#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
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
GitHub
GitHub - cactus-compute/needle: 14MB foundation model for tiny devices; phones, wearables, smart home, and robots.
14MB foundation model for tiny devices; phones, wearables, smart home, and robots. - 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
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
GitHub
GitHub - MakazhanAlpamys/Soup: Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. - MakazhanAlpamys/Soup
❤1
#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
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
GitHub
GitHub - Tencent/AI-Infra-Guard: A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan…
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation. - Tencent/AI-Infra-Guard
👍2
#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
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
GitHub
GitHub - elder-plinius/OBLITERATUS: OBLITERATE THE CHAINS THAT BIND YOU
OBLITERATE THE CHAINS THAT BIND YOU. Contribute to elder-plinius/OBLITERATUS development by creating an account on GitHub.
#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
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
GitHub
GitHub - anthropics/claude-plugins-community: Community plugin marketplace for Claude Cowork and Claude Code. Read-only mirror…
Community plugin marketplace for Claude Cowork and Claude Code. Read-only mirror — submit plugins at clau.de/plugin-directory-submission. - 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
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
GitHub
GitHub - AgriciDaniel/claude-obsidian: Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads…
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, perso...
#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
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
GitHub
GitHub - marin-community/marin: Open-source framework for the research and development of foundation models.
Open-source framework for the research and development of foundation models. - marin-community/marin
👍1
#python #cybersecurity #cybersecurity_tools #email_osint #ethical_hacking #ethical_hacking_tools #identification #infosec #osint #osint_email #osint_tool #osint_tools #osint_username #pentesting #python #redteam_tools #redteaming #threat_intelligence
User Scanner is a tool for checking emails and usernames across 455+ sites to find accounts, profile details, links, and other public traces. It can also scan in bulk, make reports, use proxies, and connect to AI tools. This helps you save time, find digital footprints faster, and gather useful information from one place.
https://github.com/kaifcodec/user-scanner
User Scanner is a tool for checking emails and usernames across 455+ sites to find accounts, profile details, links, and other public traces. It can also scan in bulk, make reports, use proxies, and connect to AI tools. This helps you save time, find digital footprints faster, and gather useful information from one place.
https://github.com/kaifcodec/user-scanner
GitHub
GitHub - kaifcodec/user-scanner: 🕵️♂️ (2-in-1) Email & Username OSINT suite for deep data extraction just from a single Email/Username.…
🕵️♂️ (2-in-1) Email & Username OSINT suite for deep data extraction just from a single Email/Username. Analyzes 465+ actively maintained scan vectors (175+ email / 290+ username) for secur...
⚡1
#python
Microduck RL gives training environments for a small biped robot, so you can teach it walking, standing up, sitting, tricks, and roller tasks in simulation, then export the learned policy to run on the real robot. It includes realistic motor physics, backlash, and random changes to help sim-to-real transfer. The benefit to you is faster robot training, easier testing, and safer deployment because one shared setup lets different skills swap on the robot without changing the runtime.
https://github.com/pollen-robotics/microduck_rl
Microduck RL gives training environments for a small biped robot, so you can teach it walking, standing up, sitting, tricks, and roller tasks in simulation, then export the learned policy to run on the real robot. It includes realistic motor physics, backlash, and random changes to help sim-to-real transfer. The benefit to you is faster robot training, easier testing, and safer deployment because one shared setup lets different skills swap on the robot without changing the runtime.
https://github.com/pollen-robotics/microduck_rl
GitHub
GitHub - pollen-robotics/microduck_rl: RL training environments for Microduck (mjlab)
RL training environments for Microduck (mjlab). Contribute to pollen-robotics/microduck_rl development by creating an account on GitHub.
👍2
#python #chinese #disclosure #obsidian #patent #skill
This tool helps you turn project files into clear patent drafts for invention, utility model, and design patents, and it can also explain patents in simple words. It can find patent points, make charts and Word files, build line drawings, organize patent notes, and help with search, policy updates, and office reply drafts. The benefit to you is faster patent work, clearer patent reading, and better support for writing, revising, and reusing patent knowledge.
https://github.com/handsomestWei/patent-disclosure-skill
This tool helps you turn project files into clear patent drafts for invention, utility model, and design patents, and it can also explain patents in simple words. It can find patent points, make charts and Word files, build line drawings, organize patent notes, and help with search, policy updates, and office reply drafts. The benefit to you is faster patent work, clearer patent reading, and better support for writing, revising, and reusing patent knowledge.
https://github.com/handsomestWei/patent-disclosure-skill
GitHub
GitHub - handsomestWei/patent-disclosure-skill: 中国专利.skill:专利点挖掘与交底书(发明/实用/外观)编写,通俗解读专利,嗅探政策动向,辅助审查答复。
中国专利.skill:专利点挖掘与交底书(发明/实用/外观)编写,通俗解读专利,嗅探政策动向,辅助审查答复。 - handsomestWei/patent-disclosure-skill
#python #automation #bot #clarifai #instagram #python #script #selenium
This project is about using AI and Python tools to automate social media tasks like likes, comments, and followers. The main benefit for you is learning practical automation ideas, tools, and examples that can save time and help you build your own bots, but it also warns that heavy use can lead to bans.
https://github.com/InstaPy/InstaPy
This project is about using AI and Python tools to automate social media tasks like likes, comments, and followers. The main benefit for you is learning practical automation ideas, tools, and examples that can save time and help you build your own bots, but it also warns that heavy use can lead to bans.
https://github.com/InstaPy/InstaPy
GitHub
GitHub - InstaPy/InstaPy: 📷 Instagram Bot - Tool for automated Instagram interactions
📷 Instagram Bot - Tool for automated Instagram interactions - InstaPy/InstaPy
👌2❤1👍1🔥1
#python #ai #audiobook #cuda #dubbing #elevenlabs_alternative #huggingface #local_first #mlx #omnivoice_studio #speech_to_text #tauri #text_to_speech #transcription #translate #tts #voice_ai #voice_cloning #voice_generation #voicestudio #workflow
VoiceStudio is a local app for voice cloning, dubbing, dictation, and long audio work on macOS, Windows, and Linux. It works offline after setup, keeps your voices and files on your machine by default, and gives you many engines and languages to choose from. This helps you make speech faster, protect privacy, and avoid accounts, subscriptions, or usage limits.
https://github.com/debpalash/VoiceStudio
VoiceStudio is a local app for voice cloning, dubbing, dictation, and long audio work on macOS, Windows, and Linux. It works offline after setup, keeps your voices and files on your machine by default, and gives you many engines and languages to choose from. This helps you make speech faster, protect privacy, and avoid accounts, subscriptions, or usage limits.
https://github.com/debpalash/VoiceStudio
GitHub
GitHub - debpalash/VoiceStudio: VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design…
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages. - debpalash/...
👌2
#python #bge #colbert #data_pipeline #deep_learning #embeddings #inference #inference_server #information_retrieval #llm #ml #mlops #natural_language_processing #nlp #python #reranking #retrieval #retrieval_augmented_generation #semantic_search #splade #vector_search
SIE is a self-hosted engine for AI agents that runs many open models from one cluster in your cloud. It can handle search, document cleanup, structured output, safety checks, and agent actions through one OpenAI-style API. This helps you use fewer services, keep control of your data, and make setup simpler and cheaper.
https://github.com/superlinked/sie
SIE is a self-hosted engine for AI agents that runs many open models from one cluster in your cloud. It can handle search, document cleanup, structured output, safety checks, and agent actions through one OpenAI-style API. This helps you use fewer services, keep control of your data, and make setup simpler and cheaper.
https://github.com/superlinked/sie
GitHub
GitHub - superlinked/sie: Open-source inference server and production cluster for all the models your agent needs.
Open-source inference server and production cluster for all the models your agent needs. - superlinked/sie
👍1👎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
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
GitHub
GitHub - blader/humanizer: Agent skill that removes signs of AI-generated writing from text
Agent skill that removes signs of AI-generated writing from text - blader/humanizer
👍1👎1