Castor: A Self-Hosted AI Agent for Business Workflows
Castor is an open-source, self-hosted AI agent designed for business operations like customer service, internal automation, and knowledge retrieval. It supports various OpenAI-compatible LLMs, including local models, and emphasizes data privacy by keeping data on the user's infrastructure.
PentesterFlow/agent: AI-Powered Offensive Security CLI Tool
PentesterFlow/agent is an open-source, agentic AI command-line interface (CLI) designed for offensive security tasks. It assists penetration testers and bug hunters with recon, enumeration, validation, evidence collection, and reporting, while maintaining human oversight.
Opilot: Integrate Ollama Models into GitHub Copilot Chat
Opilot is a VS Code extension that allows users to run Ollama models, both local and cloud-based, directly within the GitHub Copilot Chat interface. It provides features like model management, per-model settings, tool calling, and vision support.
KiwiFS: A Markdown Filesystem for AI Agents and Teams
KiwiFS is an open-source Markdown filesystem designed for AI agents and human teams, offering features like search, versioning, and structured data capabilities. It aims to bridge the gap between human-readable Markdown files and the structured data needs of AI agents.
ANARCHY: A Fully Local AI Shell for Offline Development
ANARCHY is an open-source, fully local AI shell that operates without cloud services or API keys. It integrates Ollama and GGUF models, RAG, voice input, and a task scheduler, offering a comprehensive offline AI development environment across multiple operating systems.
Gnoma: A Provider-Agnostic Agentic Coding Assistant in Go
Gnoma is an agentic coding assistant written in Go that offers provider-agnostic routing across various cloud (Anthropic, OpenAI, Gemini, Mistral) and local (Ollama, llama.cpp) large language models. It features a multi-armed bandit router for dynamic model selection, extensibility via MCP, skills, hooks, and plugins, and includes privacy-focused features like secret scanning and a no-phone-home policy.
Boxlite: A Compute Substrate for AI Agents
Boxlite is a new compute substrate designed for AI agents. It aims to be lightweight for local development and scalable for cloud deployment, offering a flexible environment for building and running AI agents.
Wide-Moat's Open-Source MCP Server for LLM-Powered Computing
Wide-Moat has released an open-source MCP server designed to provide Large Language Models (LLMs) with their own managed computing environments. This self-hosted solution offers Docker workspaces with integrated browser, terminal, and code execution capabilities, enabling LLMs to perform complex tasks autonomously.
Antfly: A Distributed Search Engine for Multimodal AI Data
Antfly is an open-source, distributed search engine built in Zig, designed for multimodal AI data. It integrates full-text search, vector similarity, and graph traversal, with built-in RAG agents and support for various AI models and deployment environments.
StatsPAI: Agent-Native Python Platform for Causal Inference and Econometrics
StatsPAI is an open-source Python platform designed for causal inference and applied econometrics, featuring a unified API, extensive method coverage, structured result objects, and machine-readable schemas. It is built with AI agents in mind, providing discovery metadata for its functions and validation statuses for certified numerical evidence.
MaIN.NET NuGet Package Integrates LLMs, RAG, and Agents into .NET
MaIN.NET is a NuGet package designed to bring Large Language Models (LLMs), Retrieval Augmented Generation (RAG), and AI Agents into the .NET ecosystem. It aims to provide a modular framework for building AI applications with a low-code philosophy.
Mnemo Cortex: Open-Source Memory Coprocessor for AI Agents
Mnemo Cortex is an open-source memory coprocessor designed for AI agents, offering persistent recall, semantic search, and crash-safe memory capture without requiring hooks. It includes features like cross-agent overnight synthesis, an auto-compiled knowledge base (WikAI), agent-to-agent messaging, and a structured facts store with confidence tracking.
GenieClaw: Limited-Context AI Harness for Agentic Smart Homes
GeniePod has released GenieClaw, a Rust-based AI agent layer designed for smart homes. It focuses on low-latency, privacy-first operation with limited context windows, optimized for devices like the Jetson Orin Nano Super. The latest alpha release, v1.0.0-alpha.9, introduces Qwen3-4B as the default model, improves voice interaction, and enhances CI/CD and supply chain security.
ClawMax: Web Orchestration Layer for OpenClaw AI Agents
ClawMax is a web-based orchestration platform designed for OpenClaw AI agents, enabling users to manage, monitor, and coordinate agent teams and workflows. It supports local and self-hosted model integration, including OpenAI-compatible APIs like LM Studio and Ollama.
Dream Server: Turn Your PC into a Private AI Server
Dream Server is an open-source project that enables users to transform their PC, Mac, or Linux machine into a private AI server. It integrates various AI functionalities like LLM inference, a chat UI, voice capabilities, agents, workflows, RAG, and image generation, all designed to run locally without cloud dependencies.
Olares: An Open-Source Personal Cloud for Data Sovereignty and Local AI
Olares is an open-source personal cloud operating system designed to give users control over their digital data by enabling local hosting of applications and AI models. It offers features like enterprise-grade security, a sandboxed application ecosystem, unified file system, single sign-on, and comprehensive AI capabilities for local LLM hosting and private knowledge bases.
Open-Source-Legal's 'cite' Project: Version Control for Knowledge and AI Agents
Open-Source-Legal has developed 'cite', a Python-based GitHub project designed to create a "ground truth layer" and version control system for knowledge, facilitating collaboration between humans and AI agents. It aims to build an open citation graph for document repositories, allowing agents to traverse relationships between documents and propose new annotations.
Lumina Note: A Markdown Note-Taking App with AI Assistant and Bidirectional Links
Lumina Note is a modern, local-first Markdown note-taking application that integrates an AI assistant, live preview, and bidirectional links. It supports various AI models and offers features like a knowledge graph, PDF annotation, and an extension ecosystem.
AgentQL: .NET Library for LLM-Friendly Database Interaction via EF Core
AgentQL is a new .NET library designed to enable AI agents to safely interact with databases. It translates EF Core models into LLM-friendly schema descriptions and facilitates secure SQL query execution.
Swarm Orchestrator v10.0.0: AI-Generated PR Audit and Merge Gate
Swarm Orchestrator v10.0.0 introduces `swarm audit`, a new subcommand and GitHub Action designed to audit pull-request diffs for ten categories of AI-coding-agent 'cheat patterns'. It can block merges if blocking findings are detected and generates hash-chained audit ledgers and AI-BOM artifacts.
Activation-Based Active Learning for In-Context Learning: Challenges and Insights
A new research paper investigates the use of transformer model activations for selecting in-context examples in large language models. The study, which includes a comprehensive analysis using Llama-3.2-3B and Qwen2.5-3B, found that MLP outputs based on massive activations or statistical moments do not correlate with example quality or task performance, suggesting that this approach is not effective for in-context learning.
NexusBench-trajectories Dataset Released by AgentSuite
AgentSuite has made the NexusBench-trajectories dataset publicly available on Hugging Face. This dataset contains per-model agent trajectory data for the NexusBench benchmark, offering detailed insights into agent behavior across various tasks.