Blaizzy
Featured
nativ
Nativ is a native macOS app that lets you run AI models locally on Apple silicon, offering chat, model management, performance analytics, and an OpenAI/Anthropic-compatible API server.
bidguard-bid-evidence
BidGuard is a local desktop tool that compares 2–10 tender documents across DOCX, PDF, scanned, and Excel formats to surface possible collusion indicators and produce evidence reports for human review.
Stars
5
7-day growth
No data
Forks
0
Open issues
0
License
GPL-3.0
Last updated
2026-07-30
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It targets bid-collusion detection specifically, combining OCR, similarity scoring, visual pairwise comparison, and multi-format export in an offline desktop workflow.
Who it is for
- Procurement specialists
- Auditors and investigators
- Tender and data analysts reviewing document sets
- Compliance or fraud-review personnel
Use cases
- Compare two to ten bid submissions to spot repeated clauses or contradictory facts
- Extract text from scanned bid documents using OCR before comparison
- Review similarity matrices and highlighted document pairs, then accept or exclude findings
- Export reviewed evidence as HTML, Word, Excel, CSV, Markdown, or JSON
Strengths
- Processes documents locally and works offline for the core comparison workflow
- Supports DOCX, PDF, scanned, and Excel inputs in one analysis set
- Includes OCR, weighted similarity ranking, and visual pair comparison
- Generates evidence reports in six formats for downstream review
Considerations
- Comparison sets are limited to a maximum of ten documents
- OCR quality depends on scan clarity, page design, and text legibility
- Running from source requires a Rust/Tauri and Node.js toolchain; optional cloud-model downloads need network access
README quick start
Getting Started
Description
BidGuard is a local desktop tool for comparing tender documents, identifying possible similarities and inconsistencies, and producing evidence reports for procurement and investigation teams.
Related repositories
Similar projects matched by category, topics, and programming language.
MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.