#python #ai_coding #claude #claude_code #code_review #graphrag #incremental #knowledge_graph #llm #mcp #python #static_analysis #tree_sitter

code-review-graph is a free, local-first tool that builds a structural map of your code to stop AI assistants from re-reading your entire codebase, saving you significant money and time. By using Tree-sitter to parse your code into a graph and tracking changes incrementally, it identifies the exact "blast radius" of a change so your AI only reads the few files that actually matter. This reduces token usage by an average of 82x (up to 528x in best cases), cutting costs and making AI reviews feasible for massive projects like monorepos.

https://github.com/tirth8205/code-review-graph

#python

LingBot-Map is an open-source AI model that instantly builds accurate 3D maps from regular video streams at 20 frames per second, handling over 10,000 frames without slowing down . It uses a special "Geometric Context Transformer" to fix camera drift and keep geometry stable as you move . You benefit by getting real-time 3D understanding for robots, autonomous vehicles, or AR apps using only a standard camera, eliminating the need for expensive depth sensors or slow offline processing .

https://github.com/Robbyant/lingbot-map

#python

KTransformers lets you run and fine-tune massive 100B+ AI models on your single consumer GPU (like an RTX 4090) by smartly using your computer's CPU memory and power alongside the GPU. This saves you money by avoiding expensive multi-GPU server clusters while still delivering high speed, allowing you to use cutting-edge AI locally without sacrificing performance.

https://github.com/kvcache-ai/ktransformers

#python #agent #agent_memory #ai_agent #book #coding_agent #context_engineering #large_language_models #llm #mcp #multi_agent #multimodal #rag #reinforcement_learning

This free open-source book and code library teaches you how to build AI Agents using the simple formula: Agent = Model + Context + Tools. You get the full book in English, Chinese, and Tamil, plus ready-to-run code examples for every chapter. The benefit is that you can learn by doing instead of just reading, letting you build real AI agents that search the web, write code, remember users, and work with other agents to solve complex tasks.

https://github.com/bojieli/ai-agent-book

#python #cfg #generative_ai #json #llms #prompt_engineering #regex #structured_generation #symbolic_ai

Outlines is a Python library that guarantees large language models produce structured outputs (like JSON, XML, or custom schemas) directly during generation, not after. By simply specifying your desired output type using Python syntax (e.g., `int` or a Pydantic model), it mathematically ensures the result matches your structure exactly. This benefits you by eliminating broken JSON, parsing errors, and fragile regex code, making your AI applications reliable, predictable, and ready for production use without post-generation fixes.

https://github.com/dottxt-ai/outlines

#python #ai #assistant #language_model #machine_learning #python #speech #speech_synthesis #speech_to_text #speech_translation

I can help you build a fast, modular voice agent that turns speech into text, sends it to a language model, then speaks the answer back. It works with open-source or hosted models, can run fully local on your own hardware, and supports live transcription and low-latency conversation, so you get a flexible voice app that you can customize for speed, privacy, and different devices.

https://github.com/huggingface/speech-to-speech

#python #agent_framework #ai_agents #ai_safety #compliance #governance #microsoft #owasp #policy_engine #python #security #trust #zero_trust

Agent Governance Toolkit helps you control AI agents with policy checks, identity, sandboxing, and audit logs so unsafe actions are blocked before they happen. It lets you govern tools in a few lines of code, works with many languages and agent frameworks, and gives you compliance and security checks, which helps you launch agents more safely and prove what they did.

https://github.com/microsoft/agent-governance-toolkit

#python

book-to-skill turns a technical book, document folder, or other source files into a reusable agent skill that your coding assistant can load only when needed. The benefit is faster, more accurate help with far fewer tokens, so you can ask questions from the real content instead of rereading PDFs or risking weak answers.

https://github.com/virgiliojr94/book-to-skill

#python #deep_face_swap #deep_learning #deep_neural_networks #deepface #deepfakes #deeplearning #face_swap #faceswap #fakeapp #machine_learning #myfakeapp #neural_nets #neural_networks #openfaceswap

FaceSwap is a computer tool that uses deep learning to recognize and swap faces in photos and videos, and it works best on Windows, Linux, or Mac with a modern GPU. You first extract faces, then train a model, then convert new images or video, so you can create face swaps or learn how AI face recognition works more easily.

https://github.com/deepfakes/faceswap

#python #audiobook #faster_whisper #gradio #karaoke #podcasts #speech_recognition #speech_synthesis #speech_to_text #subtitles #text_to_speech #transcription #translator #tts #voice_cloning #voice_conversion #webui #whisper #whisperx #yt_dlp

Voice-Pro is a free, open-source Windows app that lets you download YouTube videos, separate voices, turn speech into text, translate into 100+ languages, and create new speech or cloned voices. It gives you one tool for subtitles, dubbing, and voice work, so you can save time and make multilingual content more easily.

https://github.com/abus-aikorea/voice-pro

#python

TRELLIS.2 is a 3D AI model that turns an image into a detailed 3D object with realistic materials, sharp shapes, and support for complex forms like open surfaces and internal parts. It is built to be fast and efficient, can also add PBR textures, and lets you export usable 3D files for editing or rendering. This helps you create high-quality 3D assets much faster with less manual modeling work.

https://github.com/microsoft/TRELLIS.2

#rust #markdown #nodejs #ocr_routing #pdf #pdf_classification #pdf_extraction #pdf_parser #python #rust #text_extraction

pdf-inspector is a fast Rust tool that checks whether a PDF has real text or is scanned, then extracts text and turns it into clean Markdown without OCR for text PDFs. It works in Python, Node.js, Rust, and browsers, and it is useful because it can save time and cost by skipping OCR, while still giving you searchable, copyable, well-structured output for reports, papers, invoices, and legal files.

https://github.com/firecrawl/pdf-inspector