GitHub Trends
11.3K subscribers
15.9K 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 #agent_security #ai_agents #ai_security #benchmark #claude #claude_code #codex #cursor #llm_security #mcp #model_context_protocol #prompt_injection #threat_detection

ADR is an enterprise security system for AI agents that watches what agents do, tests them for attacks, detects risky behavior, and is being used in production at Uber; its paper was accepted to MLSys 2026. The benefit to you is better protection for AI tools like Cursor, Claude Code, and Codex, plus a way to find unsafe actions before they cause harm.

https://github.com/uber/ADR
#typescript

Cloudflare Computer is a preview tool that gives you a file system plus a place to run code, with the main state kept safely in SQLite inside a Durable Object.[Text] You can use it with a container, a shell worker, or a JavaScript worker, and each option lets you work with files and run tasks in a different way.[Text] The benefit is easier building and testing of apps, agents, and prototypes with one shared workspace, but it is not ready for production yet.[Text]

https://github.com/cloudflare/computer
👍1
#rust

celld is an open-source tool that lets you run Cloudflare Workers and Durable Objects on your own machines, with each object stored as its own SQLite database and synced through your S3-compatible bucket.[Text] This gives you easy scaling, less database contention, and smaller failure impact, while idle objects use almost no resources, which can help you save money and improve reliability.[Text]

https://github.com/denoland/celld
#python #agent_memory #ai #ai_governance #ai_infrastructure #artificial_intelligence #context_engineering #context_graphs #data_engineering #decision_intelligence #developer_tools #explainable_ai #generative_ai #graph_rag #knowledge_graph #llm #ontology #provenance #python #reasoning #semantic_search

Semantica is an open-source tool that turns messy data into clear, connected knowledge graphs for AI. It helps you track where facts came from, explain AI decisions, find conflicts, and keep systems auditable and trustworthy. This benefits you by making AI easier to trust, easier to check, and safer to use in important work like finance, healthcare, legal, and government.

https://github.com/semantica-agi/semantica
👍1
#other #cti #cyberthreatintelligence #osint #osint_tools_list #socmint

This is a free OSINT collection with tools and resources for many research areas like people search, flight tracking, domains, phishing, malware, images, video, business, legal records, and mapping. It helps you find the right tool faster for investigation work, and the CC0 license means you can use, change, and share it freely.

https://github.com/K2SOsint/Legendary_OSINT
👍1
#clojure

Do not spend money on the SWARM token. SwarmForge is a local tmux tool that lets multiple AI agents work together in separate worktrees, with roles like coder, cleaner, architect, and QA; it helps you build software faster and with fewer conflicts. The benefit to you is organized teamwork, safer handoffs, and a choice of small, medium, or full workflows for different project sizes.

https://github.com/unclebob/swarm-forge
#typescript

Prime Agent is an open-source coding and research tool for long jobs. It uses a persistent Python workspace, built-in subagents, and saved memory so work can keep going across breaks. You can install it on macOS or Linux, start it in a project folder, and use it to run commands, edit files, and keep goals active. This helps you save time, keep progress, and handle bigger tasks with less manual work.

https://github.com/PrimeIntellect-ai/prime-agent
1
#other

This repo gives 151 real DevOps, SRE, and cloud interview write-ups from 85 companies, with questions on Kubernetes, Docker, Terraform, AWS, Azure, GCP, CI/CD, Linux, scripting, and SRE basics. It helps you study smarter by searching for a company or role, comparing many interview styles, and spotting common topics before your interview.

https://github.com/litu54/DevOps-Interview-Guide
#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
#python

Harvey LAB is an open-source benchmark that tests how well AI agents can do real legal work, not just answer legal questions. It gives each agent instructions, case documents, and a required work product, then scores the result with expert rubrics. LAB includes more than 1,200 tasks across 24 legal practice areas. This helps you compare models, check agent quality, and build better legal AI tools with a realistic standard.

https://github.com/harveyai/harvey-labs
👍21
#typescript

Paperclip is an open-source tool that helps you manage many AI agents like a company, with goals, roles, budgets, approvals, and audit logs. It lets you assign work, track costs, prevent runaway spending, and watch agents run from one dashboard, which saves time and gives you better control over automated work.

https://github.com/paperclipai/paperclip
4
#html

This tool helps you make clean, branded diagrams fast, with 27 diagram types and no need for Figma or design guesswork. It can read your website, copy your colors and fonts, and turn them into diagrams in about 60 seconds, so you save time and get visuals that match your brand.

https://github.com/cathrynlavery/diagram-design
#kotlin #agent #agentic_ai #agents #ai #ai_agents #aiagentframework #genai #generative_ai #java #kotlin #llms #multi_agents #multi_agents_orchestration #multi_agents_system #spring

Embabel is a Java and Kotlin framework for building AI agents on the JVM with Spring, using typed goals, actions, and conditions instead of hard-coded prompt chains. It plans and replans at runtime, which helps you build more flexible, testable, and reusable agent flows while still fitting into existing enterprise code. The benefit to you is faster AI app development with stronger type safety, easier testing, and simpler use of LLMs, tools, and domain models in one system.

https://github.com/embabel/embabel-agent
#python #ai_agent #aippt #office #powerpoint #powerpoint_generation #ppt #pptx #presentation #slide #slides

PPT Master is a free, open-source tool that turns PDFs, DOCX files, web pages, or text into a real, editable PowerPoint with native shapes, charts, tables, animations, and speaker notes. You run it locally with an AI tool, so your files stay on your machine and you avoid platform lock-in. The benefit to you is faster slide creation with a deck you can still edit in PowerPoint, instead of a flat image file.

https://github.com/hugohe3/ppt-master
#python #cactus #gemini #gemma #llm #on_device_ai

Needle 2 is a very small tool-calling AI model that can run on low memory, work offline, and return structured results like JSON instead of free text. It helps you build apps that call tools, extract data, and fine-tune models more safely and easily, even on devices with limited RAM.

https://github.com/cactus-compute/needle
#rust

Switchyard is a Rust proxy and library for LLM traffic that lets coding agents keep using their normal OpenAI or Anthropic API while requests are routed to different model backends and translated as needed. It can also split traffic for testing, measure latency and errors, and use custom routing rules, which helps you run or compare models more easily without changing your agent setup.

https://github.com/NVIDIA-NeMo/Switchyard
👍21