Metadata-Version: 2.4
Name: llm-latency-radar
Version: 0.3.0
Summary: Zero-dependency streaming latency profiler for Time-To-First-Token (TTFT), inter-token jitter, P95/P99 percentiles, and SLO regression gating across LLM providers.
License: MIT
Project-URL: Homepage, https://github.com/andrejpimenov122-lab/llm-latency-radar
Project-URL: Repository, https://github.com/andrejpimenov122-lab/llm-latency-radar
Project-URL: Bug Tracker, https://github.com/andrejpimenov122-lab/llm-latency-radar/issues
Keywords: llm,latency,ttft,streaming,profiler,jitter,benchmark,slo,observability
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: System :: Benchmark
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# ⚡ LLM Latency Radar

**Open-source browser-side streaming profiler for Time-To-First-Token (TTFT), P95 Jitter, and Tokens/sec across LLM providers.**

- Zero server storage — API keys never leave browser memory.
- Ready for 1-click deployment on **Vercel**.
- Includes Contributor Covenant [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) and MIT License.
