{"slug": "mak4i-an-open-protocol-for-reusable-ai-artifacts-across-ai-systems", "title": "MAK4I – An open protocol for reusable AI artifacts across AI systems", "summary": "Talvik, Inc. has released MAK4I, an open protocol for packaging, identifying, versioning, sharing, injecting, and reusing AI artifacts across models, platforms, and organizations, currently in Phase 0 with only the protocol design and specification draft available. The protocol aims to standardize how reusable AI artifacts move between tools, similar to how Git standardized source control and npm standardized package distribution, with a commercial ecosystem planned on top, including a hosted registry, enterprise offering, and SDKs for Python, Node.js, Go, and Rust.", "body_md": "The protocol for not rebuilding what your AI already built.\n\n**Built by Talvik, Inc.**\n\n**Status: Phase 0 — Foundation.** This repo currently contains the protocol\ndesign, specification draft, and documentation. The reference API\nimplementation (backend, CLI, SDK) has not been built yet — that's Phase 2.\nSee [ROADMAP.md](/talvikai/mak4i-protocol/blob/main/ROADMAP.md) for what exists today versus what's planned.\n\nMAK4I is an open protocol for packaging, identifying, versioning, sharing, injecting, and reusing AI artifacts across models, platforms, and organizations.\n\nA MAK4I artifact can represent:\n\n- Project context\n- Procedural knowledge (how to do something, consistently)\n- Prompts\n- Workflows\n- Architecture and API contracts\n- Historical decisions and rationale\n- Reusable outputs (documents, code, templates)\n\n**Memory is one artifact type — not the entire protocol.** Just as Git\nstandardized source control and npm standardized package distribution,\nMAK4I standardizes how reusable AI artifacts move between tools instead of\nbeing rebuilt from scratch in each one.\n\n```\nClaude Code, Cursor, ChatGPT, Gemini, Bedrock, Copilot, internal agents\n                              │\n                        MCP / SDK / API\n                              │\n                            MAK4I\n                              │\n              Registry · Artifacts · Knowledge · Context\n```\n\nSee [ARCHITECTURE.md](/talvikai/mak4i-protocol/blob/main/ARCHITECTURE.md) for the full\narchitecture, including what's actually implemented today versus planned.\n\nMAK4I is the protocol. Talvik builds the platform.\n\n```\nMAK4I Protocol (open, MIT licensed)\n    ↓\nTalvik Registry (hosted)\nTalvik Enterprise (commercial)\nTalvik SDK (Python, Node.js, Go, Rust)\nTalvik CLI (mak4i install, inject, publish)\n```\n\n**Open protocol forever. Commercial ecosystem on top.**\n\nFollowing the open protocol + commercial ecosystem approach used by projects such as Git, Kubernetes, and OpenTelemetry.\n\nThe AI memory space is crowded — [Mem0](https://mem0.ai), [Google's Open Knowledge Format](https://github.com/google/okf), [Open Memory Protocol](https://github.com/SMJAI/open-memory-protocol), and every major platform's native memory all solve some version of \"the AI doesn't remember.\" MAK4I was designed after evaluating the existing landscape of AI memory, knowledge, and interoperability projects. See [COMPETITIVE_LANDSCAPE.md](/talvikai/mak4i-protocol/blob/main/COMPETITIVE_LANDSCAPE.md) for the full comparison.\n\nMAK4I isn't trying to out-remember them. It solves a narrower, different problem:\n\n| If your problem is... | Look at |\n|---|---|\n| \"The AI doesn't remember my preferences\" | Mem0, native platform memory |\n| \"Our knowledge should live in files, not a vendor's database\" | Google's OKF |\n| \"I want lifecycle and staleness tracked, but nothing stops duplicate work\" | OKF v0.2, ByteRover |\n| \"We keep paying to regenerate things we already built, and nothing actually stops that from happening again\" | MAK4I |\n\nMAK4I is a **reuse discipline**, enforced as a protocol behavior: check the registry before generating anything, reuse or adapt what exists, and only create new when nothing matches. That check is a protocol guarantee, not an optional convention a client can skip — the distinction that matters, since tracking that an artifact *could* be reused is different from a runtime that *requires* checking first. Every reuse decision is logged with a real token-savings estimate — not a benchmark claim, a running ledger designed to track actual reuse over time (currently reflecting development-time observations — see [Proof of Concept](#proof-of-concept) below).\n\nEvery AI tool represents reusable knowledge differently — Claude has Projects, Artifacts, and Skills; Cursor has Rules; ChatGPT has Memory; GitHub Copilot has Instructions. None of those representations travel between tools. Switch tools and you start from zero.\n\nYou re-explain your stack, regenerate code that already exists, re-establish context that was already shared.\n\nThat's waste — computational, financial, and environmental.\n\nAt 1 million AI sessions per day each wasting 1,000 tokens —\nthat is **1 billion tokens per day** in avoidable generation.\n\nAs AI moves toward metered compute billing, that waste becomes a direct dollar cost for every business running AI at scale.\n\n**MAK4I fixes this.**\n\n| Type | Answers | Examples |\n|---|---|---|\nProcedural |\nHow? | Code frameworks, deployment pipelines, engineering playbooks |\nSemantic |\nWhat? | System architecture, schemas, API contracts, domain models |\nEpisodic |\nWhy? | Decisions made, rationale, sprint history, team conventions |\n\nTogether they provide complete project continuity across any AI tool.\n\n```\n# Install memory packs\nmak4i install company/backend-standards\nmak4i install schedovia/context\n\n# Inject before any AI session\nmak4i inject\n\n# AI session starts with full context\n# No re-explaining. No regenerating. Continue instantly.\n{\n  \"id\": \"schedovia-stack-context\",\n  \"version\": \"1.0.0\",\n  \"type\": \"context\",\n  \"layer\": \"episodic\",\n  \"name\": \"Schedovia Stack Context\",\n  \"description\": \"Full stack context for Schedovia — eliminates re-explaining architecture each session\",\n  \"token_estimate\": 1500,\n  \"tags\": [\"schedovia\", \"stack\", \"context\"]\n}\n```\n\nMAK4I's core reuse mechanism — checking for and reusing existing artifacts instead of regenerating them — was demonstrated during MAK4I's own development process, before any API existed. Early figures below reflect that development-time observation, not production traffic.\n\n| Metric | Value |\n|---|---|\n| Tokens saved (dev-time observation) | 38,400+ |\n| Sessions tracked | 29 |\n| Artifacts registered | 9 across 6 types |\n\nSee [docs/MAK4I_SAVINGS_LOG.md](/talvikai/mak4i-protocol/blob/main/docs/MAK4I_SAVINGS_LOG.md) for the full,\ndated session-by-session breakdown.\n\n[WD Technology Solutions](https://western-digital.net) is Talvik's design\npartner and the intended first production adopter, once the Phase 2 API is\nlive. See [ROADMAP.md](/talvikai/mak4i-protocol/blob/main/ROADMAP.md) for the integration plan.\n\nMAK4I uses the **MAK-XXXX** convention for protocol standards. See\n[ROADMAP.md](/talvikai/mak4i-protocol/blob/main/ROADMAP.md) for the full phase-by-phase roadmap and\n[VISION.md](/talvikai/mak4i-protocol/blob/main/VISION.md#standards-process) for the standards list —\nthis repo is currently **Phase 0 — Foundation** (Aug 2026).\n\n*Write knowledge once. Inject anywhere. Continue instantly.*\n\n*MAK4I is to AI sessions what npm is to Node.js.*\n\n**Portable AI Memory. Open Forever.**\n\n*© 2026 Talvik, Inc. — MAK4I Protocol is open source, MIT licensed.*", "url": "https://wpnews.pro/news/mak4i-an-open-protocol-for-reusable-ai-artifacts-across-ai-systems", "canonical_source": "https://github.com/talvikai/mak4i-protocol", "published_at": "2026-08-21 13:54:37+00:00", "updated_at": "2026-08-21 14:15:07.824023+00:00", "lang": "en", "topics": ["ai-infrastructure", "developer-tools", "ai-agents"], "entities": ["Talvik, Inc.", "MAK4I", "Mem0", "Google's Open Knowledge Format", "Open Memory Protocol", "Claude Code", "Cursor", "ChatGPT"], "alternates": {"html": "https://wpnews.pro/news/mak4i-an-open-protocol-for-reusable-ai-artifacts-across-ai-systems", "markdown": "https://wpnews.pro/news/mak4i-an-open-protocol-for-reusable-ai-artifacts-across-ai-systems.md", "text": "https://wpnews.pro/news/mak4i-an-open-protocol-for-reusable-ai-artifacts-across-ai-systems.txt", "jsonld": "https://wpnews.pro/news/mak4i-an-open-protocol-for-reusable-ai-artifacts-across-ai-systems.jsonld"}}