Signet-AI: Local-First Identity, Memory, and Secrets for AI Agents
Signet-AI is a TypeScript-based GitHub project that provides local-first identity, memory, and secret management for AI agents. It aims to offer portable state across various AI models and harnesses, ensuring agents maintain continuity regardless of the underlying platform.
Underthesea: An Open-Source Agentic AI Toolkit with Vietnamese NLP
Underthesea is an open-source Python toolkit for building AI agents, featuring multi-provider LLM support, built-in tools, and a server adapter for A2A compatibility. It also includes comprehensive Vietnamese Natural Language Processing (NLP) capabilities.
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.
Li+ Language: A High-Level Programming Language for AI Agents
Li+ is a new high-level programming language designed for AI agents, focusing on "prompt-native harness engineering." It enables AI to function as an interactive compiler, autonomously managing development tasks like issues, specifications, implementation, CI, and releases through human dialogue. The language emphasizes observable behavior as the definition of correctness and distills requirements from conversation.
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.
Spec Kitty: Spec-Driven Development for AI Coding Agents
Spec Kitty is an open-source CLI tool designed for spec-driven development with AI coding agents. It helps developers manage product intent, create work packages, and maintain context within a Git repository, supporting various AI models like Claude, Cursor, Gemini, and Codex.
AINYC's Canonry: An Agent-First AEO Monitoring and Operating Platform
AINYC has released Canonry, an open-source, self-hosted platform designed for Answer Engine Optimization (AEO) monitoring and operation. It allows users to track citations across various AI engines like Gemini, ChatGPT, Claude, and Perplexity, diagnose traffic issues, and execute fixes.
Google's ADK-Python: An Open-Source Toolkit for AI Agent Development
Google has released ADK-Python, an open-source, code-first Python toolkit designed for building, evaluating, and deploying AI agents. The toolkit, currently at version 2.1.0, emphasizes flexibility and control in agent development and includes a graph-based execution engine for workflows and a structured Task API for agent-to-agent delegation.
Wolfpack: Mobile & Desktop Command Center for AI Coding Agents
Wolfpack is an open-source project that provides a mobile and desktop command center for managing AI coding agents like Claude, Codex, and Gemini. It allows users to control AI sessions across multiple machines from a phone or browser, with sessions persisting even if the web server restarts, and is secured by Tailscale.
Pipelock: Open-Source AI Agent Firewall for Enhanced Security
Pipelock is an open-source AI agent firewall designed to enhance security for AI agents by providing egress control, Data Loss Prevention (DLP), Server-Side Request Forgery (SSRF) protection, and prompt injection defense. It acts as an egress proxy for various AI agent traffic, offering verifiable proof of agent actions.
Daintree: An AI Coding Agent Orchestration Environment
Daintree is an open-source delegation environment designed to orchestrate AI coding agents like Claude, Gemini, and Codex. It enables developers to manage multiple agent sessions across Git worktrees, offering features such as integrated terminals, context injection, and workflow automation. The project recently released version v0.13.0.
ainovel-cli: Multi-Agent AI Novel Generation Engine
ainovel-cli is an open-source command-line interface (CLI) tool that uses multiple AI agents to autonomously generate long-form novels. It features a multi-agent architecture, adaptive context management for long narratives, and a TUI for real-time progress observation and user intervention.
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.
HackerAI: AI-Powered Penetration Testing Assistant
HackerAI is an open-source AI-powered penetration testing assistant that helps users find and fix vulnerabilities through a chat interface. The project, built with TypeScript, React, and Next.js, recently released version `desktop-v0.0.51` and supports various AI model providers and sandbox environments for secure code execution.
wshobson/agents: A Multi-Harness Agentic Plugin Marketplace for AI Code Assistants
The wshobson/agents GitHub repository presents a multi-harness agentic plugin marketplace designed for various AI code assistants, including Claude Code, Codex CLI, Cursor, OpenCode, and Gemini CLI. It offers a collection of plugins, agents, skills, and commands from a single Markdown source, generating native artifacts for each supported harness.
Project N.E.K.O.: An Open-Source Omni AI Companion with Human-like Memory and Emotional Engine
Project N.E.K.O. is an open-source AI companion platform designed to proactively interact with users by watching, reading, and playing alongside them. It features a "human-like memory" system and an "embodied emotional engine," supporting real-time voice, text, and visual understanding. The project is built with a modular architecture, including agent tool execution, a plugin ecosystem, and compatibility with over 14 AI service providers.
ElatoAI: Realtime Voice AI for Arduino ESP32 Devices
ElatoAI is a GitHub project enabling real-time voice AI on Arduino ESP32 devices, supporting over 100 voice AI models. It utilizes secure WebSockets and edge functions for applications like AI toys and companions, offering features such as speech-to-speech conversion, custom AI agents, and global edge performance.
ServiceGraph: AI Agent Skills for Structured Datasets
ServiceGraph is a GitHub repository providing AI agent skills designed to access and utilize structured datasets for startup founders. These skills enable agents to filter, rank, and extract contact data from various business datasets, including agencies, product directories, and newsletters.
Lim-Code: A VS Code AI Programming Assistant
Lim-Code is an AI programming assistant for VS Code that supports multiple AI models, including Google Gemini, OpenAI-compatible APIs (like ChatGPT), and Anthropic's Claude. It features an intelligent tool system for code operations, file management, search, terminal commands, and image generation, along with Model Context Protocol (MCP) support for extending tool capabilities.
Adam: A 5-Layer Persistent Memory and Identity Architecture for AI Agents
Adam is an open-source, 5-layer persistent memory and identity architecture for AI agents, designed to ensure an agent's continuity and identity sovereignty. It stores an AI's core memory and neural graph in user-owned files, making it resilient to model swaps, vendor shutdowns, and machine wipes. The framework has been production-validated over 353 sessions and claims to be the first documented case of emergent values in persistent AI, quantum-verified on IBM hardware.
Sutando: An Open-Source, Self-Improving AI Agent for macOS
Sutando is an open-source AI agent designed for macOS that operates in real-time and can autonomously rewrite its own code. It aims to provide a personal AI superpower, capable of handling tasks via voice, vision, and screen interaction, and can integrate with various communication channels and even scale across multiple Mac machines.