Open Source Agentic AI Projects
Agentic AI describes systems that use AI models to pursue goals through multiple steps, rather than responding only with a single answer. They can plan tasks, use tools, keep track of context, and adjust actions based on results. These capabilities help automate work that involves research, coding, data processing, or coordination across services, while requiring safeguards for errors and unintended actions.
Open source tools in this area include agent frameworks, workflow builders, orchestration systems, model-serving components, and evaluation or monitoring utilities. When choosing one, consider its license, maintenance activity, documentation, model and infrastructure requirements, security controls, and integrations with the tools you already use. These resources are useful to developers, researchers, and teams exploring or deploying multi-step AI workflows.
17 repositories · updated October 4, 2026
Awesome-Self-Improving-Agents: Explore Self-Improving Agent Research
A curated research hub for self-improving foundation-model agents, organized around model and agent-scaffold improvements. Researchers and practitioners can use it to find papers, benchmarks, and related resources by topic.
agent-factory: Generate Executable AI Agent Workflows
Agent Factory turns natural-language task descriptions into executable Python agent workflows, using MCP tools and the any-agent library. It is aimed at developers who want to create, evaluate, and run agents without hand-coding every workflow.
grok-build: Code with an Interactive Terminal AI Agent
Grok Build is a Rust-based coding agent that works in a full-screen terminal interface or in headless scripts and CI. It can inspect and edit a codebase, run shell commands, search the web, and manage longer tasks.
awesome-agentic-ai: Explore Agentic AI Tools and Learning Resources
A curated guide to agentic AI frameworks, tools, papers, and learning materials, with example projects and recommendations for choosing technologies. Useful for developers learning agent systems or evaluating options for a project.
AI-Agents-Projects-Tutorials: Explore Practical AI Agent Examples
A collection of code notebooks and scripts exploring AI agents, multi-agent workflows, memory, planning, tool use, and agentic RAG. Useful for developers and learners who want runnable examples to study or adapt.
OpenMontage: Produce Videos with AI Coding Assistants
OpenMontage gives AI coding assistants structured pipelines for researching, scripting, generating assets, editing, and rendering videos. It suits creators and developers who want to automate production while retaining control over choices and approvals.
agent-native: Build Agentic Apps with Shared UI and Actions
Agent-Native is a TypeScript framework for building applications where people and AI agents work through the same actions and shared data. It suits teams creating agent-powered tools that need an interactive UI, permissions, and workflows beyond chat.
loop-engineering: Design and Operate AI Coding-Agent Loops
A TypeScript toolkit and pattern library for designing repeatable workflows around AI coding agents. It helps teams discover work, delegate tasks, verify results, and preserve state instead of managing every step through prompts.
dexter: Research Financial Questions with an Autonomous Agent
Dexter turns complex financial questions into research plans, gathers market data with tools, and checks its work before responding. It is aimed at developers and researchers who want an extensible, command-line financial research agent, not a source of investment advice.
GLM-5: Power Long-Horizon Coding and Agentic Tasks
GLM-5 is a family of large language models from Z.ai for complex coding, systems engineering, and long-running agent tasks. The repository provides model downloads, serving guidance, and fine-tuning references.
claude-code-best-practice: Learn Claude Code Workflows and Practices
A community-maintained guide to Claude Code practices, configuration, agents, skills, and development workflows. It helps developers move from ad hoc prompting toward repeatable, agentic engineering, with examples and links to further resources.
agentic-ai-prompt-research: Study Coding Assistant Prompt Design
An independent research project reconstructing prompt patterns and coordination mechanisms used by agentic coding assistants. It is intended for AI builders, prompt engineers, and security researchers, not as a verbatim copy of any proprietary system.