AI Agents & Automation

RunWhen offers AI-powered Engineering Assistants designed to simplify troubleshooting for complex cloud systems. The platform empowers DevOps teams and SREs by suggesting what to run and when, automating investigations, and providing high-accuracy AI SRE capabilities. It helps unblock developers in pre-production and production environments, enabling faster MTTR with fewer escalations. RunWhen replaces traditional runbooks with agentic automation, making it easier to build and deploy diagnostic tools. The platform also helps keep observability budgets in check by automating diagnostics and reducing the need for extensive logging. With both foreground and background agents, RunWhen assists with root cause analysis, configuration, and continuous issue identification.

Llama-assistant is an AI-powered assistant designed to help users with daily tasks while prioritizing privacy. Powered by models such as Llama 3.2 and DeepSeek R1, it operates locally on your machine, ensuring no data is sent to external servers. The assistant can recognize voice commands, process natural language, and perform a variety of actions including text summarization, sentence rephrasing, question answering, and email writing. It supports both text-only and multimodal models like Moondream2 and LLaVA. Key features include voice recognition, natural language processing, customizable UI, and custom actions. The project is actively being developed with plans for wake word detection, offline STT, knowledge database integration, and multi-language support.

Odyssey Solutions is an offshore development company focused on making innovative technologies accessible, particularly in the energy and commodity sectors. They provide software consulting, digital transformation, and technology modernization services. The company also acts as an AI-focused investment firm, empowering startups that leverage AI and machine learning to solve challenges. Odyssey Solutions emphasizes a 'humans-first' approach, investing in ventures that prioritize humanity. Their offerings include Odyssey Analytics for energy and commodity consulting, and Odyx yHat for time series forecasting, designed for accuracy and ease of use in predicting prices and demand.

Tenkara is an AI-powered platform designed to fortify America's supply chains by providing manufacturers with advanced tools for operations and supply chain management. It automates critical functions like sourcing and qualifying raw materials, eliminating the need for cold calls or extensive manual searches. The platform also streamlines freight management by retrieving accurate DDP costs and booking with top carriers. Manufacturers can track orders in real-time, monitoring arrivals of materials and formulations, and receiving alerts for potential delays. Tenkara helps reduce procurement spend, accelerate raw material sourcing, and ensures 100% automatic tracking of COAs, SDSs, and other compliance documents. It serves as a force multiplier for lean operations teams, handling external work so manufacturers can focus on core business activities.

Terrakotta is an AI-powered platform designed to streamline commercial real estate prospecting. It offers an all-in-one solution for sourcing leads, making calls, and delivering personalized AI voicemails. Key features include an automated dialing system, a comprehensive property database with AI skip tracing, and a commercial real estate GPT for enhanced research. The platform integrates seamlessly with major CRM systems like Salesforce, HubSpot, and RealNex, enriching data with property details, owner history, and market insights. Terrakotta aims to boost outreach efficiency by allowing users to create lightning-fast voice clones and send customized AI voicemails, ensuring every connection is meaningful and saving hours of research time for commercial real estate professionals.

llama-models offers a comprehensive suite of utilities for working with Llama large language models. It provides easy accessibility to cutting-edge LLMs, fostering collaboration and advancements among developers, researchers, and organizations. Users can download model weights and tokenizers, list available models, describe model details, and run inference with various quantization modes like FP8 and Int4 to optimize memory footprint. The platform supports both Meta's direct downloads and Hugging Face access, ensuring broad ecosystem compatibility. It emphasizes responsible use with dedicated guides and reporting mechanisms for issues and risky content, promoting ethical AI development.

OGX, previously known as llama-stack, is an open-source agentic API server designed for building AI applications with maximum flexibility. It serves as a drop-in replacement for the OpenAI API, enabling developers to use any OpenAI-compatible client or agentic framework. OGX supports various models like Llama, GPT, Gemini, and Mistral, and can be deployed on diverse infrastructures, from local development with Ollama to production with vLLM or managed services. Key features include Chat Completions & Embeddings, a Responses API for server-side agentic orchestration with tool calling and file search, and support for Vector Stores & Files. It also offers multi-SDK compatibility, working natively with Anthropic and Google GenAI SDKs alongside OpenAI.

llm-graph-builder is an open-source tool designed to convert various forms of unstructured data, such as PDFs, DOCs, TXTs, YouTube videos, and web pages, into structured knowledge graphs. It utilizes Large Language Models (LLMs) and the LangChain framework to extract nodes, relationships, and properties, storing them in a Neo4j database. Users can upload files from local machines, GCS, S3 buckets, or web sources, select their preferred LLM model, and define custom or existing schemas for graph generation. Key features include graph visualization in Neo4j Bloom, conversational querying of data, and token usage tracking. It supports a wide range of LLMs including OpenAI, Gemini, Anthropic, and Ollama, and offers various embedding models for data vectorization.

Diaxel offers AI SMS agents designed to automate sales and support interactions, providing rapid responses in under 3 seconds. These agents are capable of qualifying leads, booking appointments directly via Google Calendar, and seamlessly syncing with popular CRM and advertising platforms like HubSpot, GoHighLevel, and Meta Ads. The service supports over 25 languages, making it versatile for diverse customer bases. Diaxel aims to enhance customer engagement and streamline business processes through efficient and automated SMS communication, reducing response times and improving lead management.

Khorus serves as a universal communication layer for intelligent systems, specifically designed to make AI agents interoperable on-chain. It provides the fastest way to deploy A2A (Agent-to-Agent) agents, powered by ERC-8004 identity and x402 payments. The platform allows users to create agent workforces, assign tasks, and run or sync operations. A key feature is the ability to tokenize creations and list them on a marketplace or launch them through Genesis with DAO Pools. Khorus integrates with various agent APIs and data tools, routing calls through x402 for automated signals, metered usage, and trustless on-chain settlement. It supports the design and deployment of complex dApps through coordinated agent workspaces, ensuring each agent is verified on-chain and can communicate across different chains and environments.

Bennu AI offers an autonomous AI agent designed to manage operations, deploy code, fix bugs, and maintain system uptime, allowing teams to focus on development. It provides zero-downtime monitoring, detecting crashes, restarting services, and archiving logs before users are impacted. The platform automates CI/CD processes, handling everything from Docker to production with minimal configuration. Bennu AI also integrates robust security features, scanning for misconfigurations, secrets, and access rights, blocking unsafe deployments in real-time. Users can deploy applications with a single prompt, describing their app in plain English for the AI to build, provision, and ship. It connects with existing stacks like GitHub, Docker, Kubernetes, and Terraform, orchestrating infrastructure, code, and operations with precision.

Liger-Kernel is an open-source collection of Triton kernels specifically engineered to optimize Large Language Model (LLM) training. Developed by LinkedIn, this tool boasts a 20% increase in multi-GPU training throughput and a 60% reduction in memory usage, enabling longer context lengths, larger batch sizes, and massive vocabularies. It offers optimized Post-Training kernels, including DPO, ORPO, CPO, and SimPO, which can deliver up to 80% memory savings for alignment and distillation tasks. Liger-Kernel is designed for ease of use, allowing users to patch Hugging Face models with a single line of code or compose custom models using its modules. It is compatible with multi-GPU setups like PyTorch FSDP, DeepSpeed, and DDP, and integrates with popular trainer frameworks such as Axolotl and Hugging Face Trainer. The kernels are exact, ensuring computational accuracy with rigorous unit tests and convergence testing.

llm-functions empowers developers to easily build powerful LLM tools and agents by leveraging familiar programming languages like Bash, JavaScript, and Python. This project simplifies the integration of Large Language Models with custom code through function calling, eliminating the need for complex setups. Users can execute system commands, process data, and interact with APIs directly from their LLMs. The platform automatically generates JSON declarations for tools based on comments within the code, streamlining the development process. It supports integration with AIChat and offers a Model Context Protocol (MCP) for external tool usage, making it a versatile solution for extending LLM capabilities.

Ren, developed by Refound, is an AI-powered accountability infrastructure designed to enhance leadership capabilities within organizations. It proactively assists managers in developing their teams by integrating directly into daily workflows via Slack and Microsoft Teams. Built on a decade of proven methodology, Ren helps managers with critical thinking, questioning assumptions, and evaluating work objectively. It surfaces important conversations, preps 1:1s, helps draft feedback, and ensures follow-through on commitments, leading to wider spans of control and reduced L&D spend. Ren aims to make every team member own their growth, fostering stronger relationships and improved execution.

LLMTornado is a comprehensive .NET provider-agnostic SDK designed for developers to build, orchestrate, and deploy AI agents and workflows with ease. It features built-in connectors to over 30 API providers, including Alibaba, Anthropic, Azure, Google, OpenAI, and many more, ensuring broad compatibility without dependencies on first-party SDKs. The library supports first-class local deployments with vLLM, Ollama, or LocalAI, and offers advanced agent orchestration capabilities with concepts like Orchestrator, Runner, and Advancer, including handoffs and parallel execution. LLMTornado accelerates development with its ability to write pipelines once and execute with any provider, and supports fully multimodal inputs and outputs (text, images, videos, documents, URLs, audio). It also integrates cutting-edge protocols like MCP and A2A, and connects to popular vector databases such as Chroma, PgVector, and Pinecone, making it enterprise-ready with guardrails and Open Telemetry support.

SPRYT's AI receptionist, Asa, revolutionizes healthcare appointment management by automating 80-90% of administrative tasks. Asa enables patients to effortlessly book, change, and pay for appointments via instant messaging platforms like WhatsApp, iMessage, and SMS, or even voice assistants like Alexa. Beyond simple scheduling, Asa incorporates behavioral insights and empirical linguistics to encourage attendance, particularly for preventative healthcare and diagnostic appointments. A key feature is its ability to predict no-shows, allowing clinics to proactively engage with underserved patients and reduce missed appointments, thereby alleviating strain on healthcare systems. This frees up medical administrative staff to focus on more critical tasks and patient care.

Magic CLI is a command line utility designed to make users more efficient in the terminal by leveraging Large Language Models (LLMs). Inspired by tools like Amazon Q and GitHub Copilot for CLI, it allows users to suggest commands, semantically search their shell history, and generate commands for specific tasks. The tool supports both local LLM providers like Ollama and cloud-based providers like OpenAI, offering flexibility in deployment. It relies on the `orch` library for LLM interactions, including execution and model alignment, and provides configuration options for different LLMs and their settings. While still in early development, it aims to streamline command-line workflows for developers.

LocalAIVoiceChat provides a completely local AI talk experience on your PC, integrating the powerful Zephyr 7B language model with real-time speech-to-text and text-to-speech libraries. It utilizes RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis, allowing for customizable AI personalities and voices. This experimental alpha software requires a GPU with around 8 GB VRAM and specific NVIDIA CUDA or AMD ROCm installations. While not production-ready, it offers a fast and engaging voice-based local chatbot experience, with ongoing updates to improve stability and model performance.

DAILA, the Decompiler Artificially Intelligent Language Assistant, provides a unified interface for AI systems within decompilers. This decompiler-agnostic plugin supports a wide range of AI models, including remote LLMs like GPT-4, Claude, and Gemini via LiteLLM, as well as local models such as VarBERT for variable renaming. It integrates with popular decompilers like IDA Pro, Ghidra, Binary Ninja, and angr-management, abstracting interactions through the LibBS library. DAILA offers both a GUI for interactive use and a scripting library for programmatic access, enabling tasks like function summarization, variable renaming, vulnerability identification, and free-form prompting. It can be installed via pip or used within a Docker container for offline environments.

MCP-SuperAssistant is an open-source Chrome extension designed to bridge the gap between AI platforms and the Model Context Protocol (MCP). It enables users to seamlessly integrate and execute MCP tools within popular AI interfaces such as ChatGPT, Perplexity, Grok, Gemini, Google AI Studio, and more. Key features include automatic detection and execution of MCP tool calls, integration of tool results back into conversations, and support for various AI platforms. The extension also offers advanced modes like auto-execute and auto-submit for enhanced automation, making it a powerful tool for developers and technical users looking to extend the functionality of their AI assistants.

Wonda is an AI-powered training platform designed to create tailored, immersive conversation simulations for healthcare and professional training. It enables educators to adapt scenarios, personalize conversational practice, and assess learning content with instant AI-powered feedback. The platform supports seamless deployment across devices, including desktop, mobile, and VR, allowing learners unlimited practice on their own schedule. Wonda focuses on competency-based education, offering hyper-realistic AI conversations with customizable characters, environments, and evaluation frameworks. It provides individual and group performance analytics, allowing learners to track growth and instructors to identify gaps, with up to 6 custom assessment criteria per simulation.

MemoryOS is designed to provide a robust memory operating system for personalized AI agents, drawing inspiration from memory management principles in traditional operating systems. It features a hierarchical storage architecture with four core modules: Storage, Updating, Retrieval, and Generation, ensuring comprehensive and efficient memory management. The tool boasts top performance in memory management, achieving significant improvements on long-term memory benchmarks. It offers a plug-and-play architecture for seamless integration of memory modules, including storage engines, update strategies, and retrieval algorithms. MemoryOS also supports universal LLM integration, working with a wide range of models like OpenAI, Deepseek, and Qwen, and provides an Agent Workflow Creation tool (MemoryOS-MCP) to inject long-term memory capabilities into various AI applications.

Wealize, operating under the Izertis brand, offers comprehensive technology consulting services focused on digital transformation, artificial intelligence, and cybersecurity. They are experts in propelling the technological evolution of businesses by combining strategic vision with cutting-edge technology. Their services include software engineering, cloud and infrastructure management, and developing AI and data solutions. Izertis aims to help organizations lead their industries through innovative and impactful technological solutions, ensuring they stay ahead of change and leverage data for strategic advantage.

MindGraph is an open-source, API-first proof-of-concept prototype for generating and querying an ever-expanding knowledge graph using AI. It is designed for natural language interactions, allowing users to input and output information in a human-readable format. The project serves as a flexible template for building and customizing CRM solutions, emphasizing ease of integration and extendibility through its modular architecture. Key features include entity management with CRUD operations on people, organizations, and their relationships, custom integration triggers via HTTP requests, and robust search capabilities. MindGraph is AI-ready, facilitating intelligent data processing and decision-making, and supports various database integrations including in-memory, NexusDB, NebulaGraph, and FalkorDB.