Open Source AI Agents
Discover 406 open source AI Agents repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. AI Agents projects here are most often combined with Python, Developer Tools and MCP. Last updated October 4, 2026.
406 repositories · updated October 4, 2026
CubeSandbox: Run Secure, Fast Sandboxes for AI Agents
CubeSandbox is a self-hostable sandbox service for running untrusted AI-agent workloads in hardware-isolated microVMs. It combines E2B SDK compatibility with snapshots, network controls, and single-node or multi-node deployment.
awesome-ai-agents-2026: Find AI Agents, Frameworks, and Tools
A categorized directory of AI agents, frameworks, protocols, models, and learning resources. Use it to survey the ecosystem, compare options by category, and find starting points for building or adopting agent-based systems.
agent-sandbox: Manage Isolated Stateful Workloads on Kubernetes
Agent Sandbox adds Kubernetes APIs and controllers for isolated, stateful workloads with stable identity and persistent storage. Use it to run long-lived AI agent environments, development sessions, or other singleton workloads that need managed lifecycle control.
lobehub: Organize and Run Teams of AI Agents
LobeHub is a web app for building, coordinating, and scheduling AI agents as a team. It suits individuals and teams who want shared agent workflows, model choice, and self-hosting, but requires configuring an AI model provider.
awesome-agent-almanac: Browse AI agents and agent tools
A categorized directory of AI agents, agent frameworks, MCP servers, and related projects. Use it to discover tools across development, research, creative work, infrastructure, and other agentic domains.
awesome-ai: Browse a Curated Directory of AI Tools
A categorized directory of AI APIs, tools, frameworks, platforms, and learning resources. Use it to explore options across AI development, deployment, evaluation, and education, then verify each tool’s current status before adoption.
QwenPaw: Run a Self-Hosted Personal AI Assistant
QwenPaw is a personal AI assistant that runs locally or in the cloud and connects to chat apps, models, and extensible tools. It suits people who want a customizable agent with persistent memory and security controls under their own deployment.
ReMe: Manage Persistent Memory for AI Agents
ReMe turns agent conversations and resources into searchable, editable Markdown memory that can evolve over time. It suits developers building assistants that need reusable knowledge across sessions and agent runtimes.
AgentTeams: Coordinate Human-Supervised AI Agent Teams
AgentTeams runs multiple AI agents as coordinated workers in shared Matrix rooms, with a manager to assign work and people able to observe and intervene. It is aimed at teams that want self-hosted, auditable agent collaboration across different runtimes.
DeepTutor: Build a Personalized AI Learning Workspace
DeepTutor is a self-hostable AI tutoring workspace for studying with chat, research, quizzes, and personal learning materials. It combines agent tools, memory, and knowledge retrieval for learners who want more than a single-purpose chatbot.
Memori: Give AI Agents Persistent Memory
Memori adds persistent, structured memory to LLM applications and agents, capturing conversations and execution context for later recall. It suits teams building stateful agents who want a memory layer that works across models and existing infrastructure.
code-review-graph: Map Code for AI Reviews
code-review-graph builds a local, persistent map of code structure and serves targeted review context to AI coding tools through MCP and a CLI. It suits teams working in large or interconnected repositories who want impact analysis without repeatedly scanning the whole codebase.