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 |
|---|---|---|---|---|
| kubony/claude-knowledge-graph Convert Markdown notes into an RDF/TTL knowledge graph for semantic search with SPARQL que | 48 | Claude Code | 5 | 1,402 tok |
| salavender/antigravity-compound-engineering-plugin Non-Official Antigravity IDE compound engineering plugin | 48 | Gemini CLI | 1 | 1,242 tok |
| neul-labs/fast-litellm fast-litellm.neullabs.com High-performance Rust acceleration for LiteLLM - providing significant performance improve | 48 | Claude Code | 1 | 1,987 tok |
| Anantys-oss/koan koan.anantys.com Autonomous background agent that consumes unused Claude Max quota to explore, audit, and i | 48 | Claude Code, Codex, GitHub Copilot, OpenCode | 18 | 7,998 tok |
| benclawbot/open-brain User-owned memory and continuity layer for coding agents — provenance-aware semantic memor | 48 | Codex, OpenCode | 1 | 84 tok |
| raphasouthall/neurostack neurostack.sh Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded | 47 | Claude Code | 1 | 5,085 tok |
| jessepinkman9900/claude-second-brain jessepinkman9900.github.io Fastest way to scaffold your LLM powered personal knowledge base - Obsidian, Claude Code, | 46 | Claude Code | 1 | 3,260 tok |
| scottonanski/persistent-mind-model-v1.0 Event-sourced runtime for reconstructable AI identity, memory, reflection, commitments, an | 46 | Codex, OpenCode | 2 | 214 tok |
| ZM-BAD/headroom Know when your AI is about to forget — browser extension that monitors context window usag | 46 | Claude Code, Codex, OpenCode | 2 | 6,644 tok |
| strangeadvancedmarketing/Adam strangeadvancedmarketing.github.io Adam Framework for OpenClaw — 5-layer persistent memory and identity architecture for AI a | 45 | Codex, OpenCode | 1 | 791 tok |
| robotaitai/project-bedrock Every session starts with context, every decision leaves a trail, and every session leaves | 45 | Claude Code | 8 | — |
| jonaschen/Android-Software A Hierarchical AI Agent Skill Set for managing AOSP platform integration, built on an MMU- | 45 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 2,760 tok |
| desek/outlook-local-mcp outlook-local-mcp.com Local MCP server for Microsoft Outlook — calendars, events, and email via Microsoft Graph | 45 | Claude Code, Codex, OpenCode | 9 | 5,634 tok |
| iops-leo/claude-slim npmjs.com Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agen | 44 | Claude Code, Codex, OpenCode | 2 | 774 tok |
| hyxnj666-creator/ai-memory npmjs.com Extract structured knowledge from Cursor & Claude Code conversations into git-trackable Ma | 44 | Codex, OpenCode | 1 | 4,126 tok |
| lazymac2x/agent-wiki A Knowledge-Assetization OS for AI agents — an industry-specialized LLM wiki + business-lo | 44 | Claude Code, Codex, OpenCode | 5 | 3,303 tok |
| StepzeroLab/research-git research-git-feature-replay.linyux1104.chatgpt.site A new Git tool for researchers and developers to capture experiments and features as reusa | 44 | Claude Code | 1 | 1,244 tok |
| MedAdemBHA/docflow Documentation memory for AI coding agents—route project knowledge, reduce repeated context | 44 | Codex, Cursor, Gemini CLI, OpenCode | 3 | 358 tok |
| Abhigyan-Shekhar/Waggle-mcp pypi.org MCP server for external memory layer for AI agents + more . Download from pypi , and get s | 44 | Codex, OpenCode | 1 | 242 tok |
| drleadflow/ghl-automation-builder Programmatic GHL workflow builder — reverse-engineered internal API with 95 actions, 93 tr | 44 | Claude Code | 3 | 1,572 tok |
| Wuesteon/lean-memory Embedded, local-first agent memory. No server, no daemon, no mandatory cloud key. | 43 | Claude Code | 1 | 1,646 tok |
| alchemiststudiosDOTai/kb-claude Knowledge base Claude application | 43 | Claude Code, Codex, OpenCode | 2 | 1,638 tok |
| FerroxLabs/wayland-core getwayland.com Multi-provider AI agent CLI written in Rust | 43 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 4 | 9,106 tok |
| sepehrbayat/SEPCC SEPCC — A Claude Code proxy with context that survives. Route Claude Code through 17+ prov | 43 | Claude Code, Codex, OpenCode | 17 | 994 tok |
| inite-ai/inite-brain-service brain.inite.ai Open-source bitemporal knowledge graph — long-term memory for AI agents. Hybrid retrieval, | 43 | Claude Code, Codex, OpenCode | 4 | 5,850 tok |
| putervision/state-memory-mcp statememorymcp.com Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks | 42 | Claude Code, Codex, GitHub Copilot, Windsurf | 10 | 74,369 tok |
| kellemar/claude-code-specs-generator | 42 | Claude Code | 4 | — |
| st1page/agent-knowledge-framework Agent team knowledge framework with layered structure for principles, skills, insights, an | 42 | Codex, OpenCode | 1 | 1,462 tok |
| AvengerMoJo/MoJoAssistant A Local-First Cognitive Firewall for Human Agency and AI Safety | 42 | Codex, OpenCode | 1 | 634 tok |
| rmartynenko/workflow-dev-1c-claude-code Unified standards and methodology for developing 1C:Enterprise 8 extensions and configurat | 42 | Claude Code | 10 | 5,516 tok |
| hudrazine/claude-code-memory-bank Memory management optimized for Claude Code, based on the Cline Memory Bank. | 42 | Claude Code | 7 | 1,342 tok |
| krapie/mycelium tiny.kevinprk.com Organize your AI sessions, and carry what they know into the next one. | 42 | Claude Code, Codex, OpenCode | 2 | 4,939 tok |
| OpenCognit/Opencognit opencognit.mytherrablockchain.org The open-source AI agent OS. CEO orchestrator, persistent memory, real execution, atomic b | 42 | Claude Code | 1 | 1,642 tok |
| ufna/VaCuus vacuus.ufna.dev Game UI in HTML/CSS for Unreal Engine, rendered off the game thread — RmlUi + QuickJS on a | 42 | Claude Code, Codex, OpenCode | 5 | 6,452 tok |
| ngocquang/source-of-truth Give your coding agent a persistent memory. source-of-truth keeps a living docs/ catalog o | 41 | Gemini CLI | 1 | 12 tok |
| gossipcat-ai/gossipcat-ai Multi-agent code review mesh — orchestrates AI agents from multiple providers to review co | 41 | Claude Code | 3 | 2,923 tok |
| enowdev/enowx-rag RAG Skill and MCP for AI agents for codebase indexing and memory | 41 | Claude Code, Codex, OpenCode | 2 | 2,238 tok |
| MarceloCaporale/codex-agent-mem marcelocaporale.github.io Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, | 41 | Codex, OpenCode | 1 | 1,043 tok |
| kage-core/Kage kage-core.com Persistent, verified memory for coding agents — so they stop re-explaining your codebase a | 41 | Claude Code, Codex, OpenCode | 2 | 2,407 tok |
| bacnh85/pi-extensions Pi coding agent extension packages — tools, skills, and integrations. | 41 | Codex, OpenCode | 1 | 2,109 tok |
| putervision/vision-memory-mcp visionmemorymcp.com Persistent visual cache for LLM-driven software development. Caches screenshots using perc | 40 | Claude Code, Codex, GitHub Copilot, Windsurf | 10 | 45,077 tok |
| booklib-ai/booklib booklib-ai.github.io Detects what your AI doesn't know about your project and fixes it. Post-training gap detec | 40 | Claude Code, Codex, OpenCode | 2 | 613 tok |
| neuron-core/maestro CLI agent built entirely in PHP with Neuron AI framework | 40 | Claude Code, Codex | 3 | — |
| trip2g/trip2g trip2g.com Open-source MCP knowledge mesh - self-host your second brain, expose it to AI agents, fede | 40 | Claude Code, Codex, OpenCode | 2 | 3,669 tok |
| mistval/yozakura mistval.github.io An LLM-powered social simulation and roleplaying engine where NPCs have their own lives to | 40 | GitHub Copilot | 1 | 409 tok |
| bsmi021/mcp-file-context-server A Model Context Protocol (MCP) server that provides file system context to Large Language | 39 | Claude Code | 3 | 835 tok |
| dilberryhoundog/dev-workspace Dev workspace is an advanced context management system for Claude Code. | 39 | Claude Code | 1 | — |
| EngramMemory/engram-memory engrammemory.ai The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. | 39 | Claude Code | 1 | — |
| zero8dotdev/smriti Shared memory for AI-powered engineering teams. Captures, indexes, and recalls conversatio | 39 | Claude Code, Codex | 2 | 2,832 tok |
| Foxfire1st/agents-remember foxfire1st.github.io A branch-aware, dual-revision epistemic ledger and control plane for AI coding agents. Fro | 39 | Claude Code, Codex, OpenCode | 17 | 2,531 tok |