Best claude-code 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.

Open Knowledge Format for coding agents. Author, validate, lint, search, and visualize portable Markdown knowledge bundles. One gem carries the agent skill, the CLI and Ruby library, and an interactive graph. Docker and Claude Code plugin included, 100% local.

OKF-powered knowledge context for Claude Code — injects your project's knowledge base at every session

Agent-first local harness for OKF-compatible LLM Wikis.

Janet builds and maintains a portable LLM wiki in plain Markdown using the Open Knowledge Format (OKF). Run her directly, call her as a subagent, or add her skills to your coding agent.

Structured, spec-driven development workflow for AI coding agents.

Your personal universal memory for every AI agent. Switch engines. Same mind. Git-native, zero-infra, plain markdown + MCP.

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

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.

Living Docs — a AI agent skill that runs your project's documentation as a living system: constitution, ADRs, BDRs, PRDs, issues, research notes & Mermaid architecture diagrams under five no-drift governance invariants. OKF-formatted, stack-agnostic. Works with Claude Code, Cursor, Copilot, OpenCode & Pi.

Local-first MCP memory server for AI agents, with source citations and OKF/Markdown knowledge bases.

Agent Wiki is a lightweight OKF-compatible knowledge layer for AI agents, turning documents, code, and project context into portable, retrievable memory.

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

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

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.

Context Layering & Engineering for Agentic Resources — Persistent memory, intelligent context, and structured project management for Claude Code

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

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

Agent Skill teaching Claude Code and Codex to author, validate, and consume Open Knowledge Format (OKF) v0.1 bundles

OKF conformant agent schemas for LLM-maintained wikis

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.

Portable context-economy kit for coding agents: a graph-derived PROJECT_MAP, an output wrapper, and curated knowledge (OKF) — so the agent stops reading source files to find things.

Portable, OKF-compatible company knowledge base in Markdown. Compiles to a hierarchical, scale-ready index for LLMs + an offline HTML viewer for humans — with facets, search-by-meaning, and built-in agent procedures (onboarding, dedup, capture). Works with Claude Code, Codex, Antigravity — or no agent.

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

Agent skill: structured, resumable domain-elicitation interviews that emit an OKF knowledge bundle (glossary, tri-temporal events, rules, context map)

LLM Knowledge Base — a Claude Code + Obsidian starter kit

Persistent memory for Claude Code — your sessions distilled into a Google OKF knowledge bundle (plain markdown you own, not a database you're locked into) and injected back at the start of every session.

Local-first developer workbench for Open Knowledge Format bundles

OMI/Obsidian memory tooling (Open Knowledge Format) for AI agents: reproduce the integration on any machine, plus a local web app to view, edit, and add memory entries.

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

Claude Code marketplace for the nine Spillwave second-brain ContentPack plugins. Shared OKF knowledge tree for Grok Bot job functions.

The Filesystem Agent Workspace template family: a folder-based agent workspace, a shared context store, and a capability registry. Plain Markdown + git, agent-agnostic, no lock-in.

A lightweight way for coding agents to accumulate and reference curated Markdown knowledge — no vector DB, no pre-indexing, no custom code.

A local-first, model-agnostic system that compiles sources into durable Markdown for Claude and Codex.

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

AnyPlugin — every agent has plugin dev. AnyPlugin makes it agent-agnostic. One plugin source → native installs for Claude Code, OpenCode, Codex CLI, and Google Antigravity, with an OKF v0.2 knowledge layer. By Rahul Paul / Lab LaunchPad.

Portable scaffold for spinning up focused workspaces (batcaves) in any agentic coding tool — Claude Code, Amplifier, Cursor, Codex CLI, Amp, Cline, RooCode, Aider, Gemini CLI, Windsurf. One persona + one OKF knowledge bundle, freshness-aware.

A Claude Code plugin for reading, writing, validating, and maintaining Open Knowledge Format (OKF)

Open Knowledge Format (OKF) plugin for Claude Code — a skill, auditor agent, and session hook that keep every project's knowledge catalog current.

Data Engineering Knowledge Capture (DEKC) — OKF second brain for data platforms: standard schemas, lineage, streams/jobs, medallion, semantic layer, glossary. Extends PKC + OKF. Claude / Grok / Codex / OpenCode plugin.

A portable Claude Code skill that turns Claude into the librarian of an OKF-style markdown knowledge base (compile / synthesize / audit).

A portable method for AI-maintained knowledge bases — a compounding markdown wiki (Karpathy's LLM-Wiki + Google's OKF + Anthropic's Dreaming). Spanish original included.

Shareable LLM Wiki skill kit for Obsidian-compatible agent knowledge bases

memvault — local knowledge engine for AI agents: capture Codex/Claude/Gemini sessions, hybrid semantic+keyword retrieval, one MCP server for every harness, interactive graph, OKF export.

Vendor-neutral Go CLI for the Open Knowledge Format. Create, validate, lint, index, search, and graph OKF bundles. Built to be driven by AI agents.

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.

Starter template for agent-driven projects: an OKF knowledge bundle, a decision register (ADRs), planning docs, and the agent working-hygiene rules that keep them from drifting.

Claude Code plugin: author, explore, validate, and visualize Google's Open Knowledge Format (OKF) v0.1 bundles.

Open-source client tooling for okfshare: shared, versioned knowledge for AI coding agents. CLI + MCP server + agent skill installer.

AGER → Orca ADE translator: named worktree agents, parallel fan-out, remote-control rename. Compiles OKF Agent Graphs into executable Orca orchestration.

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

Python CLI template with uv setup, strict typing, 90% coverage, offline-safe provider stubs, and optional claude-okf-repo-kit layering.

Layer 1 projector: RKC OKF → Agent Brain (Chroma + BM25 + Kuzu). Owns no nouns.

Research Knowledge Capture (RKC): ingest deep-research dumps into an OKF ContentPack. Layer 0 of the research second brain.

Public starter second brain: agent identities, packing prompts, articles workflow, fictional Northstar graph. No real client names.

Second brain for system architecture information — reverse-engineer monorepos/multi-repos into standard OKF schemas (PKC + SAC). Plugins for Claude Code, Grok, Codex, OpenCode.