Contributing to TeleMem
June 11, 2026 · View on GitHub
Thanks for your interest in improving TeleMem! Issues and pull requests are welcome — this guide gets you productive quickly.
Development setup
We use uv for a reproducible environment:
git clone https://github.com/TeleAI-UAGI/telemem.git
cd telemem
uv sync --all-extras # installs TeleMem (editable) + video/MCP extras + dev tools
Running the tests
The default suite runs fully offline (no API keys needed):
uv run pytest tests/ -q
Tests that exercise a live LLM/embedding endpoint are opt-in:
TELEMEM_RUN_API_TESTS=1 OPENAI_API_KEY=sk-... uv run pytest tests/ -q
MiniMax integration tests additionally need MINIMAX_API_KEY.
Pull requests
- Fork and create a feature branch from
main. - Keep changes focused; add or update tests for behavior changes.
- Make sure
uv run pytest tests/ -qpasses — CI runs the same suite on Python 3.10–3.12. - If you change the public API, update both
README.mdandREADME-ZH.md, and add a line toCHANGELOG.md.
Reporting issues
Use the issue templates. For bugs, include your Python version, TeleMem
version (python -c "import telemem; print(telemem.__version__)"), config
(redact keys!), and a minimal reproduction.
Good first contributions
- New LLM / embedder provider configs (with a
config/config.<provider>.yamlexample and tests, like the MiniMax one). - Framework integrations (LangChain, LlamaIndex, AutoGen, CrewAI...).
- Benchmark reproductions and evaluation scripts under
baselines/. - Documentation and bilingual README improvements.