lets you ship code quickly while ensuring it remains performant.
43
61
44
-
1. Install the Github App and actions workflow
45
-
2. Find optimizations on your whole codebase with codeflash --all
46
-
3. Find and optimize bottlenecks with the Codeflash Tracer
0 commit comments