#python

video-use is an open-source tool that lets you edit videos by simply dropping raw footage in a folder and chatting with Claude Code to get a polished final file. It automatically removes filler words like “um” and “uh,” cuts dead space, adds cinematic color grading, embeds customizable subtitles, and generates smooth animation overlays. The benefit to you is saving hours of manual editing while producing professional-quality videos for talks, tutorials, or travel content—without needing presets, menus, or any video editing skills.

https://github.com/browser-use/video-use

#python #agent_skills #agentic_ai #ai_agents #autonomous_agents #claude #claude_code #claude_skills #codex #coding_agent #context_engineering #copilot #cursor #developer_tools #github_copilot #llm_agents #long_running_agents #manus #multi_agent_systems #pi #planning

This tool makes your AI coding agent keep a plan in files like `task_plan.md` so it never loses its goals when context fills up, you run `/clear`, or it crashes. You get a working memory on disk that auto-recovers past sessions and holds the agent until the plan is truly done, letting complex, multi-step tasks finish reliably without goal drift or repeated errors.

https://github.com/OthmanAdi/planning-with-files

#python

Give Claude the ability to watch any video by installing the free `/watch` skill, which lets it see frames and hear audio from YouTube, local files, or over 1,600 sites. Instead of guessing from titles or missing 90% of a transcript, Claude analyzes what actually happens on screen at specific times. This saves you hours of scrubbing through tutorials, bug recordings, or meetings, letting you instantly get summaries, debug issues from screen videos, or find exact moments without watching the whole thing.

https://github.com/bradautomates/claude-video

#python

Pocket TTS is a lightweight, open-source text-to-speech model that generates high-quality audio efficiently on CPUs without needing GPUs or paid web APIs. You benefit by keeping your data private through offline processing, saving costs by avoiding subscription fees, and enjoying fast, real-time voice generation with easy cloning and multi-language support right on your laptop.

https://github.com/kyutai-labs/pocket-tts

#typescript #ai_textbook #algorithms #artificial_intelligence #computer_science #computer_vision #deep_learning #jax #linear_algebra #machine_learning #machine_learning_algorithms #math #mathematics #multimodal_learning #nlp #probability #python #reinforcement_learning #speech_processing #statistics

This free, open textbook teaches math, computer science, and AI from the ground up by prioritizing intuition and real-world context over dense formulas, helping you deeply understand concepts instead of just passing exams . You only need basic math and Python to start, as the material connects all topics into a clear, logical flow designed for curious practitioners . The key benefit is that it gives you the quality knowledge needed to master complex AI roles, proven by friends who used these notes to get hired at top companies like DeepMind and OpenAI .

https://github.com/HenryNdubuaku/maths-cs-ai-compendium

#python #metadata #semantic

Apache Ossie is a new open-source standard that ensures your data definitions (like KPIs) stay consistent across all your AI, BI, and analytics tools. By using a single JSON or YAML format, it acts as a vendor-neutral source of truth, so metrics like "Monthly Active Users" mean the same thing everywhere. The main benefit to you is that you stop wasting time manually reconciling conflicting definitions, which prevents unreliable AI outputs and ensures your team and tools share one accurate understanding of your business data.

https://github.com/apache/ossie

#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