MateClaw 1.3.0: Multi-Agent Orchestration, Workflow, and Enhanced Knowledge Processing
MateClaw, an open-source AI agent platform built on Spring AI Alibaba, has released version 1.3.0. This update introduces multi-agent orchestration via a new Workflow engine, event-driven Triggers, and an enhanced Wiki that acts as a processing pipeline for knowledge. It also improves tool binding for individual agents and adds multimodal sidecar routing for vision models.
AgentOS: A TypeScript AI Agent Framework with Advanced Features
AgentOS is an open-source AI agent framework built with TypeScript. It offers features like cognitive memory, runtime tool forging, and multi-agent orchestration, supporting eleven different LLM providers. The project is actively developed with a recent release and a growing community.
Airbyte Agent SDK: Empowering AI Agents with System Access
Airbyte has released an Agent SDK designed to provide AI agents with reliable, permission-aware access to external systems. This Python-based SDK aims to simplify the integration of AI agents with existing data infrastructure, enabling them to interact with various services and data sources.
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.
HarnessClaw Engine: A Go-based LLM Programming Assistant with WebSocket and Tool Calling
HarnessClaw Engine is an open-source LLM programming assistant engine built with Go. It supports WebSocket for multi-turn dialogues, tool calling, permission control, and skill extension, and recently released version v0.0.18.
Aguara: Local-First Security Scanner for AI Agents and Software Supply Chains
Aguara is an open-source, local-first security scanner designed to detect vulnerabilities in AI agents and software supply chains. It identifies risks such as prompt injection, tool poisoning, unsafe GitHub Actions, secret exfiltration, and compromised packages across various ecosystems without relying on SaaS or LLM calls.
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.
Optave's ops-codegraph-tool: Code Intelligence CLI for AI Agents
Optave has released `ops-codegraph-tool`, a command-line interface (CLI) designed to generate function-level dependency graphs across 11 programming languages. This tool aims to enhance AI agent capabilities by providing structured code context, reducing reliance on extensive token usage for codebase understanding, and improving code quality checks.
ReMe: A Memory Management Kit for AI Agents
ReMe is an open-source memory management framework for AI agents, designed to address limitations in context windows and stateless sessions. It provides both file-based and RAG-based memory systems, enabling agents to retain and recall information over long conversations and across sessions.
LangChain: The Agent Engineering Platform for LLM Applications
LangChain is an open-source Python framework designed for building and deploying LLM-powered applications and agents. It provides tools for chaining interoperable components, integrating with various data sources and models, and supporting rapid prototyping and production-ready features like monitoring and debugging.
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.
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.
SRE AI Copilot: AI-Driven Incident Response for Kubernetes
SRE AI Copilot is an open-source, AI-driven backend service designed to automate and assist with incident response in Kubernetes environments. It processes Prometheus AlertManager webhooks, analyzes incidents, proposes root causes and actions, and can optionally execute remediations with human approval.
Notebook Intelligence: A JupyterLab Extension for AI Code Assistants
Notebook Intelligence is a new JupyterLab extension designed to integrate various AI coding assistants, including Claude Code, Copilot, Ollama, and OpenAI-compatible LLMs. It aims to enhance the notebook development experience by providing features like MCP, skills, plugins, and notebook agents.
AgentFM: Decentralized AI Supercomputer via Peer-to-Peer Network
AgentFM introduces a peer-to-peer network designed to transform everyday computers into a decentralized AI supercomputer. This system enables the execution of large-scale AI workloads by leveraging a global mesh of idle CPUs and GPUs.
Mindburn-Labs Releases helm-ai-kernel for Secure AI Agent Execution
Mindburn-Labs has released helm-ai-kernel, an open-source execution firewall designed to enhance the security of AI agents. This tool acts as a fail-closed system, quarantining potentially risky tools and proxying requests to ensure secure operations.
AISix: Open-Source AI Gateway for LLMs and AI Agents
AISix is a new open-source AI gateway built in Rust, designed to provide a unified OpenAI-compatible API for various large language models and AI agents. It offers features like routing, guardrails, caching, rate limiting, and observability, aiming to simplify the management of AI infrastructure.
TMA1: Local-First Observability for AI Agents
TMA1 is a new open-source project providing local-first observability for AI agents. It records all LLM calls and routes relevant information back into the agent's operational loop through hooks and an MCP (Message Communication Protocol). This aims to enhance agent decision-making and debugging capabilities.
DuDuClaw: Open-Source AI Agent Platform with Multi-LLM Support
DuDuClaw is an open-source AI agent platform built with Rust and Python. It supports over 80 Multi-Context Protocol (MCP) tools and integrates with seven communication channels, including Slack, Discord, LINE, and Telegram. The platform is designed for self-hosting and can function as an alternative to proprietary models for production multi-LLM systems.
Tensorlake: Serverless Runtime for Agentic Applications
Tensorlake is a new serverless runtime designed for sandboxing and deploying background agentic applications. It offers a Python-based environment with features for code execution and LLM integration, aiming to simplify the development and deployment of AI agents.
Claude-Brewcode: A Development Platform for Claude Code
Claude-Brewcode is a comprehensive development platform designed for Claude Code. It offers features such as infinite focus tasks with automatic context handling, prompt optimization, skill and agent creation, and knowledge persistence.
GlideMQ: High-Performance Message Queue for Node.js with Rust Bindings
GlideMQ is a new high-performance message queue for Node.js that leverages Valkey/Redis Streams and Rust-native NAPI bindings. It aims to provide a robust and efficient solution for managing message queues in Node.js applications.
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.