Sandbox
@oguzbilgic/agent-kernel

Markdown kernel for agent memory and identity

Agent Kernel is a starter repo that teaches an AI coding agent how to keep state in plain files. The agent reads `AGENTS.md`, writes its identity into `IDENTITY.md`, tracks knowledge in `KNOWLEDGE.md`, and stores day-by-day notes in `notes/`. It is meant to be cloned per agent, so each one gets its own memory and history. The README says it works with OpenCode, Claude Code, Codex, Cursor, and Windsurf.

338 stars40 forksUpdated 5mo ago
Who it's for

Builders who want Claude Code, Codex, Cursor, or other coding agents to keep memory between sessions.

What it delivers

You can resume work without re-explaining the project, the agent’s identity, or the current state.

What it does

Persistent agent memory

Uses `IDENTITY.md`, `KNOWLEDGE.md`, `knowledge/`, and `notes/` to store identity, facts, and session history.

Append-only session notes

Keeps daily logs in `notes/` so past actions and decisions are preserved instead of rewritten.

Per-agent isolation

Lets you clone the same kernel into separate repos for different agents or domains.

Any-agent compatibility

Works with agents that already read project instruction files like `AGENTS.md`, `CLAUDE.md`, or `.cursorrules`.

kern-ai runtime support

Can be initialized and run with `npx kern-ai init my-agent` and `npx kern-ai tui` for daemon and chat channels.

How to get it

  1. 1With any coding agent
    git clone https://github.com/oguzbilgic/agent-kernel.git my-agent
    cd my-agent
    opencode     # or claude, codex, cursor, etc.
  2. 2With kern-ai (daemon + Telegram + Slack)
    npx kern-ai init my-agent
    npx kern-ai tui

README

Agent Kernel

The easiest way to create an AI agent. Clone, start, talk.

Your agent remembers between sessions, takes notes, and builds on past work. No framework, no database — just three markdown files and a git repo.

Works with any AI coding agent: OpenCode, Claude Code, Codex, Cursor, Windsurf, etc.

🚀 kern-ai — a runtime built for agent-kernel. Daemon mode, Telegram, Slack, and one brain across every channel. npx kern-ai init my-agent

Quick start

With any coding agent:

git clone https://github.com/oguzbilgic/agent-kernel.git my-agent
cd my-agent
opencode     # or claude, codex, cursor, etc.

With kern-ai (daemon + Telegram + Slack):

npx kern-ai init my-agent
npx kern-ai tui

That's it. The agent reads the kernel, realizes it's new, asks who you want it to be. You tell it. It remembers.

Memory structure

AGENTS.md          ← kernel (generic, don't edit)
IDENTITY.md        ← who this agent is (agent maintains)
KNOWLEDGE.md       ← index of knowledge files (agent maintains)
knowledge/         ← facts about the world (mutable)
notes/             ← daily session logs (append-only)

Two kinds of memory:

  • knowledge/ — State. Facts about how things are right now. The agent updates these when reality changes.
  • notes/ — Narrative. What happened each session — decisions, actions, open items. Append-only. Never modified after the day ends.

Why this works

AI agents already read AGENTS.md (or CLAUDE.md, .cursorrules, etc.) as project instructions. This kernel uses that mechanism to teach the agent how to remember.

The agent doesn't need a database, a vector store, or a custom framework. It just needs:

  • A file that says "you are stateful, here's how"
  • A git repo to store memory in
  • Plain markdown files

Multiple agents

Each agent is its own repo. To create another:

git clone https://github.com/oguzbilgic/agent-kernel.git another-agent
cd another-agent
opencode     # or claude, codex, etc.

Same kernel, different identity, different knowledge. You can have a homelab agent, an investing agent, a health agent — all running the same OS.

License

MIT

Files in the repo

Repository payload4 top-level entries
  • AGENTS.md
  • IDENTITY.md
  • KNOWLEDGE.md
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More templates

CopilotKit/
OpenBot

Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.

4.6k
Donchitos/
Claude-Code-Game-Studios

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

25k

A self-organizing Obsidian vault that gives AI coding agents persistent memory. Claude Code, Codex CLI, Gemini CLI.

4.6k
idavidov13/
agentic-playwright

Production-grade Playwright + TypeScript Scaffold for Agentic Testing. Harness for all major AI coding agents baked in.

163
gavishap/
omnia-vault

Omnia Vault - the all-in-one project brain: an Obsidian LLM wiki, Graphify code graphs, a living plan that triages new videos against itself, and a Claude Code ⇄ Codex relay. Everything your project knows, in one clonable vault.

60

🎬 Tạo video "so sánh kiến thức" ngắn tự động — HyperFrames + AI voice, 1 template nhiều chủ đề.

169