1,762 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 agents8,442Claude Code6,875Data and AI3,584Git and workflow3,574Backend and APIs3,550Languages3,468Planning3,315Code review2,876Testing2,653DevOps and cloud2,462Writing and docs2,461Research2,315
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| automateyournetwork/netclaw An AI agent that claws through your network | 715 | Claude Code, Codex, OpenCode | 21 | 22,207 tok |
| ihub-pub/plugins doc.ihub.pub A set of Gradle plugins that greatly simplify project management. | 704 | Claude Code | 1 | 6,974 tok |
| GeminiLight/MindOS mindos.you MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globall | 704 | Claude Code, Codex, OpenCode | 2 | 8,014 tok |
| swarmclawai/swarmclaw swarmclaw.ai Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent sw | 703 | Claude Code | 1 | 3,713 tok |
| cyanheads/obsidian-mcp-server npmjs.com Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via M | 702 | Claude Code, Codex, OpenCode | 2 | 22,004 tok |
| Tencent/loli_profiler Memory instrumentation tool with CI and AI support for android app&game developers. | 700 | Claude Code | 1 | 1,654 tok |
| mnemon-dev/mnemon mnemon.dev LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowled | 693 | Claude Code, Codex, OpenCode | 2 | 723 tok |
| JuliusBrussee/cavemem caveman.so Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed- | 676 | Claude Code | 1 | 1,990 tok |
| blogminhquy/javis-os javisos.com | 633 | Claude Code | 8 | 7,093 tok |
| zhangfengcdt/memoir zhangfengcdt.github.io Hierarchical Agent Memory with Git-Like Version Control | 626 | Claude Code | 1 | 2,014 tok |
| winstonkoh87/Athena-Public winstonkoh87.com Local-first memory, decision engine, and governance harness for AI agents — portable acros | 620 | Claude Code, Codex, OpenCode | 6 | 4,777 tok |
| syi0808/screenize syi0808.github.io (Development of Screenize is currently paused) Open-source macOS screen recording app with | 619 | Claude Code, Codex, OpenCode | 7 | 3,521 tok |
| rtk-ai/icm Permanent memory for AI agents. Single binary, zero dependencies, MCP native. | 613 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 6,485 tok |
| poteto/noodle poteto.github.io Orchestrate agents using skills | 598 | Claude Code, Codex | 34 | 284 tok |
| christopherkarani/Swarm christopherkarani.github.io Type-safe tools, on-device inference, multi-agent workflows, memory, and guardrails, in on | 587 | Claude Code, Codex, OpenCode | 2 | 4,737 tok |
| green-dalii/obsidian-llm-wiki llmwiki.greenerai.top Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linke | 571 | Claude Code, Codex, OpenCode | 2 | 7,934 tok |
| freddy-schuetz/n8n-claw n8n-claw.com OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, | 561 | Claude Code | 1 | 6,906 tok |
| Ikalus1988/MisakaNet misakanet.org Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->htt | 554 | Claude Code, Codex, OpenCode | 2 | 5,866 tok |
| ratel-ai/ratel ratel.sh Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory | 550 | Claude Code, Codex, OpenCode | 2 | 1,079 tok |
| caura-ai/caura caura.ai Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi- | 549 | Claude Code | 2 | — |
| Lumen-Labs/brainapi2 brainapi.lumen-labs.ai BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data in | 549 | Claude Code, Codex, OpenCode | 2 | 53 tok |
| proffesor-for-testing/agentic-qe agentic-qe.dev Agentic QE Fleet is an open-source AI-powered QA/QE platform designed for use with Coding | 525 | Claude Code | 11 | — |
| MagicCube/agentara Your 24/7 personal assistant powered by Claude Code and OpenAI Codex. Multi-channel messag | 518 | Claude Code, Cursor | 4 | 213 tok |
| chandra447/pi-hermes-memory Hermes-style persistent memory and learning loop for Pi coding agent | 514 | Claude Code, Codex, OpenCode | 2 | 1,014 tok |
| itechmeat/open-second-brain dark-factory.techmeat.dev Local-first 🧠 memory for Hermes Agent that lives in your Obsidian vault and remembers pro | 511 | Claude Code | 1 | 824 tok |
| codesstar/loci Memory Palace for AI — persistent memory, identity, and multi-project orchestration for Cl | 504 | Claude Code, Codex, OpenCode | 5 | 258 tok |
| angelnicolasc/graymatter graymatter.nickcerutti.workers.dev 30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also m | 488 | Claude Code, Codex, OpenCode | 2 | 2,408 tok |
| realopslabs/kubeledger kubeledger.io System of Record for Kubernetes cost accounting: per-namespace CPU, memory and GPU usage, | 486 | Claude Code | 1 | 1,092 tok |
| vercel-labs/personal-agent-template personal-agent-template.vercel.app Open-source template for a durable personal AI agent — web chat, Slack, Linear, and long-t | 483 | Claude Code, Codex, OpenCode | 2 | 721 tok |
| juyterman1000/entroly juyterman1000.github.io Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-e | 483 | Claude Code, Codex, Gemini CLI, OpenCode | 6 | 4,667 tok |
| TokenRollAI/llmdoc TokenRoll LLMDoc for Coding Agent | 482 | Claude Code, Codex, OpenCode | 7 | 309 tok |
| disler/claude-code-damage-control | 480 | Claude Code | 5 | 17 tok |
| nemocake/claude-obsidian-assistant | 475 | Claude Code | 1 | 1,063 tok |
| john-rocky/coreai-model-zoo john-rocky.github.io Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac. Chat, vi | 464 | Claude Code, Codex, OpenCode | 2 | 2,954 tok |
| ultracontext/ultracontext ultracontext.com Open Source Context infrastructure for AI agents. Auto-capture and share your agents' cont | 440 | Claude Code, Codex, OpenCode | 2 | 1,951 tok |
| atomicstrata/atomicmemory docs.atomicstrata.ai Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, M | 439 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 2,392 tok |
| brobertsaz/claude-os | 437 | Claude Code | 1 | 1,963 tok |
| cwinvestments/memstack memstack.pro Persistent memory and skill framework for Claude Code: session diary, fact recall, 87 free | 429 | Claude Code | 8 | 847 tok |
| Ruya-AI/cozempic pypi.org Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from contex | 428 | Claude Code | 6 | — |
| ShaftHQ/SHAFT_ENGINE shafthq.github.io Java test automation framework for web, mobile, API, CLI, database, and desktop E2E testin | 418 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 6 | 678 tok |
| Kocoro-lab/Kocoro kocoro.ai A Mac-native AI agent with memory, local computer access, browser control, IM channels, an | 415 | Claude Code, Codex, OpenCode | 2 | 28,674 tok |
| Pratiyush/llm-wiki LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sess | 400 | Claude Code, Codex, OpenCode | 26 | 4,278 tok |
| NeoVertex1/nuggets First AI assistant with holographic memory | 398 | Claude Code | 1 | 382 tok |
| ruvnet/ruv-FANN A blazing-fast, memory-safe neural network library for Rust that brings the power of FANN | 387 | Claude Code | 11 | 1,629 tok |
| lifemate-ai/embodied-claude An MCP suite that gives Claude a physical presence | 377 | Claude Code, Codex, OpenCode | 20 | 8,337 tok |
| marciopuga/cog A plain-text memory system for AI agents. Clone it, point your agent at it, start remember | 377 | Claude Code | 11 | 2,009 tok |
| poteto/brainmaxxing stupid simple persistent memory and skill improvement | 364 | Claude Code, Codex | 10 | 90 tok |
| Charlie85270/Dorothy dorothyai.app Dorothy, the wife your AI agents needs. | 357 | Claude Code, Codex | 4 | 259 tok |
| qf-studio/navigator quantflow.studio Finish What You Start — Context engineering for Claude Code. Sessions last 20+ exc | 355 | Claude Code | 2 | 5,653 tok |
| kunchenguid/vision Agent skill that mines your repo's history to draft a VISION.md, stress-tests it with hard | 345 | Claude Code, Codex, OpenCode | 2 | 150 tok |