2,373 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 |
|---|---|---|---|---|
| sordi-ai/skill-everything Git-versioned agent memory: agents that never make the same mistake twice. Anthropic-Skill | 21 | Claude Code, Codex, Cursor, Gemini CLI, OpenCode | 4 | 4,060 tok |
| aws-samples/sample-ai-assistant-on-agentcore A full-stack AI assistant built on Amazon Bedrock AgentCore. This sample demonstrates how | 21 | Codex, OpenCode | 1 | 3,651 tok |
| context-foundry/context-foundry contextfoundry.dev Stop vibe coding. Start building. | 21 | Claude Code, GitHub Copilot | 9 | 2,921 tok |
| paladini/mcp-me mcp-me.page Your AI assistants don't know who you are. mcp-me fixes that: a local MCP server that give | 21 | Codex, GitHub Copilot, OpenCode | 2 | 1,577 tok |
| monkey2jack/aiduMEI aiduMEI⚕ Aidu Memory Engine Insight · General-purpose wisdom engine for agents — Excellent | 21 | Codex, OpenCode | 1 | 1,538 tok |
| flowercomputers/hivemind global agent memory and skill sharing | 21 | Codex, OpenCode | 1 | 1,948 tok |
| hilyfux/knowledge-graph Stop AI Coding from forgetting. A knowledge graph–driven memory layer for LLMs (ChatGPT, | 21 | Claude Code, Codex, OpenCode | 2 | 1,190 tok |
| HMAKT99/AKF akf.dev Trust metadata for AI agents — a stamp costs ~15 tokens, re-verifying costs 15,000. Agents | 21 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode, Windsurf | 5 | 1,886 tok |
| wuisabel-gif/Delphin wuisabel-gif.github.io A duplex companion for AI agent CLIs: talk and listen at the same time. | 21 | Claude Code, Codex | 1 | — |
| oakoss/agent-skills | 21 | Claude Code, Codex, OpenCode | 4 | 1,956 tok |
| crustyhacker/pi-jarvis Memory you can edit. Watchers that wake an idle Pi agent without model polling. A persiste | 21 | Codex, OpenCode | 1 | 7,602 tok |
| putervision/spc spaceproofcode.com High-performance zero-dependency static analysis tool enforcing NASA Power of Ten rules ac | 20 | Claude Code, GitHub Copilot | 2 | 3,510 tok |
| natea/ExoMind Highly skilled voice-based assistant with intimate knowledge of your preferences, interest | 20 | Claude Code | 6 | 3,282 tok |
| coalesce-labs/catalyst Deprecated — Catalyst local runtime, kept for history. Use coalesce-labs/catalyst-dev-skil | 20 | Claude Code, Codex, OpenCode | 2 | 7,966 tok |
| Alenryuichi/openmemory-plus 🧠 AI Agent Memory Management Framework - Dual-layer memory architecture with smart classi | 20 | Codex, OpenCode | 1 | 1,017 tok |
| neverinfamous/memory-journal-mcp search.adamic.tech Secure AI Memory MCP Server with Multi-Tenancy, Dynamic Project Routing, Auto Session Brie | 20 | GitHub Copilot | 1 | 2,706 tok |
| julymetodiev/post-cortex 369.is Post-Cortex provides durable memory infrastructure with automatic knowledge graph construc | 20 | Claude Code | 5 | 870 tok |
| KitTheFox123/workspace Kit's open-sourced agent workspace 🦊 - SOUL.md, memory, knowledge, scripts | 20 | Codex, OpenCode | 1 | 628 tok |
| hyungchulc/memory-forest A verifiable local memory architecture for long-running AI agents | 20 | Codex, OpenCode | 1 | 195 tok |
| mondweep/sparc-evolution Evolution of the SPARC methodology | 20 | Claude Code | 37 | 8,669 tok |
| 1EchA/context-sync-mcp Cross-device context sync for coding agents via MCP + Git | | 20 | Cursor | 1 | 184 tok |
| adamwang99/NEUTRON-EVO-OS NEUTRON EVO OS - Self-Evolving Intelligence via Functional Accumulation $\int f(t)dt$ & Me | 20 | Claude Code | 1 | 512 tok |
| j3k0/mcp-brain-tools A powerful MCP memory using a knowledge graph powered by elastic search | 20 | Claude Code | 1 | 687 tok |
| ProsusAI/prism Give Claude Code persistent memory — captures patterns from your sessions, validates them | 20 | Claude Code | 1 | 2,987 tok |
| jumppad-labs/spektacular spektacular.dev Spec-driven development for AI coding agents. Spektacular helps you to generate specificat | 20 | Claude Code, Codex, OpenCode | 4 | 4,884 tok |
| russbeye/claude-memory-bank Give Claude Code a brain upgrade. Automatically tracks your work and keeps everything orga | 20 | Claude Code | 1 | 849 tok |
| nemanjavlahovic/instruments-mcp-server MCP server for Xcode Instruments — AI agents get structured performance profiling (CPU, Sw | 20 | Claude Code | 1 | 480 tok |
| asimons81/nexusos Files you own. Memory your agents can trust. Also: your AI won't gaslight you about what's | 20 | Codex, OpenCode | 1 | 1,779 tok |
| growilabs/growi-mcp-server A Model Context Protocol (MCP) server that connects AI models to GROWI wiki content. Enabl | 20 | Claude Code, Kiro | 16 | 2,793 tok |
| hereisSwapnil/memwiki A persistent memory protocol for AI coding agents that gives projects a shared, markdown b | 20 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode | 4 | 680 tok |
| JubaKitiashvili/context-mem npmjs.com Your AI forgets everything between sessions. This fixes that — 98%+ retrieval accuracy, 10 | 20 | Claude Code | 1 | 1,038 tok |
| staticroostermedia-arch/engram glama.ai Geometric agent memory for Agents: 8-tool lean contract, harness injection at wake, sessio | 20 | Claude Code, Codex, OpenCode | 2 | 3,188 tok |
| hjqcan/GoodMemory npmjs.com Local-first, auditable memory layer for AI apps and coding agents — Codex, Claude Code, MC | 20 | Claude Code, Codex, OpenCode | 2 | 3,320 tok |
| Ramsbaby/jarvis Frozen reference snapshot (Oct 2026) of a self-hosted AI operations stack — Discord bot + | 20 | Claude Code | 3 | 1,997 tok |
| Muvon/octobrain octomind.run Persistent memory for AI assistants — semantic search, knowledge graph, and MCP server int | 20 | Codex, OpenCode | 1 | 2,898 tok |
| chenmingtang830/proofpress proofpress.dev Decision infrastructure for agents. Verifiable, traceable, auditable. | 20 | Claude Code, Codex, OpenCode | 2 | 6,095 tok |
| FastEndpoints/Documentation fast-endpoints.com Documentation website source code for FastEndpoints. | 20 | Codex, OpenCode | 1 | 650 tok |
| menkesu/genaipm-claw genaipm.com Turn NanoClaw into an AI PM operating system — 16 skills, daily brief, Command Center, mem | 19 | Claude Code | 1 | — |
| Lyzr-Cognis/claude-cognis A Claude Code plugin that gives your AI persistent memory across sessions using Cognis. Yo | 19 | Claude Code | 2 | — |
| GetCacheOverflow/CacheOverflow | 19 | Codex, OpenCode | 1 | 2,197 tok |
| paulyuk/snap-squad Warm-start addon for bradygaster/squad — pre-baked agent squads for hire for instant deplo | 19 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 2,506 tok |
| shravan-swagwalapm/shipstack Knowledge OS for AI-assisted development. Memory, past mistakes, decision records, session | 19 | Claude Code | 1 | 1,080 tok |
| tim-mccrimmon/structured-context-spec structuredcontext.dev A community-driven specification for creating, validating, and versioning structured conte | 19 | Claude Code | 1 | 2,486 tok |
| stevenflyai/llm-wiki-web Implementation inspired by Andrej Karpathy's LLM Knowledge Base pattern. | 19 | Claude Code | 3 | 1,681 tok |
| Wolfe-Jam/grok-faf-mcp faf.one Persistent Project Context for xAI Grok — IANA-registered .faf format · MCP server on a UR | 19 | Claude Code, Codex, OpenCode | 2 | 1,195 tok |
| dsebastien/obsidian-cli-rest dsebastien.github.io Control your Obsidian vault programmatically. This plugin turns all Obsidian CLI commands | 19 | Claude Code, Codex, OpenCode | 3 | 10,297 tok |
| fstamatelopoulos/cerefox cerefox.org Shared memory for your AI agents: what one agent learns, every other agent can find. Hybri | 19 | Claude Code | 1 | 13,284 tok |
| edg-l/engram-mcp crates.io MCP server in Rust for AI agent persistent memory: branch-aware session handoffs, local ON | 19 | Claude Code | 1 | 7,648 tok |
| SecurityRonin/alaya A memory engine for conversational AI agents, inspired by neuroscience and Buddhist psycho | 19 | Claude Code | 1 | 96 tok |
| keshrath/agent-knowledge npmjs.com Cross-session memory and recall for AI agents — git-synced knowledge base, hybrid semantic | 19 | Claude Code | 1 | 3,056 tok |