Skip to content
Fossfits

ai-agents.

Listed 33Updated Sep 13, 2026

  1. Rank 1. claude-memPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + MoreGitHub stars: 93.8k
  2. Rank 2. VaneVane is an AI-powered answering engine.GitHub stars: 36.7k
  3. Rank 3. hexstrike-aiHexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.GitHub stars: 11.9k
  4. Rank 4. potpieContext Graph for AI Native SDLCGitHub stars: 5.7k
  5. Rank 5. sphere-sdkThe SDK for autonomous economic agents. Give an agent an identity, a wallet, and the ability to find, negotiate with, and settle with other agents - peer-to-peer, with perfect privacy and ultra-fast finalityGitHub stars: 5.4k
  6. Rank 6. LongMemoryLocal persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.GitHub stars: 4.5k
  7. Rank 7. langchainrbBuild LLM-powered applications in RubyGitHub stars: 2k
  8. Rank 8. hivemindHivemind turns your traces into reusable skills across agentsGitHub stars: 1.6k
  9. Rank 9. NanoResearch🦞+🔬 NanoResearch: The Autonomous AI Research AssistantGitHub stars: 1.4k
  10. Rank 10. ai-game-devtoolsYour AI Game Dev Hub. The ultimate resource hub for AI-powered game development tools. Discover cutting-edge LLMs, World Model, Agent, Code, Image, Texture, Shader, 3D Model, Animation, Video, Audio, Music, Singing Voice and Analytics. 🔥GitHub stars: 1.3k
  11. Rank 11. sreThe SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.GitHub stars: 1.3k
  12. Rank 12. SkillNetCreate, Evaluate, and Connect AI SkillsGitHub stars: 1.3k
  13. Rank 13. LightMem[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented GenerationGitHub stars: 1.1k
  14. Rank 14. agents-from-scratchBuild AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.GitHub stars: 996
  15. Rank 15. AI-BootcampSelf-paced bootcamp on Generative AI. Tutorials on ML fundamentals, Ollama, LLMs, RAGs, LangChain, LangGraph, Fine-tuning, DSPy & AI Agents (CrewAI), (Using ChatGPT, gpt-oss, Claude, Qwen, Gemma, Llama, Gemini)GitHub stars: 943
  16. Rank 16. FoundryThe foundation layer for agentic intelligence.GitHub stars: 870
  17. Rank 17. manifoldManifold is an experimental platform for enabling long horizon workflow automation using teams of AI assistants.GitHub stars: 496
  18. Rank 18. incognideExplore the unknown, build the future, own your data.GitHub stars: 471
  19. Rank 19. everything-ai-mlA curated collection of learning resources for Generative AI, Machine Learning, Agentic AI, LLMs, RAG, Fine-tuning, MLOps, and more.GitHub stars: 460
  20. Rank 20. mentals-aiNo code AI agentsGitHub stars: 445
  21. Rank 21. ai-platform-engineeringCAIPE is an open-source AI platform for building, governing, and operating AI agents and agentic workflows for platform engineering and beyond.GitHub stars: 408
  22. Rank 22. Curie❓Curie: Automated and Rigorous Scientific Experimentation with AI AgentsGitHub stars: 370
  23. Rank 23. texeraHuman-AI Collaborative Data Science Using Visual WorkflowsGitHub stars: 314
  24. Rank 24. swarmzeroSwarmZero's SDK for building AI agents, swarms of agents and much more.GitHub stars: 275
  25. Rank 25. tinycortexThe Fastest AI Memory Model - Your Second BrainGitHub stars: 253
  26. Rank 26. rails-audit-thoughtbotClaude skill to run code auditsGitHub stars: 248
  27. Rank 27. graphsignal-profilerGraphsignal ProfilerGitHub stars: 245
  28. Rank 28. openbrowser-aiOpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.GitHub stars: 242
  29. Rank 29. agent-pulseEvidence-backed AI industry intelligence — trends, source updates, daily data refreshes, and weekly decision briefs.GitHub stars: 240
  30. Rank 30. EquiblesSelf-hosted, open-source financial data MCP server for AI agents — SEC filings, XBRL financials, 13F holdings, insider & congressional trades, short interest, FRED, CFTC/CBOE and daily prices across 64 MCP tools. Equibles Cloud adds earnings call transcripts, live quotes, options chains with Greeks, guidance and a screener.GitHub stars: 230
  31. Rank 31. Awsome_AI_AgentsThis is end to end course on AI Agents and Agentic AI with 15+ AI Agent Projects with real time use cases and industry expertise.GitHub stars: 222
  32. Rank 32. collective-intelligenceAilin¹ is an open-source collective intelligence engine where tens of thousands of AI models collaborate through dozens of coordination strategies, applying structured diversity and independent reasoning to improve reliability, auditability, and resilience.GitHub stars: 211
  33. Rank 33. stationThe Station is an open-world multi-agent environment where AI agents pursue autonomous scientific discovery and build a shared literature.GitHub stars: 189