GitHub Trends
11K subscribers
15.8K links
See what the GitHub community is most excited about today.

A bot automatically fetches new repositories from https://github.com/trending and sends them to the channel.

Author and maintainer: https://github.com/katursis
Download Telegram
#python

RLMs let a language model break a large task into smaller parts, call itself again, and work through very long inputs more effectively. They include tools for local or isolated code execution, support major model providers, and offer training and logging features. For you, this means better handling of long-context tasks, more flexible model workflows, and a way to test or train your own recursive AI system safely.

https://github.com/alexzhang13/rlm
1
#python #agent #agentic_ai #ai #claude #copilot #cursor #elevenlabs #ffmpeg #flux #image_generation #open_source #openai #python #remotion #stable_diffusion #text_to_speech #text_to_video #video_generation #video_production

OpenMontage turns a plain idea or even a reference video into a full video production workflow, handling research, script writing, asset creation, editing, captions, and final rendering. Your benefit is faster video creation with lower cost, more control, and fewer surprises, because it can use free/open footage or AI tools, estimate cost first, and check quality before showing you the result.

https://github.com/calesthio/OpenMontage
1
#python #generative_ai #ltx #ltx_2

LTX-2 is an open-source AI video model that makes video and sound together in one system, with sync between speech, movement, and audio. It offers high-quality results, multiple speed and quality modes, API use, and local running, so you can create faster previews or more polished videos depending on your needs.

https://github.com/Lightricks/LTX-2
#python #ai #ai_agents #cli #hypergraph #information_extraction #knowledge #knowledge_graph #llm #python #rag

Hyper-Extract is a tool that uses AI to turn messy documents into clean, structured knowledge like lists, graphs, and linked data with one command. It gives you fast search, easy visual reports, and ready-made templates, so you can save time, understand information faster, and keep adding new documents without rebuilding everything.

https://github.com/yifanfeng97/Hyper-Extract
#python

Hiring Agent reads your PDF resume, extracts structured data, and enriches it with your GitHub profile to give a fair, explainable score with category breakdowns. You benefit by getting an objective evaluation that removes human bias, highlights your real skills and projects, and speeds up your hiring process with transparent, evidence-backed feedback you can trust and improve.

https://github.com/interviewstreet/hiring-agent
#python #agent_skills

Agent Skills are lightweight, open folders containing plain-language instructions and resources that give AI agents specialized knowledge and repeatable workflows, solving the problem of missing context for real work. You benefit by defining complex tasks like data analysis or compliance checks once and reusing them across any compatible agent, ensuring consistent expert-level output without rewriting prompts, while saving thousands of tokens through progressive disclosure that loads full instructions only when needed.

https://github.com/agentskills/agentskills
👍1
#python #antigravity #claude_code #codex #gemini #graphrag #knowledge_graph #leiden #openclaw #rag #skills #tree_sitter

Graphify is an AI tool that maps your entire project—code, docs, PDFs, images, and videos—into a searchable knowledge graph instead of forcing you to grep through files. You simply type `/graphify .` in your AI coding assistant (like Cursor, Claude, or Copilot) to get three outputs: an interactive HTML map, a report with key concepts and surprising connections, and a JSON file for instant queries. The main benefit to you is that you can instantly ask complex questions like "what connects auth to the database?" and get precise answers from the graph, saving hours of manual file searching and helping you understand your project's architecture faster.

https://github.com/safishamsi/graphify
👍1
#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
11
#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
💩3
#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
👍2
#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
👍1