#python #agent_control_plane #agent_ops #ai_agents #codex #long_running_agents #loop_engineering #loopx #workflow_automation

LoopX is a local control plane for long-running AI agent work. It keeps goals, tasks, evidence, quota, and handoffs in one place so work stays clear, restartable, and easier to pass between agents and people; the benefit is less lost context, safer progress, and easier review across long projects.

https://github.com/huangruiteng/loopx

#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

#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

#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

#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

#python #cli #consumer_gpu #dpo #fine_tuning #gguf #huggingface #llm #llmops #local_ai #local_llm #lora #low_vram #machine_learning #ollama #peft #python #pytorch #qlora #sft #transformers

Soup is a tool that helps you fine-tune and post-train large language models with one command, using one config file and little setup. It can work on a local GPU, even a 4 GB laptop GPU for an 8B model with layer streaming, so you can train without SSH or cloud hassle. This saves time, reduces setup pain, and makes model training easier to start and manage.

https://github.com/MakazhanAlpamys/Soup

#python #agent #agent_security #ai_infra #ai_red_teaming #ai_security #llm #llm_evaluation #llm_jailbreak #llm_security #mcp_scan #openclaw_security #prompt_injection #prompt_security #scanner #security #security_tools #skill_scanner #skills_security #vulnerability

A.I.G (AI-Infra-Guard) is a Tencent Zhuque Lab tool for AI red teaming and security checks. It scans AI infrastructure, MCP servers, agent skills, and jailbreak risks, and it can run with Docker, a web UI, or an API. This helps you find weak points early, understand real security risks, and fix problems before they affect your AI systems.

https://github.com/Tencent/AI-Infra-Guard

#python

This is a free research tool for removing a model’s refusal behavior while trying to keep its main language ability. It gives you an easy web app, a command line tool, a Python API, and tests to study how safety parts work and how they change. For you, the benefit is simple: you can run clear checks, compare models, save time, and choose how much control and risk you want when working with local AI models.

https://github.com/elder-plinius/OBLITERATUS

#python

This is a read-only list of community plugins for Claude Cowork and Claude Code. Each plugin was submitted through the official form, checked for security, and approved before being added. You can install them from the Claude plugins site or by adding the marketplace in Claude Code. The benefit is simple: you get a safe, approved place to find useful plugins without needing to sort through unverified ones.

https://github.com/anthropics/claude-plugins-community

#python #agent_skills #ai_note_taking #ai_second_brain #claude_code #claude_code_skill #claude_memory #claude_plugin #karpathy_llm_wiki #knowledge_graph #knowledge_management #note_taking #notion_alternative #obsidian #obsidian_ai #obsidian_plugin #obsidian_second_brain #open_source #personal_knowledge_management #pkm #second_brain

Claude-obsidian helps you build a local Obsidian knowledge base that keeps getting better as you use it. It saves sources, makes linked notes, gives grounded answers from your own vault, and keeps your files under your control. This helps you find trusted information faster, avoid losing evidence, and grow a clean, useful knowledge system without relying on a cloud database.

https://github.com/AgriciDaniel/claude-obsidian

#python

Marin is an open platform for building large language models, with tools for data cleaning, training, and testing. It saves every step so people can learn from both success and failure. You can use it to train small or very large models and follow clear guides to get started. The benefit is faster, more transparent model development, plus reusable code and examples that help you build your own AI projects more easily.

https://github.com/marin-community/marin