Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs
Repository Index
69,734 visible repositories in the index
1,369–1,392 of 2,754 · Most stars
Plugin for JADX to integrate MCP server
zot - A scale-out production-ready vendor-neutral OCI-native container image/artifact registry (purely based on OCI Distribution Specification)
- zot
- opencontainers
- oci
- distribution-spec
A Model Context Protocol server for converting almost anything to Markdown
Linux daemon for Intel CPU power limits and firmware-induced throttling.
- linux
- cpu-throttling
- intel
- intel-cpu
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.一键免费部署你的私人AutoGPT 网页应用
LLM Finetuning with peft
- falcon
- fine-tuning
- huggingface
- llama
A cross-platform video structuring (video analysis) framework based on CV models & mLLM.
한국 문서를 읽고·고치고·새로 쓰는 AI 문서 도구 — HWP·HWPX·PDF·오피스·스캔(OCR)을 Markdown으로, 신구대조·서식 보존 편집·Markdown→HWPX 작성·HWP→HWPX 변환·양식 채우기·공문서 검수까지. 라이브러리·CLI·MCP | Read, diff, edit, write and convert Korean documents (HWP, HWPX, PDF, Office, scans) — library, CLI and MCP server
- cli
- document-parser
- hancom
- hwp
Programmatically collect normalized news from (almost) any website.
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
- llm
- text-embeddings
- bert-embeddings
The pretty much "official" DSPy framework for Typescript
AI-powered cross-platform e-book reader with semantic search, RAG chat, local vector store, notes, TTS, and WebDAV sync.
- ai
- anthropic
- ebook-reader
- embeddings
Convert code repos into an LLM prompt-friendly format. Mostly built by GPT-4.
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.
A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.
An unofficial PyTorch implementation of the audio LM VALL-E
- vall-e
- valle
- text-to-speech
- pytorch
Modular AI HAL (Hardware Abstraction Layer) for Robots
Terraform provider plugin for proxmox
The no-code platform for building custom LLM Agents
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
- large-language-models
- chatglm
- nlp
- chatglm2
A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on your hardware.
- rust
- ai-agent
- ai-assistant
- llm
User Profile-Based Long-Term Memory for AI Chatbot Applications.