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 |
|---|---|---|---|---|
| nablo-io/lerim docs.lerim.dev Compiles AI agent traces and truns them into reusable context. | 97 | Claude Code, Codex, OpenCode | 2 | 1,428 tok |
| pinkpixel-dev/mem0-mcp pinkpixel.dev A memory system using mem0 for AI applications. Enables long-term memory for AI agents as | 96 | Claude Code, Codex | 2 | — |
| aaronnat23/disp8ch Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and | 96 | Codex, OpenCode | 1 | 227 tok |
| rasimme/FlowBoard clawhub.ai Local-first project management and persistent context for OpenClaw, Claude Code, Codex, Cu | 96 | Codex, OpenCode | 1 | 450 tok |
| tpierrain/kenjaku Kenjaku is a Karpathy-style LLM wiki, reinforced where it counts with battle-tested softwa | 96 | Claude Code | 11 | 5,261 tok |
| RLabs-Inc/memory Memory server for llms that can be easily integrated to any client. | 94 | Claude Code | 1 | 1,848 tok |
| joe960913/Jixu jixu.dev Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, expl | 93 | Claude Code, Codex, OpenCode | 2 | 3,488 tok |
| arpitnath/claude-capsule-kit npmjs.com A toolkit that makes Claude Code better at engineering — session memory, dependency analys | 93 | Claude Code | 1 | 1,133 tok |
| henryhawke/mcp-titan This tool is a cutting-edge memory engine that blends real-time learning, persistent three | 93 | Claude Code | 1 | 784 tok |
| ruvnet/sublinear-time-solver Rust + WASM sublinear-time solver for asymmetric diagonally dominant systems. Exposes Neum | 92 | Claude Code | 5 | — |
| zby/commonplace The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, | 92 | Claude Code, Codex, OpenCode | 4 | 2,964 tok |
| TGYD-helige/pi Pluggable extension packages for the Pi AI-agent runtime. Each package exposes LLM-callabl | 92 | Claude Code, Codex, OpenCode | 2 | 4,823 tok |
| CloudLLM-ai/mentisdb mentisdb.com Memory that lasts and compounds. MentisDB gives agents durable memory so they do not just | 91 | Codex, OpenCode | 1 | 176 tok |
| zcag/tela telawiki.com Open-source, self-hostable markdown team wiki with a built-in MCP server — so AI agents re | 91 | Claude Code | 1 | 7,681 tok |
| ldclabs/KIP anda.ai 🧬 KIP (Knowledge Interaction Protocol) is an open protocol for durable AI agent memory an | 91 | Codex, OpenCode | 1 | 2,737 tok |
| vstorm-co/memv vstorm-co.github.io Structured, temporal memory for AI agents. | 90 | Claude Code | 6 | 1,576 tok |
| nikita-rulenko/Helixir One infinite session for any agents and harness you have. No more degradation and hallucin | 90 | Codex, OpenCode | 1 | 8,101 tok |
| raia-live/amfs sense-lab.ai Recursive Self-Improvement for AI agents and models, helping your agents self-improve with | 90 | Claude Code | 1 | 3,099 tok |
| Soul-Brews-Studio/arra-oracle-v3 Oracle v2 - MCP Memory Layer with semantic search, philosophy, and knowledge management | 90 | Claude Code, Codex, OpenCode | 17 | 8,313 tok |
| adelinamart/robrain robrain.dev Shared memory across your team and your AI agents — with judgment about what's worth keepi | 89 | Codex, OpenCode | 1 | 586 tok |
| Vortx-AI/emem emem.dev A memory that's external, shareable & verifiable. Complements web search for real world ta | 89 | Claude Code, Codex, Gemini CLI, OpenCode | 2 | 2,970 tok |
| deivid11/obsidian-claude-code-plugin Interactive Claude Code integration for Obsidian | 88 | Claude Code | 1 | 379 tok |
| vitaecontext/vitaecontext vitaecontext.github.io AI agent context layer for career-related tasks. | 88 | Codex, GitHub Copilot, Gemini CLI, OpenCode | 3 | 1,238 tok |
| joelhooks/pi-tools 🔧 Power tools for pi — repo autopsy, tsgo LSP, codex background loops, session reader, an | 87 | Claude Code, Codex, OpenCode | 2 | 388 tok |
| TOKTOKHAN-DEV/agent-company agent-company.site Create an automated organization with an AI Company | 87 | Claude Code, Codex, OpenCode | 8 | 5,073 tok |
| brake71/1c-ssl-skills A collection of skills for AI agents working with 1C's Library of Standard Subsystems (BSP | 85 | Claude Code, Codex | 19 | 1,553 tok |
| sandst1/remind sandst1.github.io A memory layer for AI Agents | 84 | Claude Code, Codex, OpenCode | 6 | 3,423 tok |
| shyftlabs/continuum docs.continuum.shyftlabs.io Continuum — the agent runtime by ShyftLabs. Build, orchestrate, ship. | 84 | Claude Code, Codex, OpenCode | 13 | 6,521 tok |
| attunehq/nudge attunehq.com Give your agent a nudge. | 84 | Claude Code, Codex, OpenCode | 6 | 6,135 tok |
| simpx/loopat Self-hosted AI workspace built around context management. Works solo, scales to teams. | 84 | Claude Code | 1 | 708 tok |
| Abinesh-L/claude-crusts Analyze your Claude Code context window, detect wasted tokens, and get pasteable fix comma | 82 | Claude Code | 2 | 15,122 tok |
| postmelee/hyper-waterfall A human-governed AI coding workflow that distills ephemeral session context into persisten | 82 | Claude Code, Codex, OpenCode | 2 | 1,432 tok |
| sverklo/sverklo sverklo.com Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Code | 82 | Claude Code | 1 | 406 tok |
| tuirk/Kompl A compounding LLM-wiki, best fit as a personal second brain that organizes and updates its | 82 | Codex, OpenCode | 1 | 1,558 tok |
| escoffier-labs/brigade brigadestack.com Brigade Stack: run coding agents anywhere and keep one record of the work. Shared tasks, c | 82 | Codex, OpenCode | 1 | 2,653 tok |
| orual/pattern agent builder | 81 | Claude Code, Codex, OpenCode | 4 | 1,420 tok |
| openJiuwen-ai/agent-memory Memory is a long-term memory module for AI agents, providing capabilities for memory extra | 81 | Claude Code, Codex, OpenCode | 3 | 3,129 tok |
| dragosroua/claude-assess-decide-do-mega-prompt dragosroua.com First human cognitive framework integrated into an LLM. Claude learns to detect if you're | 80 | Claude Code | 9 | 584 tok |
| kunickiaj/codemem codemem.sh A lightweight persistent-memory companion for OpenCode & Claude | 80 | Codex, OpenCode | 1 | 1,357 tok |
| panayiotism/claude-harness | 79 | Claude Code | 2 | 701 tok |
| 7xuanlu/wenlan wenlan.app A living personal wiki. Wenlan turns your documents, notes, and AI chats into pages with l | 79 | Claude Code, Codex, OpenCode | 5 | 1,448 tok |
| TSchonleber/brainctl A cognitive memory system for AI agents. Single SQLite file. MCP server included. | 78 | Claude Code | 1 | 6,298 tok |
| juntoku9/Sessory Shared memory for AI coding sessions. | 78 | Claude Code | 1 | 522 tok |
| baldaworks/callee Markdown-defined provider-backed agents and deterministic workflows for ACP runtimes. | 78 | Claude Code, Codex, OpenCode | 3 | 355 tok |
| lsszz2100/VibeHacking A Collection of Repositories, Videos, Books, and Lecture Materials to Learn Security & Hac | 78 | Codex, OpenCode | 1 | 28,786 tok |
| kuitos/opencode-claude-memory npmjs.com OpenCode plugin for Claude Code memory: persistent local Markdown memory shared with Claud | 78 | Codex, OpenCode | 1 | 5,519 tok |
| serac-labs/serac serac.build A ServiceNow MCP server, and the skill guides that teach an agent to use it. 400+ snow_* t | 77 | Claude Code, Codex, OpenCode | 1 | 1,554 tok |
| tech4idea/viforge ViForge is a local-first AI collaboration workbench for creative and knowledge work. It he | 77 | Codex, OpenCode | 1 | 1,036 tok |
| AI4CreativityLab/Index.skill “Index.skill,” a personal knowledge management, updating, and interaction system based on | 77 | Claude Code | 6 | 2,933 tok |
| hassancs91/brainoutside brainoutside.com Self-hosted memory server for AI agents. Your brain is a git repo, served over MCP and RES | 77 | Claude Code | 1 | 1,796 tok |