GitHub Trends
12.1K subscribers
16K 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 #ai #ast #claude_code #code_analysis #code_understanding #codebase_search #developer_tools #graph_database #knowledge_graph #llm #mcp #mcp_server #memgraph #monorepo #multi_language #python #rag #retrieval_augmented_generation #semantic_search #tree_sitter

Code-Graph-RAG is an open-source tool that reads a codebase, builds a graph of functions, classes, modules, and links, and lets you ask questions, find code, edit safely, and improve code in plain English. It supports many languages and can run as an MCP server for direct use with AI tools. Benefit: you can understand and change large mixed-language projects faster, with less manual searching and fewer mistakes.

https://github.com/vitali87/code-graph-rag
👍1
#typescript #agent #agent_harness #agent_os #agentic #ai #ai_agent #ai_agents #artificial_intelligence #claude_code #codex #electron #holaboss #holaos #llm #mcp #memory #model_context_protocol #runtime #typescript #workspace

holaOS is a local-first desktop workspace that lets you run agents like Claude Code, Codex, or its built-in agent together with your tools, files, apps, and shared memory. It supports macOS, Windows, and Linux, includes built-in models or your own keys, and can help you get work done with real browser control, app automation, and ready-made files. This can save you time because one setup works across agents, keeps your context, and lets you produce useful results without switching systems.

https://github.com/holaboss-ai/holaOS
👍1
#typescript #agents #claude_code #free #harness #harness_engineering #memory

This is a desktop app that turns coding CLIs into a team of agents that work together on your computer, with your own clone acting as the boss. It helps you by letting many agents share memory, send messages, and handle tasks while you can watch, guide, and approve important actions, so work can keep moving even when you are away.

https://github.com/chaitanyagiri/munder-difflin
👍2
#javascript #agent_skills #ai_agents #claude #claude_code #claude_code_plugin #cursor_rules #developer_tools #llm #prompt_engineering #yagni

Ponytail is a tool for AI coding agents that tells them to use the simplest safe solution, like native features, shared code, or one-line fixes, instead of extra code. It can cut code, cost, and time while keeping safety checks, validation, and accessibility. For you, this means cleaner code, faster results, and less wasted work.

https://github.com/DietrichGebert/ponytail
👍4
#go #agentic_coding #ai_gateway #anthropic #claude_code #codex #model_router #openai_compatible

This tool sends your AI requests through one smart local router that chooses the best model for each task and works with Anthropic, OpenAI, Gemini, and other models. It keeps your provider keys on your machine, supports easy setup, and lets you use it with tools like Claude Code, Codex, Cursor, or your own app. The benefit is simpler setup, better model choice, and safer key handling, which can save time and improve results.

https://github.com/workweave/router
👍1
#python #agent_skills #ai_writing #claude_code #codex #cursor #prompt_engineering #writing_tools

Humanizer rewrites AI-like text so it sounds more natural and human while keeping the meaning the same. It checks for common AI writing patterns, avoids inventing facts, can match your writing style, and leaves code, data, and links unchanged. The benefit to you is cleaner text that reads better and feels more real, with a preview of the rewrite and any remaining issues before you use it.

https://github.com/blader/humanizer
👍1👎1
#rust #ai #ai_coding_assistant #claude_code #codex #coding_agents #git #gitops #kilo_code #mcp #mcp_client #opencode #opencode_ai #opencode_skills #self_hosted #skills

Atlas is a local app for coding agents that records what each agent did, why it did it, and what code changed. It lets you use tools like Claude Code and Codex together, share memory between them, and keep your code, notes, and sessions on your own machine. This helps you switch agents without losing work, review past changes more easily, and protect your private project data.

https://github.com/pacifio/atlas
❤2👍1👌1
#rust #agents #claude_code #codex #developer_tools #git #worktrees

Worktrunk is a simple command-line tool for managing git worktrees, made for running many AI agents at the same time. It makes creating, switching, listing, merging, and cleaning up worktrees fast, and it can automate setup with hooks, commit messages, and shared build caches. The benefit to you is less manual git work, fewer conflicts, and an easier way to handle many parallel tasks.

https://github.com/max-sixty/worktrunk
❤3
#python #agent #ai #ai_agent #ai_tools #claude_code #codex #hermes_agent #hermes_skill #skills

oh-my-hermes adds a smart layer on top of Hermes Agent to turn unclear requests into clear steps, better model choices, and honest proof of what happened. It helps you plan, research, code, verify, and remember work more safely and efficiently, so you get faster results, cleaner handoffs, and less guesswork.

https://github.com/rlaope/oh-my-hermes
#python #3d_models #agent_skills #ai_agents #ai_art #blender #claude_code #claude_skills #codex #game_assets #game_development #generative_ai #image_generation #maya #mcp #model_context_protocol #skills_sh #unity #unreal_engine #video_generation #zbrush

Scenario Agent Skills is a collection of guides that teaches AI coding agents to create and edit images, video, audio, game assets, and 3D content using Scenario. It also helps agents review results, maintain consistent styles, and train custom models. Separate expert tools guide agents in creative software and game engines such as Blender, Maya, Unity, and Unreal Engine. This is useful for people making games, entertainment, and other creative projects who want AI agents to help with content production.

https://github.com/scenario-labs/skills
👍2
#typescript #agents #claude_code #code_review #codex #obsidian #opencode #pi_mono #plan_mode #skills

Plannotator is a local, browser-based tool for reviewing work from AI coding agents. It lets users annotate plans, documents, messages, and HTML, review code changes and pull requests, and send feedback directly to an agent. Its inbox brings together questions, files, and review requests from multiple agents while they continue working. This helps users stay involved in agent work, make decisions, and give clear feedback. Plans, annotations, and other review data stay local by default.

https://github.com/backnotprop/plannotator
#go #agent_orchestration #agentic_workflow #ai_agents #ai_coding #claude_code #code_review #codebuddy #codex #coding_agents #cursor #developer_tools #human_on_the_loop #llm #mcp #multi_agent #sdlc #self_hosted #sop #workflow_automation #workflow_engine

LoopForge is a self-hosted workspace that helps teams build software with coding agents. Users can chat with agents to explore ideas, fix code, and create pull requests, or run repeatable workflows that combine agent roles, scripts, and human approvals. It provides sandboxed workspaces, progress tracking, logs, and cost reports. This helps teams apply consistent checks, review changes, and keep people in control of what is delivered. A local version also lets individual developers use built-in workflows in supported coding assistants.

https://github.com/Tencent/LoopForge
👍1
#python #ai_security #anthropic #application_security #bug_bounty #bugbounty #bugcrowd #claude #claude_code #claude_skills #ethical_hacking #hackerone #offensive_security #pentesting #red_team #security_tools #web_security

Claude-BugHunter is a collection of skills that helps AI coding agents find and report security weaknesses in authorized targets. It covers websites, APIs, cloud services, and internet-facing enterprise systems. The bundle guides researchers through gathering information, prioritizing targets, testing, validating findings, and writing reports. It also provides commands, engagement organization tools, and Burp Suite integration. This helps security teams apply known testing patterns, keep work within scope, and produce clearer, better-supported reports.

https://github.com/elementalsouls/Claude-BugHunter
👍1
#python #agent_evaluation #agent_plugins #agent_security #agent_skills #agentic_ai #benchmark #claude_code #codex #evaluate #evaluation #plugin #plugin_evaluation #security_scanner #skill_eval #skill_evals #skill_evaluation #skill_evaluator #skills

SkillEvaluator checks the quality and security of AI agent skills, which are folders of instructions and supporting files. It can find repeated or overlapping guidance and compare agent task results with and without a skill. Its reports help developers identify problems and understand whether a skill improves performance. It can also check changed skills during the software review process.

https://github.com/NVIDIA/SkillEvaluator
1👍2
#python #agent_skills #ai_agents #audio_processing #captions #claude_code #codex #coding_agent #cursor #ffmpeg #gemini_cli_extension #loudness_normalization #mcp #mcp_server #model_context_protocol #python #subtitles #transcoding #video #video_editing #whisper

ffmpeg-skill gives AI coding agents tools to edit video and audio using FFmpeg on a local computer. It can cut and join clips, remove silence, add captions, clean up audio, resize video, and export files for different platforms. It also measures files before editing and checks results afterward, helping reduce mistakes and unnecessary re-encoding. It works offline without cloud services or API keys, so footage does not need to be uploaded.

https://github.com/kajisho5/ffmpeg-skill
👍2