MeraLLM
Python chat workspace for Ollama and OpenRouter models, built with FastAPI.
Features
- Model and skill favorites
- Projects, chat search, web search, agent mode, and MCP tools
- Markdown, equations, tables, code, and Mermaid diagrams
- File attachments up to 100 MB
- Responsive light and dark interface
Install
python -m pip install merallm
Install the latest GitHub version:
python -m pip install "git+https://github.com/pankajkarman/MeraLLM.git"
For local development:
python -m pip install -e .
Install and start Ollama to use local models.
Configure
$env:OPENROUTER_API_KEY="your-key-here"
$env:MERALLM_DATA_DIR="optional-custom-data-path"
The data directory can also be changed under Settings → MERALLM_DATA_DIR.
Run
merallm
Open http://127.0.0.1:8002. Use merallm --help for host, port, and reload
options.
Uninstall
python -m pip uninstall merallm
Uninstalling does not delete chats or preferences. Delete the configured data directory manually if you also want to remove local data.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file merallm-0.2.0.tar.gz.
File metadata
- Download URL: merallm-0.2.0.tar.gz
- Upload date:
- Size: 2.0 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
be21fd9344722c77882d23d9c5a2fa89da49765b97a20a6c695d062c7a04a714
|
|
| MD5 |
ac3b0a9fc7aec374dc0eac44b9abdec8
|
|
| BLAKE2b-256 |
a3ae9762edacade8849b2395b6ce262861966cff3160ad14c2b8a9ba4551a7d2
|
File details
Details for the file merallm-0.2.0-py3-none-any.whl.
File metadata
- Download URL: merallm-0.2.0-py3-none-any.whl
- Upload date:
- Size: 2.0 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
29041cadb177db60f597cc377c5c516d0338995b11ffd9cf4eaa97d30c74dca9
|
|
| MD5 |
b856a83614ab2c4f901c1a2f5b2f9a80
|
|
| BLAKE2b-256 |
f710021a2139c00bf7a87724db295012bf52fa62a483760a8a71d147781c7170
|
