Best llm OKF Bundles for AI Agents

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

Persistent memory plugin for OpenCode. Obsidian-style knowledge base that survives across sessions

AI chat, workflow automation, semantic search (RAG), LLM Wiki (OKF) powered by Google Gemini. Works on both desktop and mobile.

Portable, always-fresh docs for agents and humans. A Surface hub is a conformant OKF concept; Surface adds the freshness OKF leaves out - it fails the build when the code a doc describes changes. Deterministic, no LLM.

Open standard for portable AI knowledge interchange — JSON-LD + Markdown dual format with W3C PROV provenance, bi-temporal tracking, entity relationships, and OKF support.

🧠 Knowledge-Driven Development (KDD): ready-to-use template combining OKF (knowledge as linked markdown nodes) + CCDD (deterministic contracts for ephemeral AI agents). Clone it, write a contract, and the built-in validator + CI are already working for you.

MCP server + CLI that turns the task manager you already use into persistent agent memory for Claude Code and any MCP client. Hybrid retrieval (RRF), no vector database. Adapters: TickTick, Obsidian, Notion, GitHub, Airtable, Google, OKF, Taskmaster, Beads.

Memory for your coding agent — markdown project graph template: product, plans, features, bugs, specs, architecture, releases

A Go-native framework for LLM agents, with OpenTelemetry observability built in.

Transform institutional knowledge into Open Knowledge Format (OKF). OKF Studio ingests enterprise knowledge from multiple sources, structures it into portable OKF bundles, builds linked knowledge graphs, and makes knowledge reusable across LLMs, agents, and applications.

Knowledge graph on a canvas. Notes are Markdown files in Open Knowledge Format, with Typst math, PDF-to-graph import with citation verification, and storylines that read and export as documents. Local-first, no account.

Fast, deterministic CLI to search and navigate Open Knowledge Format (OKF), or Obsidian style doc bundles — for humans and AI agents. Find by frontmatter, traverse the link graph, surface orphans/deadlinks.

Long-term memory for CLI agents — cross-CLI, cross-project, cross-session. OKF Wiki + MCP server, model-agnostic.

An open, interactive knowledge graph of modern AI — 123 concepts from tokens & attention to LoRA, DPO, reasoning models, and agents, with typed connections. Fully offline, zero dependencies. Built on the Open Knowledge Format.

LangGraph and LangChain retriever, tools, and navigator subgraph for OKF (Open Knowledge Format) bundles.

SKILL.md to create and maintain OKF about your repo

Ready-to-fork starter for an AI-maintained knowledge base on the Open Knowledge Format (OKF) v0.1 — Markdown + YAML frontmatter, with a Claude Code skill, conformance validator, and EN/TH docs.

Self-hosted LLM wiki turning project context into OKF memory

Marketing memory for your AI agent — markdown campaign graph template: positioning, launch venues, CRM, posts, mentions, experiments

InfraWiki writes and maintains your infrastructure documentation for agents in Open Knowledge Format (OKF)

Store, query, and generate knowledge in the Open Knowledge Format (OKF) - markdown bundles with YAML frontmatter, trust signals, CLI, and LLM ingestion.

OpenCode plugin: progressive disclosure + auto-unload for OKF (Open Knowledge Format) knowledge bundles. Inspired by DCP.

OKF conformant agent schemas for LLM-maintained wikis

Builds a portable OKF knowledge base from code and git history, with checkable evidence, preserved human input, and agent workflows that keep it current as code evolves

LLM-maintained, fully-cited personal wiki in Open Knowledge Format — with an MCP server so an AI can search and read it.

KAUT — Knowledge Actualization Under Trust: self-maintaining, AI-first project knowledge for AI agents. Source-bound docs, git-computed freshness verdicts, a gated write path, zero dependencies, MCP server included.

Turn hard-won human experience into knowledge your AI agents can act on — a methodology (routing + Book-to-Skill + governance) above OKF. A production field report.

Bi-directional Graphify ↔ Google OKF v0.1 integration toolkit. Export knowledge graphs to LLM-optimized Markdown catalogs via progressive disclosure. Bilingual EN/BG.

An advanced AI knowledge retrieval architecture comparison (Hybrid RAG vs Graph RAG vs OKF-Wiki), benchmarked on the Taiwan Building Regulations dataset.

An OKF-native memory layer for code repos — so the why behind your project survives across AI coding sessions. Exports to Google's Open Knowledge Format.

A VS Code and Cursor extension for exploring Open Knowledge Format (OKF) v0.2 and Karpathy-style LLM wikis—view Markdown, YAML metadata, PDFs, links, outlines, and knowledge graphs, then hand grounded context to AI agents.

Git-backed markdown wiki for humans and AI agents, web UI and MCP endpoint from one binary

A bilingual academic wiki with searchable knowledge, citation-grounded LLM answers, and agent-readable OKF exports.

AI-optimized personal knowledge base starter kit. OKF v0.2 compatible with concept graph, dual-dimension index, and lint tool. / 面向 AI 检索的个人知识库启动套件，兼容 OKF v0.2，含概念关联网络、双维度索引和体检工具。

Serve + maintain an OKF (Open Knowledge Format) markdown knowledge bundle: read API + ai-wiki CLI + headless-agent curation. Apache-2.0.

Personal context storage in OKF format

Reconfigurable LLM surface that reshapes per task

Cross-agent Claude Code / Codex skill to author, convert, and validate Markdown in Open Knowledge Format (OKF).

Turn any website into a portable, agent-ready Open Knowledge Format (OKF) bundle — no LLM required. Crawl, sync, chat offline, and serve docs to coding agents over MCP.

Why an OKF knowledge base needs a metabolism, not just a body — the automation layer Google's spec leaves out. By Team Dub Labs.

LLM Knowledge Base — a Claude Code + Obsidian starter kit

Use IA grátis de forma avançada com governança profissional

The OpenDPP Integration API as a machine-readable OKF (Open Knowledge Format) bundle — agent-ingestible, cross-linked Markdown for every endpoint, schema and webhook, regenerated from the live OpenAPI spec.

Harness-owned reader/author for Pi-agent OKF (Open Knowledge Format) knowledge bundles

Portable, model-agnostic workspace template for AI agents: file-based knowledge, skills, contracts, deterministic validation, and no external runtime dependencies.

LLM-maintained knowledge base (OKF + Karpathy LLM-wiki pattern) for STRT's daily That's a First Digest n8n workflow.

Convert Obsidian vaults to Open Knowledge Format (OKF) bundles, then validate and repair any OKF bundle. Python CLI, GitHub Action and pre-commit hook.

Scrape a whole website and distill it into an OKF (Open Knowledge Format) bundle

OKF (Open Knowledge Format) bundle of ScalarDB / ScalarDL documentation, per product and per version, for AI-assisted design, implementation and operations

OKT — open knowledge tools; OKTS — tool search and discovery for any agent.

Comparing Google's Open Knowledge Format (OKF) against Traditional RAG on the same document. FastAPI backend, Streamlit UI, FAISS vector search vs linked markdown traversal, powered by Groq Llama 3.3. No embeddings needed for OKF, no vector database required.

LLM context handler over an Open Knowledge Format bundle BM25 search via MCP, usage telemetry, and a health dashboard. No embeddings, no API key.

Let AI agents navigate Open Knowledge Format (OKF) bundles — tools for LangChain/LangGraph, CrewAI, Google ADK, OpenAI Agents, PydanticAI, LlamaIndex, smolagents, Microsoft Agent Framework and MCP.

Partition-Prompt-Aggregate context engineering for LLMs (ACE, OKF, PPA) — Apache-2.0

Domain-Centric Architecture as a typed, cross-linked knowledge graph in the Open Knowledge Format: the implementation guide anchored to marker contracts and ArchUnit rules, plus recipes, decisions, pitfalls and templates for building DCA code.

Local-first OKF Markdown second brain with SQLite FTS5, graph retrieval, usage-aware archival, backups, and MCP

A read-only server, web UI, and semantic search for Open Knowledge Format (OKF) bundles — directories of Markdown files with YAML front matter.

Vectorless first-order log-n retrieval for OKF wiki trees — reason through the hierarchy, skip the vector DB

Context engineering for LLM apps: put the right pages in the window, and prove the answer.

Nepal-focused AI document understanding and grounded knowledge platform using Open Knowledge Format (OKF v0.2), offline embeddings, and Devanagari OCR.

Autonomous QA Intelligence Platform — agent-native test automation for software teams.

PromptPeter keeps the thread — a local-first AI chat journal. No server, no cloud, no account. Just your prompts, kept.

A timeline where domain-specialised AIs each keep their own memory and speak only when it is their business.

LLM-powered OKF bundle creation from documentation sources

Compiles a source corpus into an interlinked, OKF-conformant markdown wiki.

Governance for AI-written project docs — verify, catch drift, keep them code-grounded, enforce in CI. Zero-dependency, OKF-compatible.

Official MvgeOS catalog of Runes (extensions) and Mvges (agents): the OpenRouter Realm plus MCP, Agent Skills, Agent Plugins, OpenTelemetry, OKF, and ADR bridges. Every artifact is installable by name and documented at https://iamno1special.github.io/mvgeos-marketplace/

Convert Markdown files and web pages into a conformant Open Knowledge Format (OKF v0.1) bundle. Deterministic Python + optional LLM enrichment. Claude Code skill + standalone CLI.

OKF（Open Knowledge Format）v0.2 準拠の知識バンドルを Quarto で作るテンプレート。.qmd を書くだけで人間用 HTML と機械用 OKF バンドルを並行生成し、検証・デプロイまで自動化。エージェントにも人間にも読める知識基盤を育てる。

Hands-on demo of two agent-friendly knowledge formats: Andrej Karpathy's llm-wiki pattern and Google's Open Knowledge Format (OKF) — the same Claude knowledge base organized both ways.

Convert messy documents into Google OKF v0.2 knowledge bundles for AI agents

okft — lint and MCP-serve Open Knowledge Format (OKF) bundles. Spec validator + agent server for Google's OKF v0.1.

OKF — Production-hardened persistent memory and System 2 dialectic reasoning for AI coding agents. Eliminates context amnesia with Shannon-entropy security.

Long-term memory extension for pi — distills sessions into human-readable OKF v0.1 Markdown and recalls them across sessions. Weighted learning, zero dependencies, no build step.

A folder you can drop anything into, that an AI keeps organized as a wiki — portable plain files, OKF-compatible.

Local-first RAG memory for LLMs: Node server with ONNX embeddings, OKF-structured chunks, portable vector bundles, and REST + Web UI + CLI + MCP interfaces

SSSS — a database-free, Markdown-first schema and mutation contract for AI-agent state. Turn a running business into a single tradeable .ucw file.

An AI-powered Fact Knowledge Layer that extracts grounded facts from PDFs, validates them, and intelligently identifies corroborations, contradictions, and contextual discrepancies across documents with source-level evidence.

UIG Studios AI — local-first desktop AI agent you can check up on: undo for shell commands, code-stamped evidence tiers, verified examples, OKF memory, safety gates that don't depend on the model. Tauri 2 + React + Rust + Ollama; cloud/custom endpoints optional. macOS, signed + notarized.

Local-first YouTube-to-knowledge CLI: timestamped captions + video frames → agent JSON and Google OKF via any OpenAI-compatible VLM.

LLM wiki as Agent Skills — generate wiki pages from your docs and URLs, publish with Git, review one page at a time.

Starter kit for a Zettelkern vault: an LLM-maintained markdown wiki with typed pages, provenance rules, an append-only log, and a stdlib-only lint script. Karpathy's LLM-wiki pattern, OKF-compatible, works with any agent harness.