Lore

A unified harness abstraction over agentic vendor tooling.

Lore manages rules, skills, and agents, then projects them into every platform's native format. Write once, works everywhere. A single Go binary with zero runtime dependencies.

Quick Start

# Install the binary
go install github.com/lorehq/lore@latest

# Initialize a new project
cd my-project
lore init

# Generate platform-native files
lore generate

Set "platforms" in .lore/config.json to control which platforms are active. The projector only generates files for enabled platforms.

What You Get

Sessions accelerate instead of resetting. The harness loads your project identity, rules, active work, available agents, and a map of everything your agent knows at session start. No re-explaining.

One knowledge base, every platform. Capture a fieldnote in Claude Code -- it's available in Cursor, Copilot, and OpenCode. No copying, no drift. See it in action.

Rules are enforced, not just documented. Your coding standards and security policies are injected before every file write via hooks. The agent sees the relevant rules right when it matters.

Snags become fieldnotes that persist. When your agent hits an API quirk or a deployment snag, it captures a fieldnote. That fieldnote loads in every future session. The mistake happens once, the fix persists.

Complex work delegates to focused workers. When work benefits from a fresh context window, the harness spawns workers loaded with curated skills and rules.

How It Works

Lore is a Go binary that centrally manages the three standard components of an agentic system -- rules, skills, and agents -- and projects them into every platform's native format. It also exposes a unified hook lifecycle interface across platforms.

Global Directory (~/.lore/)

~/.lore/
├── AGENTIC/             # Rules, skills, agents
│   ├── .harness/        # System content (binary-managed)
│   ├── SKILLS/          # Operator-managed skills
│   ├── RULES/           # Operator-managed rules
│   └── AGENTS/          # Operator-managed agents
├── BEHAVIOR/            # OS behavioral layer
│   └── LORE_OS/         # Hook scripts (optional install)
└── MEMORY/
    ├── DATABANK/         # Persistent knowledge store
    │   ├── KNOWLEDGE_BASE/   # Fieldnotes, runbooks, profiles
    │   ├── workspace/        # Active work (drafts, projects, work items)
    │   └── imports/          # Staging inbox
    └── HOT/              # Hot memory persistence (Docker mount)

AGENTIC -- Composition layer. Operator-managed content alongside system content (prefixed lore-*) that the binary manages. Projected into platform-native files by lore generate.

BEHAVIOR -- Runtime behavioral layer. Contains hook scripts that platforms invoke for lifecycle events (pre-tool-use, post-tool-use, prompt-submit). Lore OS ships as the default behavioral configuration.

MEMORY -- Structured knowledge. The Databank holds persistent knowledge (fieldnotes, runbooks, operator profile) and active work. The Hot Cache provides Redis-backed session memory via the optional Docker memory engine.

Project Instances

my-project/
├── .lore/
│   ├── config.json       # Project config
│   ├── AGENTIC/          # Project-specific rules, skills, agents
│   ├── MEMORY.md         # Failsafe scratchpad (gitignored, OS-created)
│   └── LORE.md           # Project instructions
├── CLAUDE.md             # Generated platform projection
└── src/

When lore generate runs, three layers merge: harness system content, global operator content, and project-local overrides. The result is emitted as platform-native files.

Commands

Slash commands (in-session)

Command	What it does
/lore	Show available subcommands
/lore status	Show instance health -- version, hooks, skills, fieldnotes, active work
/lore memory	Start/stop the local Docker memory engine
/lore memory burn	Promote hot cache facts to the persistent DATABANK

CLI commands (terminal)

Command	What it does
lore	Launch the TUI dashboard
lore init	Scaffold a new Lore project
lore generate	Run composition and projection
lore memory start|stop|status	Docker memory engine lifecycle
lore hook <event>	Hook handler (called by platforms, not users)

Platforms

Platform	Target files
Claude Code	CLAUDE.md, .claude/
GitHub Copilot	.github/copilot-instructions.md, .github/hooks/, AGENTS.md
Cursor	.cursor/rules/*.mdc, .cursor/hooks.json, AGENTS.md
Gemini CLI	GEMINI.md, .gemini/
Windsurf	.windsurfrules, .windsurf/
OpenCode	AGENTS.md, .opencode/

All platforms share the same knowledge base. Rules, skills, agents, and fieldnotes written once are projected into platform-specific formats automatically.

Documentation

Full docs: lorehq.github.io/lore-docs

Contributing

See CONTRIBUTING.md for development setup and guidelines.

Security issues: see SECURITY.md.

License

Apache-2.0