Skip to content

About

A curated directory of open-source AI repositories for agents, LLM apps, coding assistants, MCP servers, RAG, generative AI, automation, developer tools, research, and AI security.

Resources

Stars

2 stars

Watchers

0 watching

Forks

 
 

Latest commit

 

History

17 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

Awesome AI Repos cover

🤖 AI Agents & Agent Frameworks

  • langchain-ai/langchain — Framework for building LLM applications and agents with model, tool, and retrieval integrations.

  • lobehub/lobehub — Platform for organizing and operating teams of AI agents with scheduling, knowledge, and MCP support.

  • langflow-ai/langflow — Visual platform for building and deploying AI agents and workflows.

  • openclaw/openclaw — Cross-platform personal AI assistant designed to run on the user's own infrastructure.

  • paperclipai/paperclip — Orchestration app for managing teams of AI agents with goals, budgets, governance, and cost tracking.

  • msitarzewski/agency-agents — Collection of specialized AI agent definitions for engineering, design, marketing, and business roles.

  • gastownhall/gastown — Workspace manager for coordinating multiple coding agents with persistent work tracking, handoffs, and merge queues.

  • browser-use/browser-use — Framework that lets AI agents navigate websites, interact with pages, and complete browser tasks.

  • andrewyng/openworker — Local desktop AI coworker that uses model providers and governed integrations to complete security and office tasks.

  • LocoreMind/locoagent — LLM-driven social-media agent that operates accounts through browser automation, scheduled workflows, and platform skills.

  • chaitanyagiri/munder-difflin — Desktop harness for coordinating multiple coding agents with messaging, memory, and shared workspaces.

💬 LLM Applications

  • lucaswalter/n8n-ai-automations — Collection of n8n workflows and templates for AI automations and agents.

  • koala73/worldmonitor — Global intelligence dashboard that uses AI to synthesize news feeds into situational briefs.

  • f/prompts.chat — Open-source application for sharing, discovering, and self-hosting prompts for LLMs.

  • macro-inc/macro — Unified team workspace combining email, documents, tasks, CRM, and action-taking AI agents with shared memory.

  • odysseus-dev/odysseus — Self-hosted AI workspace for chat, agents, research, documents, email, and local model workflows.

  • mvanhorn/last30days-skill — Agent skill that researches recent discussion across social and web sources and synthesizes evidence-ranked briefs.

  • trypostit/trypost — Self-hosted social-media scheduler with AI content generation, automation workflows, and an MCP interface for agents.

  • stevenflanagan1/social-ai-team — Claude Code skill suite for brand setup, social content creation, publishing, and performance review.

  • ScrapeCreators/social-media-research-skills — Agent-skill collection for researching social posts, comments, competitors, trends, ads, and audiences.

  • ericciarla/trendFinder — Monitoring app that uses LLMs to identify trends in social and web content and send alerts.

🛠️ AI Developer Tools

  • Panniantong/Agent-Reach — CLI that gives AI agents search and reading access across social, video, and developer platforms.

  • HKUDS/CLI-Anything — Toolkit for generating and testing command-line harnesses that let AI agents operate existing software.

  • firecrawl/firecrawl — Context API for searching, scraping, and transforming web data for AI applications and agents.

  • semantica-agi/semantica — Graph-native context infrastructure for knowledge graphs, GraphRAG, provenance, and accountable AI systems.

  • diegosouzapw/OmniRoute — LLM gateway that routes requests across providers and models with quota-aware fallback and agent-tool support.

  • AlexsJones/llmfit — Terminal tool that detects hardware and ranks local LLMs by memory fit, speed, quality, and context capacity.

  • guillaumemeyer/watermarks-remover — Agent skill and local service for inspecting and removing AI provenance markers and metadata from user-owned text and files.

  • FlashML-org/FreeToken — Edge-native MoE inference engine for running large open-weight models across consumer GPU and CPU memory.

  • Wei-Shaw/sub2api — Self-hosted AI API gateway for distributing subscription quotas across model providers and compatible clients.

  • microsoft/markitdown — Python utility that converts documents and media to Markdown for LLM and text-analysis pipelines.

  • ToolJet/ToolJet — Internal-app platform with AI app generation and an MCP server that lets coding agents build and modify ToolJet applications.

💻 AI Coding Assistants

  • awesome-opencode/awesome-opencode — Curated list of plugins, themes, agents, projects, and resources for the OpenCode coding agent.

  • different-ai/openwork — Desktop app and MCP service for sharing reusable AI workflows across compatible agent clients.

  • DietrichGebert/ponytail — Coding-agent skill that guides implementations toward smaller and simpler code.

  • PrimeIntellect-ai/prime-agent — Self-improving RLM agent for coding workflows and long-running autonomous tasks.

  • addyosmani/agent-skills — Collection of production-oriented engineering skills for AI coding agents.

  • nextlevelbuilder/ui-ux-pro-max-skill — Design knowledge skill for AI coding assistants building web and mobile interfaces.

  • anomalyco/opencode — Open-source terminal-based AI coding agent.

  • pbakaus/impeccable — Design-language skill and plugin for improving interface output from AI coding harnesses.

  • Leonxlnx/taste-skill — Frontend design skill for AI coding agents and low-code tools.

  • mattpocock/skills — Composable engineering workflow skills for Claude Code, Codex, and other coding agents.

  • obra/superpowers — Skills-based software development methodology for coding agents, including planning, testing, and subagent workflows.

  • Nutlope/hallmark — Design skill for coding agents that builds, audits, studies, and redesigns interfaces using reusable design rules.

  • stablyai/orca — Desktop environment for running and coordinating multiple coding agents in isolated Git worktrees.

  • tt-a1i/archify — Coding-agent skill and deterministic renderer for producing validated interactive system diagrams from codebases or descriptions.

  • multica-ai/andrej-karpathy-skills — Coding-agent guidelines for explicit assumptions, simple implementations, targeted edits, and verifiable outcomes.

  • Alishahryar1/free-claude-code — Model and provider router for using multiple coding agents with failover across remote and local LLM backends.

  • Leonxlnx/unlazy — Agent skill that enforces acceptance criteria, executable gates, evidence checks, and revalidation for substantial coding work.

  • affaan-m/ECC — Collection of skills, memory, security, and workflow tooling for optimizing coding-agent harnesses.

🔐 AI Security & Safety

  • ottosulin/awesome-ai-security — Curated collection of resources covering AI and LLM security.

  • yueliu1999/Awesome-Jailbreak-on-LLMs — Curated collection of LLM jailbreak attacks, defenses, guard models, evaluations, datasets, and analysis.

  • GenggengSvan/Jailbreak-Observatory — Interactive research map tracking LLM jailbreak papers, conference coverage, citations, and attack-defense relationships.

  • x-zheng16/Awesome-Embodied-AI-Safety — Survey and searchable catalog of embodied-AI safety research across perception, cognition, planning, interaction, and agentic systems.

  • cckuailong/awesome-gpt-security — Curated collection of LLM security tools, prompt-injection research, red-team resources, and vulnerability case studies.

  • uber/ADR — Framework for AI agent observability, security benchmarking, and threat detection.

  • zhaoxuya520/reverse-skill — Skill router for AI agents performing authorized reverse engineering, security research, and penetration testing.

  • GreyDGL/PentestGPT — LLM-powered agent framework for automated penetration testing.

  • Rizzo-AI-Academy/rizzo-pii — Local Italian PII detection model and reversible anonymization workflow for using sensitive documents with LLMs.

  • cyberark/FuzzyAI — Fuzzer for testing LLM APIs against jailbreaks and other security vulnerabilities.

  • JailbrokenAI/wallbreaker — Terminal-based AI red-team harness with automated attacks, benchmarks, target adapters, and LLM judging.

  • usestrix/strix — Agentic penetration-testing tool for finding and validating application vulnerabilities.

  • ifixai-ai/iFixAi — CLI and agent skill for auditing AI agents across operational assurance, red-team, governance, and security checks.

  • elder-plinius/L1B3RT4S — Collection of jailbreak prompts for major AI models.

  • cyber-albsecop/Awesome-AI-Super-Prompting — Curated directory of LLM jailbreaks, system-prompt leaks, prompt engineering, red-team tools, and AI security resources.

  • elder-plinius/OBLITERATUS — Toolkit for locating and modifying LLM refusal representations, comparing intervention methods, and benchmarking behavior changes.

  • elder-plinius/CL4R1T4S — Collection of extracted system prompts, tool definitions, and behavioral guidelines from major AI products.

  • Tencent/AI-Infra-Guard — AI red-teaming platform for scanning agents, skills, MCP servers, model infrastructure, and jailbreak exposure.

  • confident-ai/deepteam — Local red-teaming framework that tests LLM agents, RAG pipelines, and chatbots for security and safety vulnerabilities.

  • mukul975/Anthropic-Cybersecurity-Skills — Library of structured cybersecurity skills for AI agents across defensive, offensive, incident-response, and governance workflows.

🎨 Image & Video Generation

📚 AI Research & Learning

🔌 MCP & AI Integrations

AI God

Keywords

agentic-workflows, agent-orchestration, agent-memory, agent-observability, agent-security, ai-gateway, llm-gateway, model-routing, inference-routing, context-engineering, context-management, context-window, knowledge-graphs, graph-rag, semantic-search, hybrid-search, reranking, llm-evaluation, llm-observability, hallucination-detection, prompt-injection, red-teaming, ai-safety, responsible-ai, model-evaluation, benchmark-datasets, synthetic-data, data-labeling, model-serving, local-llm, edge-ai, quantization, model-compression, gpu-inference, multimodal-models, vision-language-models, speech-recognition, text-to-speech, text-to-image, text-to-video, diffusion-models, image-generation, video-generation, retrieval-augmented-generation, tool-calling, function-calling, structured-output, llmops, mlops, ai-governance

About

A curated directory of open-source AI repositories for agents, LLM apps, coding assistants, MCP servers, RAG, generative AI, automation, developer tools, research, and AI security.

Resources

Stars

2 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors