Heretic is a tool that removes censorship from transformer-based language models without expensive post-training. It combines directional ablation with a TPE-based parameter optimizer to automatically find high-quality abliteration parameters. Users can easily decensor language models without needing to understand transformer internals. Heretic supports most dense models and provides features for research into model semantics. The tool offers flexible ablation weight kernels and separate ablation parameters for different components, improving compliance/quality tradeoff. Heretic was developed from scratch and does not reuse code from other projects.

Otter Camp is an open source work management tool designed for AI agent teams. It provides a centralized platform for managing AI agents, ensuring that important context is not lost, enabling quick hiring and firing of agents, maintaining a single pipeline for all work types, keeping context organized within projects, facilitating work review processes, tracking team activities, and offering self-hosted data security. The tool integrates with OpenClaw to run agents and provides a user-friendly interface for managing agent teams efficiently.

IntentKit is an autonomous agent framework that enables the creation and management of AI agents with capabilities including blockchain interactions, social media management, and custom skill integration. It supports multiple agents, autonomous agent management, blockchain integration, social media integration, extensible skill system, and plugin system. The project is in alpha stage and not recommended for production use. It provides quick start guides for Docker and local development, integrations with Twitter and Coinbase, configuration options using environment variables or AWS Secrets Manager, project structure with core application code, entry points, configuration management, database models, skills, skill sets, and utility functions. Developers can add new skills by creating, implementing, and registering them in the skill directory.

Shannon is an AI pentester that delivers actual exploits, not just alerts. It autonomously hunts for attack vectors in your code, then uses its built-in browser to execute real exploits, such as injection attacks, and auth bypass, to prove the vulnerability is actually exploitable. Shannon closes the security gap by acting as your on-demand whitebox pentester, providing concrete proof of vulnerabilities to let you ship with confidence. It is a core component of the Keygraph Security and Compliance Platform, automating penetration testing and compliance journey. Shannon Lite achieves a 96.15% success rate on a hint-free, source-aware XBOW benchmark.

Julep is an advanced platform for creating stateful and functional AI apps powered by large language models. It offers features like statefulness by design, automatic function calling, production-ready deployment, cron-like asynchronous functions, 90+ built-in tools, and the ability to switch between different LLMs easily. Users can build AI applications without the need to write code for embedding, saving, and retrieving conversation history, and can connect to third-party applications using Composio. Julep simplifies the process of getting started with AI apps, whether they are conversational, functional, or agentic.

Tambourine is a personal voice interface tool that allows users to speak naturally and have their words appear wherever the cursor is. It is powered by customizable AI voice dictation, providing a universal voice-to-text interface for emails, messages, documents, code editors, and terminals. Users can capture ideas quickly, type at the speed of thought, and benefit from AI formatting that cleans up speech, adds punctuation, and applies personal dictionaries. Tambourine offers full control and transparency, with the ability to customize AI providers, formatting, and extensions. The tool supports dual-mode recording, real-time speech-to-text, LLM text formatting, context-aware formatting, customizable prompts, and more, making it a versatile solution for dictation and transcription tasks.

LLMGA (Multimodal Large Language Model-based Generation Assistant) is a tool that leverages Large Language Models (LLMs) to assist users in image generation and editing. It provides detailed language generation prompts for precise control over Stable Diffusion (SD), resulting in more intricate and precise content in generated images. The tool curates a dataset for prompt refinement, similar image generation, inpainting & outpainting, and visual question answering. It offers a two-stage training scheme to optimize SD alignment and a reference-based restoration network to alleviate texture, brightness, and contrast disparities in image editing. LLMGA shows promising generative capabilities and enables wider applications in an interactive manner.

BioAgents AgentKit is an advanced AI agent framework tailored for biological and scientific research. It offers powerful conversational AI capabilities with specialized knowledge in biology, life sciences, and scientific research methodologies. The framework includes state-of-the-art analysis agents, configurable research agents, and a variety of specialized agents for tasks such as file parsing, research planning, literature search, data analysis, hypothesis generation, research reflection, and user-facing responses. BioAgents also provides support for LLM libraries, multiple search backends for literature agents, and two backends for data analysis. The project structure includes backend source code, services for chat, job queue system, real-time notifications, and JWT authentication, as well as a frontend UI built with Preact.

LlamaBot is an open-source AI coding agent that rapidly builds MVPs, prototypes, and internal tools. It works for non-technical founders, product teams, and engineers by generating working prototypes, embedding AI directly into the app, and running real workflows. Unlike typical codegen tools, LlamaBot can embed directly in your app and run real workflows, making it ideal for collaborative software building where founders guide the vision, engineers stay in control, and AI fills the gap. LlamaBot is built for moving ideas fast, allowing users to prototype an AI MVP in a weekend, experiment with workflows, and collaborate with teammates to bridge the gap between non-technical founders and engineering teams.

Zeus is a library for measuring the energy consumption of Deep Learning workloads and optimizing their energy consumption. It provides functionalities for energy and power measurement, time and energy optimization, device abstraction, utility functions, and more. Zeus is part of The ML.ENERGY Initiative and has been recognized in various research papers and conferences. It offers a Docker image with all dependencies, working examples for integration, and ongoing research to enhance its capabilities.

OpenKF (Open Knowledge Flow) is an online intelligent customer service system. It is an open-source customer service system based on OpenIM, supporting LLM (Local Knowledgebase) customer service and multi-channel customer service. It is easy to integrate with third-party systems, deploy, and perform secondary development. The system provides features like login page, config page, dashboard page, platform page, and session page. Users can quickly get started with OpenKF by following the installation and run instructions. The architecture follows MVC design with a standardized directory structure. The community encourages involvement through community meetings, contributions, and development. OpenKF is licensed under the Apache 2.0 license.

GPT4Point is a unified framework for point-language understanding and generation. It aligns 3D point clouds with language, providing a comprehensive solution for tasks such as 3D captioning and controlled 3D generation. The project includes an automated point-language dataset annotation engine, a novel object-level point cloud benchmark, and a 3D multi-modality model. Users can train and evaluate models using the provided code and datasets, with a focus on improving models' understanding capabilities and facilitating the generation of 3D objects.

World Monitor is a real-time global intelligence dashboard powered by AI. It offers news aggregation, geopolitical monitoring, and infrastructure tracking in a unified interface. The tool provides interactive global maps, AI-powered intelligence summaries, real-time data layers on geopolitics, military, infrastructure, and market intelligence. It also includes live news feeds, video streams, signal aggregation, anomaly detection, story sharing, and social export capabilities. The tool is designed for speed, assumes failure, and emphasizes multi-signal correlation for accurate insights. It offers source credibility and tiering for RSS feeds, edge function architecture for data processing, and caching architecture for performance optimization.

LLMos is an operating system designed for physical AI agents, providing a hybrid runtime environment where AI agents can perceive, reason, act on hardware, and evolve over time locally without cloud dependency. It allows natural language programming, dual-brain architecture for fast instinct and deep planner brains, markdown-as-code for defining agents and skills, and supports swarm intelligence and cognitive world models. The tool is built on a tech stack including Next.js, Electron, Python, and WebAssembly, and is structured around a dual-brain cognitive architecture, volume system, HAL for hardware abstraction, applet system for dynamic UI, and dreaming & evolution for robot improvement. The project is in Phase 1 (Foundation) and aims to move into Phase 2 (Dual-Brain & Local Intelligence), with contributions welcomed under the Apache 2.0 license by Evolving Agents Labs.

VoltAgent is an open-source TypeScript framework designed for building and orchestrating AI agents. It simplifies the development of AI agent applications by providing modular building blocks, standardized patterns, and abstractions. Whether you're creating chatbots, virtual assistants, automated workflows, or complex multi-agent systems, VoltAgent handles the underlying complexity, allowing developers to focus on defining their agents' capabilities and logic. The framework offers ready-made building blocks, such as the Core Engine, Multi-Agent Systems, Workflow Engine, Extensible Packages, Tooling & Integrations, Data Retrieval & RAG, Memory management, LLM Compatibility, and a Developer Ecosystem. VoltAgent empowers developers to build sophisticated AI applications faster and more reliably, avoiding repetitive setup and the limitations of simpler tools.

ccprompts is a collection of ~70 Claude Code commands for software development workflows with agent generation capabilities. It includes safety validation and can be used directly with Claude Code or adapted for specific needs. The agent template system provides a wizard for creating specialized sub-agents (e.g., security auditors, systems architects) with standardized formatting and proper tool access. The repository is under active development, so caution is advised when using it in production environments.

Heretic is a tool that removes censorship from transformer-based language models without expensive post-training. It combines directional ablation with a TPE-based parameter optimizer to automatically find high-quality abliteration parameters. Users can easily decensor language models without needing to understand transformer internals. Heretic supports most dense models and provides features for research into model semantics. The tool offers flexible ablation weight kernels and separate ablation parameters for different components, improving compliance/quality tradeoff. Heretic was developed from scratch and does not reuse code from other projects.

This repository is dedicated to summarizing papers related to large language models with the field of law. It includes applications of large language models in legal tasks, legal agents, legal problems of large language models, data resources for large language models in law, law LLMs, and evaluation of large language models in the legal domain.

This repository is a comprehensive guide for individuals looking to start and improve their skills in Large Language Models (LLMs) without an advanced background in the field. It provides free resources, online courses, books, articles, and practical tips to become an expert in machine learning. The guide covers topics such as terminology, transformers, prompting, retrieval augmented generation (RAG), and more. It also includes recommendations for podcasts, YouTube videos, and communities to stay updated with the latest news in AI and LLMs.

AI Verify is an AI governance testing framework and software toolkit that validates the performance of AI systems against internationally recognised principles through standardised tests. It offers a new API Connector feature to bypass size limitations, test various AI frameworks, and configure connection settings for batch requests. The toolkit operates within an enterprise environment, conducting technical tests on common supervised learning models for tabular and image datasets. It does not define AI ethical standards or guarantee complete safety from risks or biases.

This repository contains a collection of research papers related to watermarking techniques for text and images, specifically focusing on large language models (LLMs). The papers cover various aspects of watermarking LLM-generated content, including robustness, statistical understanding, topic-based watermarks, quality-detection trade-offs, dual watermarks, watermark collision, and more. Researchers have explored different methods and frameworks for watermarking LLMs to protect intellectual property, detect machine-generated text, improve generation quality, and evaluate watermarking techniques. The repository serves as a valuable resource for those interested in the field of watermarking for LLMs.

This repository contains code for reproducing experiments on lie detection in black-box LLMs by asking unrelated questions. It includes Q/A datasets, prompts, and fine-tuning datasets for generating lies with language models. The lie detectors rely on asking binary 'elicitation questions' to diagnose whether the model has lied. The code covers generating lies from language models, training and testing lie detectors, and generalization experiments. It requires access to GPUs and OpenAI API calls for running experiments with open-source models. Results are stored in the repository for reproducibility.

The GraphRAG project is a data pipeline and transformation suite designed to extract meaningful, structured data from unstructured text using LLMs. It enhances LLMs' ability to reason about private data. The repository provides guidance on using knowledge graph memory structures to enhance LLM outputs, with a warning about the potential costs of GraphRAG indexing. It offers contribution guidelines, development resources, and encourages prompt tuning for optimal results. The Responsible AI FAQ addresses GraphRAG's capabilities, intended uses, evaluation metrics, limitations, and operational factors for effective and responsible use.

LangTest is a comprehensive evaluation library for custom LLM and NLP models. It aims to deliver safe and effective language models by providing tools to test model quality, augment training data, and support popular NLP frameworks. LangTest comes with benchmark datasets to challenge and enhance language models, ensuring peak performance in various linguistic tasks. The tool offers more than 60 distinct types of tests with just one line of code, covering aspects like robustness, bias, representation, fairness, and accuracy. It supports testing LLMS for question answering, toxicity, clinical tests, legal support, factuality, sycophancy, and summarization.

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, and exciting jailbreak methods on Large Language Models (LLMs). The repository contains papers, codes, datasets, evaluations, and analyses related to jailbreak attacks on LLMs. It serves as a comprehensive resource for researchers and practitioners interested in exploring various jailbreak techniques and defenses in the context of LLMs. Contributions such as additional jailbreak-related content, pull requests, and issue reports are welcome, and contributors are acknowledged. For any inquiries or issues, contact [email protected]. If you find this repository useful for your research or work, consider starring it to show appreciation.