Clear recommendations, setup reality, and source links — so you can decide without opening twenty tabs.
100 GitHub Agent projects checked on August 15, 2026. Stars are a snapshot, not our verdict.
Filter by the work you need done, then check the trade-offs before you commit.
Nous Research
A self-hostable personal agent that can plan, use tools, remember context, and delegate work to subagents.
It combines a broad toolset with multiple model providers and several local or remote execution backends.
n8n-io
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Ranked #2 by GitHub stars in AgentFind's filtered Agent project snapshot.
Anomaly
An open-source coding agent available in the terminal, desktop app, and editor-oriented workflows.
It offers a polished interface, broad provider choice, and a strong open-source community without forcing one model vendor.
Significant Gravitas
A platform for building, deploying, and running continuous AI agents, with managed and self-hosted paths.
It is one of the most established autonomous-agent projects and supports reusable blocks and recurring workflows.
langflow-ai
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Ranked #5 by GitHub stars in AgentFind's filtered Agent project snapshot.
langgenius
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Ranked #6 by GitHub stars in AgentFind's filtered Agent project snapshot.
langchain-ai
The agent engineering platform.
Ranked #7 by GitHub stars in AgentFind's filtered Agent project snapshot.
Anthropic
Anthropic's terminal coding agent for understanding codebases, editing files, running commands, and coordinating development tasks.
It pairs strong coding models with a mature agent loop, permissions, hooks, and a large ecosystem of skills.
Browser Use
A Python agent and tooling layer for navigating websites, filling forms, extracting information, and completing browser tasks.
It has broad model support, cloud and local browser options, and a large community focused on computer-use workflows.
Google's open-source terminal agent for coding, research, file operations, and tool-based workflows with Gemini models.
It provides a low-friction entry point, an account-based allowance, and native access to Google's model ecosystem.
OpenAI
OpenAI's coding agent for terminal, IDE, desktop, and cloud workflows, with local repository tools and sandbox controls.
It combines a fast native client with clear approval controls and access through ChatGPT plans or an API key.
Tauric Research
A multi-agent financial research system that assigns analyst, researcher, trader, and risk roles to discuss market decisions.
It makes an agentic investment-research workflow inspectable and supports several model and market-data providers.
Andrej Karpathy
An experimental agent loop that changes training code, runs short experiments, and keeps improvements to a small language model.
It is a clear, minimal example of an agent conducting measurable machine-learning experiments autonomously.
Earendil Works
A compact terminal coding agent and TypeScript toolkit with multi-provider models, extensions, and optional isolation.
It is intentionally small and extensible, making the agent loop easier to understand and customize than larger platforms.
infiniflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Ranked #15 by GitHub stars in AgentFind's filtered Agent project snapshot.
nexu-io
🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode / Hermes & 20+ CLIs via BYOK.
Ranked #16 by GitHub stars in AgentFind's filtered Agent project snapshot.
OpenHands
A software-development agent platform that can run locally, in Docker, on VMs, or through managed infrastructure.
It provides a visual workspace, isolated execution options, and a long-running open-source development community.
ByteDance
A self-hosted super-agent harness for research, coding, files, reports, presentations, and subagent delegation.
It combines deep research with useful output formats and explicit configuration for models, search, sandboxes, and tools.
A useful directory should narrow the decision, not inflate the list. Every profile answers the same three questions.
We start with the job and expected output, not the feature list.
Accounts, API keys, skills, permissions, time, and money stay visible.
Official pages and repositories make the starting evidence traceable.