Find the open-source solution that fits.
Start with a real need, then filter by use case, format, runtime, and repository facts to find projects you can use, combine, or build on.
- Projects
- 4,306
- Authors
- 3,645
- GitHub Stars
- 13,022,829
4306 projects · page 1 of 240
Open openclawGeneral agentPersonal and daily lifeLinux
openclaw↗
@openclaw·TypeScript
Run a personal AI assistant across your devices and messaging channels
Project overviewOpenClaw is a personal AI assistant that runs on your own devices and connects to common messaging channels such as WhatsApp, Telegram, Slack, and WeChat. It also supports voice and a controllable Canvas across Apple and Android surfaces. The onboarding command guides setup of the gateway, workspace, channels, and skills on macOS, Linux, or Windows.
- Stars
- ★ 382,482
- Forks
- ⑂ 80,278
- GitHub updated
- Jul 10, 2026
Open awesome-selfhostedCollection or directoryDevOps and deployment
awesome-selfhosted↗
@awesome-selfhosted
Browse free software and network services that can run on your own servers.
Project overviewAwesome Selfhosted is a categorized catalog of free software for running web applications and network services on infrastructure you control. It covers areas such as analytics, backups, bookmarks, communication, generative AI, project management, wikis, and self-hosting platforms, with entries commonly listing websites, source code, licenses, and technology stacks. It helps with discovery and comparison rather than installation or hosting.
- Stars
- ★ 305,416
- Forks
- ⑂ 14,311
- GitHub updated
- Jul 14, 2026
Open superpowersCollection or directorySoftware developmentClaude Code
superpowers↗
@obra·Shell
Guides coding agents through clarification, planning, implementation, testing, review, and branch completion.
Project overviewSuperpowers is a composable skill framework and development methodology for coding agents. It prompts clarification before implementation, confirms a specification in readable chunks, and guides worktrees, plans, TDD, subagent execution, two-stage reviews, and branch finishing. It supports several agent harnesses, including Claude Code, Codex, Cursor, and OpenCode, but must be installed separately for each one.
- Stars
- ★ 251,573
- Forks
- ⑂ 22,448
- License
- MIT
Open ECCPluginSoftware developmentClaude Code
ECC↗
@affaan-m·JavaScript
Add modular agents, skills, rules, memory, and security hooks to coding assistants.
Project overviewECC provides a modular environment of specialized subagents, development skills, rules, commands, session state, and security hooks for planning, testing, review, debugging, and reusable knowledge. It is primarily distributed as a Claude Code plugin, with adapters and configuration for Codex, OpenCode, Cursor, and other assistants. Its selective installer lets advanced users add only the components needed for their workflow rather than adopting the entire collection.
- Stars
- ★ 228,177
- Forks
- ⑂ 34,995
- License
- MIT
Open hermes-agentGeneral agentPersonal and daily lifeCLI integration
hermes-agent↗
@NousResearch·Python
Run a self-improving agent across sessions and remote machines
Project overviewHermes Agent is designed to retain useful context across sessions by creating skills from experience, searching past conversations, and nudging knowledge to persist. It can run on a small VPS, a GPU cluster, or serverless infrastructure, and Telegram access lets you interact with a cloud instance while it works away from your laptop.
- Stars
- ★ 212,620
- Forks
- ⑂ 39,216
- License
- MIT
Open n8nAutomationWorkflow automation
n8n↗
@n8n-io·TypeScript
Automate workflows and AI agents with a visual canvas and custom code.
Project overviewn8n combines a visual workflow builder with JavaScript, Python, and npm packages for automations that connect models, data, and business systems. It can run in n8n Cloud or be self-hosted with Node.js or Docker, with a large library of integrations and templates. The source is available under a fair-code licensing model rather than a conventional permissive open-source license.
- Stars
- ★ 195,947
- Forks
- ⑂ 59,224
- GitHub updated
- Jul 10, 2026
Open claw-codeAgent harnessSoftware developmentLinux
claw-code↗
@ultraworkers·Rust
Build and inspect an agent-maintained Rust experiment around the `claw` CLI.
Project overviewClaw Code contains a Rust implementation of the `claw` terminal agent harness that can be built from source and used for diagnostics, one-shot prompts, and interactive sessions with an API key. The repository presents itself as an agent-planned and maintained museum exhibit, warns that the same-named crates.io package is the wrong install, and points practical users to LazyCodex or Gajae-Code.
- Stars
- ★ 194,695
- Forks
- ⑂ 109,767
- License
- MIT
Open vscodeDesktop appSoftware development
vscode↗
@microsoft·TypeScript
Edit, navigate, debug, and extend code with the open-source core behind VS Code.
Project overviewCode - OSS is the community-developed source repository behind Visual Studio Code, combining code editing, navigation, understanding, lightweight debugging, and an extension model. It is the place to study, contribute to, or build from the editor core. The downloadable Visual Studio Code product adds Microsoft-specific customizations and is distributed under a separate product license.
- Stars
- ★ 187,554
- Forks
- ⑂ 41,269
- License
- MIT
Open AutoGPTAutomationWorkflow automation
AutoGPT↗
@Significant-Gravitas·Python
Build, deploy, and monitor continuously running agents with visual blocks.
Project overviewAutoGPT’s current platform uses a low-code block builder to create agents and workflows, manage deployments, and run automations continuously from external triggers. The repository also retains classic tooling such as Forge and an agent benchmark. Self-hosting is a technical Docker-based setup, the hosted service remains a closed beta, and licensing differs between the Polyform Shield platform directory and the MIT-licensed classic components.
- Stars
- ★ 185,450
- Forks
- ⑂ 46,114
- GitHub updated
- Jul 10, 2026
Open opencodeCoding agentSoftware developmentLinux
opencode↗
@anomalyco·TypeScript
Runs an open-source coding agent in your terminal with build and read-only planning modes.
Project overviewOpenCode is an open-source coding agent for the terminal. Its built-in build agent handles development work, the plan agent is read-only for analysis and exploration, and a general subagent supports complex searches and multistep tasks. The project also offers a beta desktop app for macOS, Windows, and Linux, so users can choose a CLI or desktop workflow.
- Stars
- ★ 184,484
- Forks
- ⑂ 22,988
- License
- MIT
Open skillsCollection or directoryAI and agent developmentClaude
skills↗
@anthropics·Python
Provides Claude skill examples, the Agent Skills specification, and a template for custom skills.
Project overviewAnthropic Skills collects Claude skill examples, the Agent Skills specification, and a starter template for document, development, enterprise, communication, and creative tasks. The repository can be registered as a Claude Code plugin marketplace, and its example skills can also be used through Claude.ai or the API. A custom skill is a directory containing a SKILL.md file with YAML frontmatter and instructions. Most examples use Apache 2.0, while the document-creation skills are source-available rather than open source.
- Stars
- ★ 160,062
- Forks
- ⑂ 18,890
- GitHub updated
- Jul 10, 2026
Open langflowWeb appAI and agent development
langflow↗
@langflow-ai·Python
Design agent workflows visually and expose them as APIs or MCP tools.
Project overviewLangflow lets developers assemble models, retrieval, vector databases, and multi-agent steps on a visual canvas, while retaining Python access for custom components. Flows can be tested interactively, exported as JSON, deployed behind an API, or served as MCP tools for other applications. A bundled desktop edition is available for Windows and macOS, alongside Python and Docker installations.
- Stars
- ★ 151,552
- Forks
- ⑂ 9,640
- License
- MIT
Open difyWeb appAI and agent development
dify↗
@langgenius·TypeScript
Build LLM apps with visual workflows, RAG, agents, and APIs.
Project overviewDify combines visual AI workflows, model management, prompt testing, document-based RAG, agent tools, and operational logs in one application-development platform. Each application is exposed through APIs for integration with existing products. Teams can use Dify Cloud or self-host the Community Edition with Docker Compose; the repository uses the Dify Open Source License, based on Apache 2.0 with additional conditions.
- Stars
- ★ 148,407
- Forks
- ⑂ 23,395
- GitHub updated
- Jul 10, 2026
Open open-webuiWeb appProductivity and officeModel Context Protocol
open-webui↗
@open-webui·Python
Host an extensible chat interface for Ollama and OpenAI-compatible model services.
Project overviewOpen WebUI provides a self-hosted interface for Ollama, local models, and OpenAI-compatible APIs, with built-in retrieval, user and group permissions, and an extensible plugin system. It can connect tools through MCP or OpenAPI and deploy through pip, Docker, or Kubernetes. Docker users need to mount the persistent data volume, or the application database can be lost when the container is removed.
- Stars
- ★ 145,394
- Forks
- ⑂ 21,048
- GitHub updated
- Jul 14, 2026
Open langchainFrameworkAI and agent development
langchain↗
@langchain-ai·Python
Combine interchangeable models, data sources, and tools in LLM applications.
Project overviewLangChain provides common interfaces and modular components for building agents and other LLM-powered applications. Developers can connect models, embeddings, vector stores, retrievers, and third-party tools while swapping providers without rebuilding the whole application. The core framework works on its own; LangGraph handles lower-level orchestration, while LangSmith products support debugging, evaluation, and deployment workflows.
- Stars
- ★ 141,475
- Forks
- ⑂ 23,505
- License
- MIT
Open claude-codeCLI appSoftware developmentClaude Code
claude-code↗
@anthropics·Python
Handle coding tasks through natural language in the terminal, IDE, or GitHub.
Project overviewClaude Code is an agentic coding tool that works with the surrounding codebase to carry out routine tasks, explain complex code, and manage Git workflows from natural-language instructions. It can be used in a terminal or IDE and can participate on GitHub when tagged as @claude. The repository also includes plugins that add custom commands and specialized agents.
- Stars
- ★ 137,282
- Forks
- ⑂ 22,163
- GitHub updated
- Jul 10, 2026
Open gstackCollection or directorySoftware developmentClaude Code
gstack↗
@garrytan·TypeScript
Run product work from discovery through review, QA, and release in Claude Code.
Project overviewgstack organizes product discovery, planning, design critique, code review, browser QA, security checks, release, and retrospectives as connected Claude Code slash commands. Each stage passes artifacts such as design documents and test plans to the next, giving founders and engineering teams a repeatable way to run one or many development sprints.
- Stars
- ★ 120,962
- Forks
- ⑂ 18,077
- License
- MIT
Open cc-switchDesktop appSoftware development
cc-switch↗
@farion1231·Rust
Switch providers and sync MCP, prompts, skills, and sessions across AI coding tools.
Project overviewCC Switch replaces manual JSON, TOML, and environment-file edits with a desktop interface for managing providers across Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw, Hermes, and related tools. It also synchronizes MCP servers, prompt files, and skills across supported apps and can browse session history. Most tools still need a terminal or CLI restart after a provider switch.
- Stars
- ★ 117,149
- Forks
- ⑂ 7,839
- License
- MIT