2,354 projects whose own agent configuration covers memory and context. These are not mods to install — they are how the maintainers of these repositories tell an agent what to do, and what to avoid.
All projects Building agents7,374Claude Code6,573Data and AI3,706Backend and APIs3,486Languages3,398Planning3,181Git and workflow3,100Code review2,701Testing2,311Research2,292DevOps and cloud2,282Writing and docs2,269
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| RinDig/Interpretable-Context-Methodology Folder structure as agent architecture. ICM replaces framework-level orchestration with f | 1,146 | Claude Code | 1 | 439 tok |
| Mibayy/token-savior mibayy.github.io MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active t | 1,144 | Claude Code, Codex, OpenCode | 2 | 3,006 tok |
| metaskills/experts unremarkable.ai Experts.js is the easiest way to create and deploy OpenAI's Assistants and link them toget | 1,063 | Cursor | 1 | 371 tok |
| SterlingChin/marvin-template MARVIN is your personal AI assistant that can help you connect to the apps you need and ha | 1,017 | Claude Code | 18 | 2,792 tok |
| AlmanacCode/codealmanac codealmanac.com A codebase wiki for AI coding agents. Captures what the code can't say: decisions, flows, | 993 | Claude Code, Codex, OpenCode | 5 | 3,548 tok |
| Kulaxyz/self-learning-skills A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a | 949 | Codex, OpenCode | 1 | 846 tok |
| oceanbase/powercontext powercontext.oceanbase.io Not only memory but a full story. | 944 | Codex, OpenCode | 1 | 1,049 tok |
| toonight/get-shit-done-for-antigravity | 940 | Claude Code, Codex | 17 | — |
| hmans/beans A CLI-based, flat-file issue tracker for humans and robots. 🤖 | 915 | Claude Code | 6 | 1,364 tok |
| vostride/agent-qa vostride.com Open-source self-improving QA agent for software teams. A test harness with memory. Write | 901 | Codex, OpenCode | 1 | 1,569 tok |
| beita6969/ScienceClaw scienceclaw.science 🔬🦞 A self-evolving AI research colleague for scientists. 285 skills, zero hallucination, | 894 | GitHub Copilot | 1 | 574 tok |
| ComposioHQ/trustclaw A self-hostable personal AI agent with vector memory, Composio tools, and Telegram. | 891 | Claude Code | 1 | 6,071 tok |
| pydantic/pydantic-ai-harness Your agent's favorite harness, built on Pydantic AI | 857 | Claude Code, Codex, OpenCode | 6 | 2,654 tok |
| asheshgoplani/agent-deck discord.gg Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex | 845 | Claude Code, Codex | 3 | — |
| awizemann/scarf awizemann.github.io Native macOS and iOS App for the Hermes AI agent — multi-window, multi-server (local + rem | 844 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 4 | 3,716 tok |
| kunchenguid/backpass You don't write AGENTS.md. You train it with gradient descent. | 843 | Claude Code, Codex, OpenCode | 2 | 6,577 tok |
| verygoodplugins/automem automem.ai Long-term memory for AI assistants. Graph + vector store that recalls decisions, relations | 811 | Claude Code, Codex, OpenCode | 2 | 6,251 tok |
| taracodlabs/aiden aiden.taracod.com Aiden — Autonomous AI agent that operates your computer with prompts: browser control, ter | 808 | Codex, OpenCode | 1 | 1,664 tok |
| ruvnet/agentic-flow ruv.io Easily switch between alternative low-cost AI models in Claude Code/Agent SDK. For those c | 801 | Claude Code | 12 | 1,672 tok |
| christopherkarani/Wax christopherkarani.github.io Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo | 788 | Codex, OpenCode | 1 | 1,437 tok |
| vshulcz/deja-vu vshulcz.github.io Memory for coding agents built from the session history already on disk: Claude Code, Code | 780 | Claude Code, Gemini CLI | 2 | 236 tok |
| coleam00/second-brain-starter Build your own AI Second Brain with Claude Code - a skill that generates a personalized PR | 768 | Claude Code | 1 | — |
| RichmondAlake/memorizz MemoRizz: A Python library serving as a memory layer for AI applications. Leverages popula | 765 | Claude Code | 1 | — |
| aws/bedrock-agentcore-sdk-python Python SDK for transforming any AI agent into a production-ready application. Framework-ag | 757 | Codex, OpenCode | 1 | 31 tok |
| grapeot/context-infrastructure A context and memory system for AI coding agents. Persistent memory, personal rules, skill | 745 | Codex, OpenCode | 1 | 1,190 tok |
| kitfunso/hippo-memory hippo-memory.com Biologically-inspired memory for AI agents. Decay, retrieval strengthening, consolidation. | 740 | Claude Code, Codex, OpenCode | 2 | 417 tok |
| AVIDS2/memorix mem.rglens.com Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Cod | 729 | Claude Code, Gemini CLI | 2 | 1,919 tok |
| neo4j-labs/create-context-graph create-context-graph.dev AI agents with graph based reasoning memory, scaffolded in seconds | 719 | Claude Code | 1 | 12,544 tok |
| aeonfun/aeon aeon.fun The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing sk | 716 | Claude Code, Codex, OpenCode | 3 | 7,960 tok |
| agentic-box/memora Give your AI agents persistent, collective memory — with deduplicating absorb, supersessio | 715 | Claude Code | 1 | 63 tok |
| ihub-pub/plugins doc.ihub.pub A set of Gradle plugins that greatly simplify project management. | 711 | Claude Code | 1 | 6,974 tok |
| LC044/TrailSnap trailsnap.cn TrailSnap (行影集) | AI-powered open-source photo album for travel and life memories. | 709 | Claude Code, Codex, OpenCode | 2 | 8,520 tok |
| jason-effi-lab/karpathy-llm-wiki-vault | 701 | Claude Code | 4 | 1,191 tok |
| Tencent/loli_profiler Memory instrumentation tool with CI and AI support for android app&game developers. | 692 | Claude Code | 1 | 592 tok |
| JuliusBrussee/cavemem caveman.so Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed- | 677 | Claude Code | 1 | 1,990 tok |
| cyanheads/obsidian-mcp-server npmjs.com Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via M | 673 | Claude Code, Codex, OpenCode | 2 | 13,450 tok |
| GeminiLight/MindOS mindos.you MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globall | 666 | Claude Code, Codex, OpenCode | 2 | 7,887 tok |
| elvisun/newsjack newsjack.sh The open-source skills that turn your agent into a full PR team. | 665 | Claude Code, Codex, OpenCode | 2 | 2,168 tok |
| swarmclawai/swarmclaw swarmclaw.ai Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent sw | 663 | Claude Code | 1 | 3,713 tok |
| automateyournetwork/netclaw An AI agent that claws through your network | 650 | Claude Code, Codex, OpenCode | 2 | 12,239 tok |
| sandbaseai/sandbase-harness Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, | 642 | Codex, OpenCode | 1 | 1,731 tok |
| zavora-ai/adk-rust adk-rust.com Rust Agent Development Kit (ADK-Rust): Build AI agents in Rust with modular components for | 638 | Codex, OpenCode | 1 | 12,794 tok |
| kiwifs/kiwifs docs.kiwifs.com Markdown filesystem for agents and teams. | 623 | Codex, OpenCode | 1 | 1,245 tok |
| alibaba/anolisa agentic-os.sh ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with | 617 | Codex, OpenCode | 1 | 5,082 tok |
| zhangfengcdt/memoir zhangfengcdt.github.io Hierarchical Agent Memory with Git-Like Version Control | 610 | Claude Code | 1 | 1,839 tok |
| syi0808/screenize syi0808.github.io (Development of Screenize is currently paused) Open-source macOS screen recording app with | 602 | Claude Code, Codex, OpenCode | 7 | 3,521 tok |
| MaxFreedomPollard/Compartment maxfreedompollard.github.io Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and | 592 | Gemini CLI | 1 | 613 tok |
| winstonkoh87/Athena-Public winstonkoh87.com Athena is a local-first agentic PKM that helps you make better decisions with your own con | 582 | Claude Code, Codex, OpenCode | 6 | 4,355 tok |
| agentic-in/elephant-agent elephant.agentic-in.ai Personal-Model First Self Evolving AI Agent 🐘 | 582 | Codex, GitHub Copilot, OpenCode | 2 | 1,922 tok |
| christopherkarani/Swarm christopherkarani.github.io Type-safe tools, on-device inference, multi-agent workflows, memory, and guardrails, in on | 574 | Claude Code, Codex, OpenCode | 2 | 4,714 tok |