michaelfeil/infinity

infinity

✅ Recently maintained

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

2,980Stars
220Forks
+127-day stars

C++ · MIT · Last push 2026-11-02

Official repository & installation ↗
llmtext-embeddingsbert-embeddings

Star history

2025-09-292026-11-02
View historical data
DateStars
2026-10-042,943
2026-10-052,943
2026-10-062,944
2026-10-072,947
2026-10-082,947
2026-10-092,949
2026-10-102,951
2026-10-112,953
2026-10-122,953
2026-10-132,955
2026-10-142,955
2026-10-152,958
2026-10-162,960
2026-10-172,961
2026-10-182,962
2026-10-192,963
2026-10-202,964
2026-10-212,967
2026-10-222,967
2026-10-232,968
2026-10-242,968
2026-10-252,968
2026-10-262,969
2026-10-272,970
2026-10-282,972
2026-10-292,974
2026-10-302,978
2026-10-312,978
2026-11-012,978
2026-11-022,980

Get the project

git clone https://github.com/michaelfeil/infinity.git

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

hermes-agent

Open-source AI agent from Nous Research that works with Claude, GPT and other models and grows with use.

★ 259,584firecrawl

Crawls and scrapes web pages into clean Markdown for AI agents and LLM pipelines.

★ 197,744AutoGPT

Open-source autonomous AI agent platform that breaks down and executes multi-step tasks on its own.

★ 187,861