1,284 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 |
|---|---|---|---|---|
| agentic-in/elephant-agent elephant.agentic-in.ai Personal-Model First Self Evolving AI Agent 🐘 | 582 | Codex, GitHub Copilot, OpenCode | 2 | 1,922 tok |
| liliu-z/stashbase stashbase.ai Turn local files into searchable context for AI agents. | 577 | Claude Code, Codex, OpenCode | 2 | 1,898 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 |
| 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 |
| mnemon-dev/mnemon LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowled | 561 | Claude Code, Codex, OpenCode | 2 | 723 tok |
| zosmaai/pi-llm-wiki zosmaai.github.io Self-maintaining, Obsidian-compatible knowledge base for pi — turn raw sources into an int | 560 | Codex, OpenCode | 1 | 594 tok |
| rtk-ai/icm Permanent memory for AI agents. Single binary, zero dependencies, MCP native. | 557 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 6,485 tok |
| nossa-y/activity-frames Turn your workday into structured workflows agents can execute. 100% local, served over MC | 541 | Codex, OpenCode | 1 | 861 tok |
| flytohub/flyto-core flyto2.com AI said it finished. Flyto2 shows the proof. | 480 | Claude Code, Codex, OpenCode | 2 | 1,488 tok |
| taylorsatula/mira-OSS miraos.org This is the public release of MIRA OS. Discrete memories decay through momentum loss, tool | 478 | Codex, OpenCode | 1 | 5,586 tok |
| angelnicolasc/graymatter graymatter.nickcerutti.workers.dev 30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also m | 465 | Claude Code, Codex, OpenCode | 2 | 1,836 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 | 464 | Claude Code, Codex, OpenCode | 2 | 721 tok |
| ai-driven-dev/framework ai-driven-dev.fr Marketplace Framework AI-Driven Dev : Context Engineering, Plugins, Agents, Skills, Hooks, | 455 | Claude Code, Codex, OpenCode | 4 | 1,664 tok |
| Ikalus1988/MisakaNet misakanet.org 📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously shar | 450 | Claude Code, Codex, OpenCode | 2 | 1,005 tok |
| Dicklesworthstone/cass_memory_system Procedural memory for AI coding agents: transforms scattered session history into persiste | 435 | Codex, OpenCode | 1 | 8,655 tok |
| ratel-ai/ratel ratel.sh Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory | 433 | Claude Code, Codex, OpenCode | 2 | 1,018 tok |
| atomicstrata/atomicmemory docs.atomicstrata.ai Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, M | 429 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 2,392 tok |
| halofyai/halofy halofy.ai Halofy is the open access and governance layer for AI agents across your organization. Ide | 424 | Codex, OpenCode | 1 | 1,533 tok |
| chandra447/pi-hermes-memory Hermes-style persistent memory and learning loop for Pi coding agent | 418 | Claude Code, Codex, OpenCode | 2 | 870 tok |
| john-rocky/coreai-model-zoo john-rocky.github.io Community model zoo for Apple Core AI (iOS/macOS 27): 66 models — LLM, VLM, OCR, ASR, TTS, | 409 | Claude Code, Codex, OpenCode | 2 | 2,026 tok |
| ShaftHQ/SHAFT_ENGINE shafthq.github.io Java test automation framework for web, mobile, API, CLI, database, and desktop E2E testin | 408 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 38 | 1,295 tok |
| Kocoro-lab/Kocoro kocoro.ai A Mac-native AI agent with memory, local computer access, browser control, IM channels, an | 407 | Claude Code, Codex, OpenCode | 2 | 28,639 tok |
| Pratiyush/llm-wiki LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sess | 385 | Claude Code, Codex, OpenCode | 26 | 4,278 tok |
| lifemate-ai/embodied-claude An MCP suite that gives Claude a physical presence | 377 | Claude Code, Codex, OpenCode | 20 | 8,315 tok |
| veyliss/ai-localbase A local-first AI knowledge base system (RAG) for integrating local documents into assisted | 377 | Codex, OpenCode | 1 | 109 tok |
| Goldentrii/AgentRecall-X Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across | 371 | Codex, OpenCode | 1 | 2,047 tok |
| mengjian-github/xiaomo-starter-kit xiaomo.dev 🐈⬛ OpenClaw Chinese AI assistant template | Get your own AI personal assistant in 5 minu | 367 | Codex, OpenCode | 1 | 261 tok |
| LTplus-AG/ifc-lite ifclite.dev Open-source IFC toolkit: WebGPU rendering, columnar in-memory store, exact-arithmetic geom | 360 | Claude Code, Codex, Cursor, OpenCode | 3 | 11,443 tok |
| spencermarx/open-code-review AI-powered multi-agent code review. Simulates a customizable team of Engineers performing | 355 | Claude Code, Codex, OpenCode | 11 | 2,239 tok |
| Lyellr88/marm-memory lyellr88.github.io Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS C | 350 | Codex, OpenCode | 1 | 2,165 tok |
| awizemann/harness awizemann.github.io AI-driven user testing for iOS Simulator, macOS apps, and web apps. Write a goal in plain | 345 | Codex, GitHub Copilot, Gemini CLI, OpenCode | 3 | 2,968 tok |
| gatelynch/llm-knowledge-base Inspired by Andrej Karpathy's llm-wiki concept, a personal knowledge base system that clea | 329 | Claude Code, Codex, OpenCode | 9 | 2,933 tok |
| kunchenguid/vision Agent skill that mines your repo's history to draft a VISION.md, stress-tests it with hard | 314 | Claude Code, Codex, OpenCode | 2 | 150 tok |
| AGI-is-going-to-arrive/Memory-Palace Memory Palace is a long-term memory operating system purpose-built for AI Agents. | 311 | Codex, OpenCode | 1 | 303 tok |
| sopaco/cortex-mem sopaco.github.io 🧠 The production-ready cognitive foundation for autonomous systems such as Embodied-AI an | 307 | Codex, OpenCode | 1 | 1,620 tok |
| mathomhaus/guild Shared context, memory, and task coordination across AI coding agents. Single Go binary, l | 305 | Claude Code, Codex, OpenCode | 2 | 701 tok |
| Lumen-Labs/brainapi2 brainapi.lumen-labs.ai BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data in | 304 | Claude Code, Codex, OpenCode | 2 | 53 tok |
| ScottRBK/forgetful Opensource Memory for Agents | 298 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 411 tok |
| hsingjui/ContextWeaver ContextWeaver is a tool based on the MCP protocol that uses Tree-sitter and vector search | 297 | Claude Code, Codex, OpenCode | 2 | 1,216 tok |
| myICOR/myPKA myicor.com AI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain | 295 | Claude Code, Codex, OpenCode | 8 | 6,334 tok |
| ultracontext/ultracontext ultracontext.com Open Source Context infrastructure for AI agents. Auto-capture and share your agents' cont | 289 | Claude Code, Codex, OpenCode | 2 | 1,951 tok |
| ling-kong-ran/pisper ling-kong-ran.github.io Multi-agent app for parallel sessions, tools, memory, workflows, desktop, terminal, and mo | 284 | Codex, OpenCode | 1 | 4,109 tok |
| egregore-labs/egregore egregore.xyz Shared intelligence layer for organizations | 282 | Claude Code, Codex, OpenCode | 59 | 15,235 tok |
| fpytloun/mnemory A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides i | 277 | Codex, OpenCode | 1 | 4,008 tok |
| AIOSAI/AIPass aipass.ai Persistent Agent Workspace — AI agents that remember, collaborate, and never start from ze | 273 | Claude Code, Codex, OpenCode | 7 | 568 tok |
| Signet-AI/signetai signetai.sh Sync and store memories, shared identity files (AGENTS.md, CLAUDE.md), session transcripts | 273 | Claude Code, Codex, OpenCode | 4 | 2,249 tok |
| detroittommy879/aicodeprep-gui wuu73.org Surgical context engineering with a nice UI, Windows, Mac, Linux, BSD, anywhere where pyth | 272 | Claude Code, Codex, OpenCode | 2 | 3,881 tok |
| huiliyi37/dsh-tianshu-tui An interactive terminal UI plugin for the official DeepSeek Harness: custom minimal ANSI r | 264 | Codex, OpenCode | 1 | 1,210 tok |
| 69gg/Undefined QQ bot platform with cognitive memory architecture and multi-agent Skills, via OneBot V11. | 261 | Claude Code, Codex, OpenCode | 2 | 5,261 tok |
| taichuy/1flowbase 1flowbase.taichuy.com 1flowbase: self-hosted AI gateway with protocol translation, dispatch, chat logs, built-in | 259 | Claude Code, Codex, Gemini CLI, OpenCode | 10 | 1,558 tok |