2,351 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 agents7,410Claude Code6,578Data and AI3,695Backend and APIs3,487Languages3,404Planning3,188Git and workflow3,106Code review2,712Testing2,325Research2,289DevOps and cloud2,283Writing and docs2,279
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| vstorm-co/memv vstorm-co.github.io Structured, temporal memory for AI agents. | 89 | Claude Code | 6 | 1,576 tok |
| mitchross/talos-argocd-proxmox mitchross.github.io Talos ArgoCD Homelab. My personal production Cluster. | 88 | Claude Code, Codex, OpenCode | 12 | 5,863 tok |
| zby/commonplace The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, | 88 | Claude Code, Codex, OpenCode | 4 | 5,145 tok |
| deivid11/obsidian-claude-code-plugin Interactive Claude Code integration for Obsidian | 87 | Claude Code | 1 | 379 tok |
| nikita-rulenko/Helixir One infinite session for any agents and harness you have. No more degradation and hallucin | 87 | Codex, OpenCode | 1 | 8,101 tok |
| Soul-Brews-Studio/arra-oracle-v3 Oracle v2 - MCP Memory Layer with semantic search, philosophy, and knowledge management | 87 | Claude Code, Codex, OpenCode | 17 | 8,313 tok |
| buildomator/buildomator A structured plan/execute/verify coding workflow for Claude Code: atomic commits, MCP-back | 86 | Claude Code | 1 | 770 tok |
| CloudLLM-ai/mentisdb mentisdb.com Memory that lasts and compounds. MentisDB gives agents durable memory so they do not just | 85 | Codex, OpenCode | 1 | 176 tok |
| rand/mnemosyne rand.github.io Mnemosyne is a agentic memory and orchestration system designed to provide Claude Code wit | 85 | Claude Code | 21 | 8,021 tok |
| hamidi-dev/opentab 📊 Browse your AI coding spend in the terminal — OpenCode, Claude Code, Codex & friends | 85 | Claude Code, Codex, OpenCode | 2 | 887 tok |
| joelhooks/pi-tools 🔧 Power tools for pi — repo autopsy, tsgo LSP, codex background loops, session reader, an | 84 | Claude Code, Codex, OpenCode | 2 | 388 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 |
| sandst1/remind sandst1.github.io A memory layer for AI Agents | 83 | Claude Code, Codex, OpenCode | 6 | 3,153 tok |
| Abinesh-L/claude-crusts Analyze your Claude Code context window, detect wasted tokens, and get pasteable fix comma | 83 | Claude Code | 2 | 7,152 tok |
| plasma-ai/wiki Indexed knowledge bases with command-line tools for agents. | 83 | Claude Code, Codex, OpenCode | 2 | 4,453 tok |
| attunehq/nudge attune.inc Give your agent a nudge. | 82 | Claude Code, Codex, OpenCode | 5 | 5,519 tok |
| adelinamart/robrain robrain.dev Shared memory across your team and your AI agents — with judgment about what's worth keepi | 81 | Codex, OpenCode | 1 | 247 tok |
| simpx/loopat Self-hosted AI workspace built around context management. Works solo, scales to teams. | 81 | Claude Code | 1 | 708 tok |
| tpierrain/kenjaku Kenjaku is a Karpathy-style LLM wiki, reinforced where it counts with battle-tested softwa | 80 | Claude Code | 11 | 5,247 tok |
| putervision/state-memory-mcp statememorymcp.com Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks | 79 | Claude Code, Codex, GitHub Copilot | 5 | 3,642 tok |
| panayiotism/claude-harness | 79 | Claude Code | 2 | 701 tok |
| orual/pattern agent builder | 79 | Claude Code, Codex, OpenCode | 4 | 1,420 tok |
| TSchonleber/brainctl A cognitive memory system for AI agents. Single SQLite file. MCP server included. | 79 | Claude Code | 1 | 6,112 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 | 79 | Claude Code | 9 | 584 tok |
| postmelee/hyper-waterfall A human-governed AI coding workflow that distills ephemeral session context into persisten | 79 | 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 | 79 | Claude Code | 1 | 406 tok |
| major7apps/pensyve pensyve.com Universal memory runtime for AI agents | 79 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 5,627 tok |
| serac-labs/serac serac.build A ServiceNow MCP server, and the skill guides that teach an agent to use it. 400+ snow_* t | 78 | Claude Code, Codex, OpenCode | 1 | 1,554 tok |
| vectorize-io/agent-memory-benchmark Agent Memory Benchmark | 78 | Claude Code | 1 | 80 tok |
| juntoku9/Sessory Shared memory for AI coding sessions. | 78 | Claude Code | 1 | 522 tok |
| tech4idea/viforge ViForge is a local-first AI collaboration workbench for creative and knowledge work. It he | 78 | 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 |
| vakovalskii/ontoship md+git knowledge base: FTS5 search (bm25+trigram/fuzzy), HTML+graph, code-ontology linter, | 77 | Claude Code | 1 | 434 tok |
| TOKTOKHAN-DEV/agent-company agent-company.site Create an automated organization with an AI Company | 77 | Claude Code, Codex, OpenCode | 8 | 5,073 tok |
| tuirk/Kompl A compounding LLM-wiki, best fit as a personal second brain that organizes and updates its | 76 | Codex, OpenCode | 1 | 1,732 tok |
| raia-live/amfs sense-lab.ai Continual Learning for AI agents, helping your agents self-improve with every run | 76 | Claude Code | 1 | 2,185 tok |
| vitaecontext/vitaecontext vitaecontext.github.io Give your AI agents grounded, reusable career context. | 75 | Codex, GitHub Copilot, Gemini CLI, OpenCode | 3 | 1,368 tok |
| baldaworks/callee Markdown-defined provider-backed agents and deterministic workflows for ACP runtimes. | 74 | Codex, OpenCode | 2 | 355 tok |
| ukkit/memcord 🧠 Self-hosted, privacy-first MCP server for long-term AI memory — save, search & summariz | 73 | Claude Code | 20 | — |
| hassancs91/brainoutside brainoutside.com Self-hosted memory server for AI agents. Your brain is a git repo, served over MCP and RES | 73 | Claude Code | 1 | 1,796 tok |
| 9thLevelSoftware/Daem0n-MCP Persistent memory, decision-making, and governance for AI agents | 73 | Claude Code, Codex, OpenCode | 11 | 1,459 tok |
| caura-ai/caura-cross-fleet-gov Multi-agent memory governance demo using MemClaw + OpenClaw. Three agents (Sales, Legal, A | 72 | Claude Code | 1 | 1,402 tok |
| escoffier-labs/brigade brigade.tools Track work, verify results, carry memory, and sync tools across coding agents. Local files | 72 | Codex, OpenCode | 1 | 1,962 tok |
| kruschdev/krusch-context-mcp Unified MCP server merging semantic codebase search, episodic memory, holographic steering | 71 | Codex, OpenCode | 1 | 3,347 tok |
| knowall-ai/mcp-neo4j-agent-memory knowall.ai Memory management MCP server for AI agents using Neo4j knowledge graphs | 69 | Claude Code | 1 | 930 tok |
| banodoco/hivemind Drop-in skill so coding agents (Claude Code / Codex) can search the Banodoco Discord messa | 69 | Codex, OpenCode | 1 | 1,297 tok |
| jaychouya/MemoryAgent An AI Agent with a cognitive memory architecture that remembers your preferences and under | 68 | GitHub Copilot | 1 | 139 tok |
| WhenMoon-afk/claude-memory-mcp Local citation-backed recall for Pi, OMP, Claude Code, Codex, and ChatGPT history. | 68 | Codex, OpenCode | 1 | 2,331 tok |
| liyupi/github-claw ai.codefather.cn Build AI agents with GitHub: long-term memory + AI Agent skill packs (UI/UX, image generat | 67 | Codex, OpenCode | 1 | 1,268 tok |
| kromahlusenii-ops/ham goham.dev (HAM) Memory system for AI coding agents. Cut token usage by 80% by scoping context to dir | 66 | Claude Code | 1 | 332 tok |