Locus

Locus

Hierarchical markdown-based memory system for autonomous AI agents. Each directoryis a room (locus) in the palace, containing specific knowledge navigated on demand.Named for the atomic unit of the Method of Loci.

Core idea: Keep context windows small. Load only the room you need, not the whole palace.

How it works

palace/
  INDEX.md                    ← always read first (~50 lines max)
  global/
    toolchain/
      toolchain.md            ← canonical facts about tools
  projects/
    my-project/
      my-project.md           ← room overview + key files
      technical-gotchas.md    ← specialty: issues & resolutions
      sessions/
        2026-03-02.md         ← append-only session log

An agent reads INDEX.md, navigates to the relevant room, and reads only that room.Session logs accumulate until consolidation merges them into canonical files.

See the wiki for full documentation.

Quick start

# Install
pip install locus-mcp
# or: uvx locus-mcp --palace ~/.locus  (no install needed)

# Create a palace from the example template
cp -r example-palace ~/.locus
# Edit ~/.locus/INDEX.md to describe your palace

# Run the MCP server
locus-mcp --palace ~/.locus
# or: LOCUS_PALACE=~/.locus locus-mcp

Installation

MCP server (recommended for MCP-capable clients)

pip install locus-mcp

Or run without installing using uvx:

uvx locus-mcp --palace ~/.locus

Claude Code skills

cp -r skills/claude/locus ~/.claude/skills/locus
cp -r skills/claude/locus-consolidate ~/.claude/skills/locus-consolidate

Codex

cp -r skills/codex/locus ~/.codex/skills/locus
cp -r skills/codex/locus-consolidate ~/.codex/skills/locus-consolidate

Gemini

Reference skills/gemini/locus/SKILL.md from your .gemini/ directoryor a GitHub Actions workflow (see skills/gemini/).

Agent SDK (Python)

pip install locus-mcp
locus --palace ~/.locus --task "What toolchain conventions are set?"

MCP Server

The locus-mcp command exposes four tools over the Model Context Protocol (stdio transport):

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "locus": {
      "command": "locus-mcp",
      "args": ["--palace", "/path/to/palace"]
    }
  }
}

Or using uvx (no install required):

{
  "mcpServers": {
    "locus": {
      "command": "uvx",
      "args": ["locus-mcp", "--palace", "/path/to/palace"]
    }
  }
}

Cursor / Zed

{
  "mcp": {
    "servers": {
      "locus": {
        "command": "locus-mcp",
        "args": ["--palace", "/path/to/palace"]
      }
    }
  }
}

Environment variable

All clients support LOCUS_PALACE as an alternative to --palace:

export LOCUS_PALACE=~/.locus
locus-mcp

See MCP Server Configurationfor the full client setup guide and spec/mcp-server.md for architecture details.

Benchmarks

Palace navigation loads 52% fewer context lines than flat memory for specific queries,while maintaining full recall. Session-only queries (recent work not yet consolidated)are accessible only via the palace.

Palace: 822 lines / 9 queries found   avg  91 lines/query · 3.2 calls
Flat:  1719 lines / 8 queries found   avg 191 lines/query · 2.0 calls

See docs/benchmarks.md for charts and full methodology.

Structure

example-palace/   Copy-paste palace template to get started
spec/             Palace convention definitions:
  index-format.md       INDEX.md rules and routing
  room-conventions.md   Room structure and naming
  size-limits.md        Context budget thresholds
  write-modes.md        Session logs vs canonical edits
  mcp-server.md         MCP server architecture and safety model
  metrics-schema.md     Run metrics JSON schema
  audit-algorithm.md    Palace health scoring
  health-report-format.md  Audit report structure
  inferred-feedback.md  Disagreement signal classification
templates/        Copy-paste templates for INDEX.md, rooms, session logs
skills/
  claude/         SKILL.md files for Claude Code + Agent SDK
  codex/          Codex-compatible skill files
  gemini/         Gemini CLI + GitHub Actions skill files
docs/
  architecture.md       Mermaid diagrams
  benchmarks.md         Benchmark results and charts
  onboarding.md         Step-by-step agent onboarding
scripts/
  bench-mcp.py          40-case MCP integration benchmark
  bench-compare.py      Palace vs flat recall comparison
  generate-charts.py    Regenerate docs/img/ charts
locus/agent/      Python Agent SDK (CLI + metrics)
locus/audit/      Palace health auditor (locus-audit CLI)
locus/feedback/   Inferred feedback classifier
locus/mcp/        MCP server (locus-mcp CLI)

Roadmap

Contributing

See CONTRIBUTING.md for dev setup, test instructions, and PR guidelines.

License

MIT