FlockParser and FlockParser-legacy

FlockParser
40
Emerging
FlockParser-legacy
22
Experimental
Maintenance 6/25
Adoption 3/25
Maturity 16/25
Community 15/25
Maintenance 6/25
Adoption 1/25
Maturity 15/25
Community 0/25
Stars: 4
Forks: 4
Downloads: —
Commits (30d): 0
Language: Python
License: MIT
Stars: 1
Forks: —
Downloads: —
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About FlockParser

B-A-M-N/FlockParser

Distributed document RAG system with intelligent GPU/CPU orchestration. Auto-discovers heterogeneous nodes, routes workloads adaptively, and achieves 60x+ speedups through VRAM-aware load balancing. Privacy-first architecture with 4 interfaces (CLI, API, MCP, Web UI). Real distributed systems engineering, not just an API wrapper.

FlockParser helps engineering and research teams privately extract insights from large collections of documents, like research papers or contracts. It takes your documents (e.g., PDFs) and processes them much faster by intelligently distributing the work across your existing computers, even if some have GPUs and others don't. The output is structured information and answers from your documents, without sending your sensitive data to external cloud services.

document-intelligence private-RAG research-data-extraction on-premise-AI knowledge-base-processing

About FlockParser-legacy

B-A-M-N/FlockParser-legacy

Legacy version of FlockParser PDF processing system

Scores updated daily from GitHub, PyPI, and npm data. How scores work