superlinked/sie
Open-source inference server and production cluster for all the models your agent needs.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest 18 days ago, with 22 contributors on GitHub.
Use Cases & Benefits
- Provides a unified open-source inference server that hosts and serves 100+ AI models for agent tasks via a single API.
- Eliminates the need for multiple model servers by enabling on-demand loading and management of diverse models in one scalable cluster.
- Use for deploying scalable semantic search and retrieval systems with multiple embedding and reranking models.
- Use for converting complex documents like PDFs and scans into clean markdown for content processing workflows.
- Use for running agent loops that plan and execute multi-step tasks using open large language models with streaming support.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
- Contributing guide: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
Self-hosted inference for agents. Every open model your agents call, served from one cluster in your cloud.
⭐ Help us reach more developers and grow the SIE community. Star this repo!
SIE is an open-source inference engine that runs the models behind every agent task through one API: search and retrieval, document-to-markdown conversion, structured output, content safety, and the agent loop itself. It replaces the patchwork of a separate model server per task with one system that serves 100+ models, loading each on demand.
The repository root is a virtual Python workspace. From the repository root, install and verify every workspace member with the committed lock (the audio-prep member requires its documented native build prerequisites):
Package membership is explicit in the root
pyproject.toml; a package joins the workspace only in the same change that adds its complete source.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+772 stars over 85 days across 9 snapshot days; best day +118 on Sep 3.
Forks
328+67
Open issues
40+29
Compared with peers in Data Engineering
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| apache/airflow | 47.3K | — | 63 | 40 days ago |
| pion/webrtc | 16.9K | — | 60 | 1 day ago |
| flexprice/flexprice | 6.9K | — | 65 | 5 days ago |
| truelockmc/streambert | 6.4K | — | 28 | 120 days ago |
| lakehq/sail | 3.5K | — | 63 | 28 days ago |
| superlinked/sie | 3.5K | — | 59 | 18 days ago |
| Category median | 6.9K | — | 63 | — |
Discover Repositories
Search across tracked repositories by name or description