infinity
AI-native database for LLM applications offering fast hybrid search capabilities.
GraphCanon updated today · GitHub synced today
Decision brief
Designed for high-speed hybrid searches in LLM applications, infinity supports dense vector, sparse vector, tensor, and full-text data types.
Good fit when
- When your application requires rapid hybrid search capabilities across multiple data types including tensors and full texts.
- For projects that need to integrate closely with large language models using AI-native technologies.
Avoid when
- If your project does not benefit from fast hybrid search features or if you prefer not to use an AI-native database solution.
- When support for only dense vectors is sufficient, and the added complexity of supporting tensors and full texts is unnecessary.
Observed Jul 14, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (3d since push)
- As of today
- Provenance
- Not a fork · Organization account
- As of today
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Backing
Company context for InfiniFlow. Display-only - separate from trust and ranking.
- Company
- InfiniFlow·GitHub org profile·1mo
- Commercial model
- Pure OSS·GitHub org profile (public repos)·1mo
Install
git clone https://github.com/infiniflow/infinityHow it fits your stack(15)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Integrates
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Infiniflow/infinity is an AI-native database designed to support large language model (LLM) applications by enabling extremely rapid hybrid searches across dense vector, sparse vector, tensor, and full-text data types.
Capability facts
- Languages
- c++, python
Source: github.language+pyproject.toml · Aug 21, 2026
Categories
Graph entities
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 21, 2026)
pip install infinity-sdk==0.7.3Source link
Tags
README
Install Infinity server
Linux x86_64 & MacOS x86_64
sudo mkdir -p /var/infinity && sudo chown -R $USER /var/infinity
docker pull infiniflow/infinity:nightly
docker run -d --name infinity -v /var/infinity/:/var/infinity --ulimit nofile=500000:500000 --network=host infiniflow/infinity:nightly
Windows
If you are on Windows 10+, you must enable WSL or WSL2 to deploy Infinity using Docker. Suppose you've installed Ubuntu in WSL2:
-
Follow this to enable systemd inside WSL2.
-
Install docker-ce according to the instructions here.
-
If you have installed Docker Desktop version 4.29+ for Windows: Settings > Features in development, then select Enable host networking.
-
Pull the Docker image and start Infinity:
sudo mkdir -p /var/infinity && sudo chown -R $USER /var/infinity docker pull infiniflow/infinity:nightly docker run -d --name infinity -v /var/infinity/:/var/infinity --ulimit nofile=500000:500000 --network=host infiniflow/infinity:nightly
Install Infinity client
pip install infinity-sdk==0.7.3
For agents
This page has a .md twin and JSON over the API.