solo-mise 0.2.0

Mise en place for agent memory. Installable starter kit for a harness-agnostic agent workspace.

Solomon's Mise en Place

Mise en place for agent memory.

Public-safe workspace bootstrap, memory handoffs, and publish guards for real agent setups.

solo-mise is the installable starter kit behind Solomon's Guide to Cookin' with Gas. It gives you the workspace skeleton, handoff inbox, conservative ingester, and publish guard that make a multi-agent setup usable without leaking private junk into public repos.

What this is

Mise en place means "everything in its place before the work starts." In a kitchen, that is chopped mirepoix, clean pans, labels, and a station that does not make you hunt for salt & butter mid-service. For agents, it is the same idea: rules, memory, tools, handoff inboxes, publish guards, and boring verification already laid out before the session gets expensive.

This package lays down a clean starting point for an agent workspace or a repo that needs durable memory handoffs. It is meant for people running real tools, real docs, and real automation across OpenClaw, Claude Code, Codex, Hermes, or a similar harness.

The cookbook explains the why. This package gives you the kitchen.

What you get

• sanitized bootstrap files for agent behavior, safety, tools, identity, and memory
• a canonical memory layout where one configured owner holds durable knowledge
• a shared .claude/memory-handoffs/ inbox for Claude Code, Codex, and other side harnesses
• starter memory cards and routing rules
• multi-workspace handoff patterns for people administering more than one agent setup
• memory-care staleness checks so durable cards do not quietly rot
• TokenJuice output-compaction guidance for Claude Code and Codex, including wrapper notes and savings expectations
• content-guard publish gates so private infrastructure does not leak into public docs
• adapter fragments for OpenClaw (tested), Hermes (stubbed), and generic harnesses
• doctor checks that prove the system is wired before you trust it

What you do not get

• private hostnames, IPs, account IDs, or personal details
• live auth profiles or OAuth tokens
• cron jobs that post publicly by default
• destructive automation or write-enabled integrations without explicit opt-in

Install

pipx install solo-mise

Or, to track main:

pipx install git+https://github.com/solomonneas/solo-mise

Quick path

solo-mise init --target .                     # repo-local handoff flow + publish guard
solo-mise init --target ~/agent-kitchen --profile workspace
solo-mise doctor --target ~/agent-kitchen
solo-mise scrub --target .

Re-running solo-mise init against an existing target is safe. It refuses to overwrite tracked files without --force, and the .gitignore block it manages is replaced between its markers without touching the rest of your file.

See QUICKSTART.md for setup, verification, and the ingest flow.

What a green doctor looks like

solo-mise doctor: target /home/you/agent-kitchen (generic)
  [ok]   bootstrap: AGENTS.md              /home/you/agent-kitchen/AGENTS.md
  [ok]   bootstrap: CLAUDE.md              /home/you/agent-kitchen/CLAUDE.md
  [ok]   bootstrap: MEMORY.md              /home/you/agent-kitchen/MEMORY.md
  [ok]   bootstrap: TOOLS.md               /home/you/agent-kitchen/TOOLS.md
  [ok]   bootstrap: USER.md                /home/you/agent-kitchen/USER.md
  [ok]   bootstrap: SAFETY_RULES.md        /home/you/agent-kitchen/SAFETY_RULES.md
  [ok]   bootstrap: INSTALL_FOR_AGENTS.md  /home/you/agent-kitchen/INSTALL_FOR_AGENTS.md
  [ok]   handoff: inbox                    /home/you/agent-kitchen/.claude/memory-handoffs
  [ok]   handoff: TEMPLATE.md              /home/you/agent-kitchen/.claude/memory-handoffs/TEMPLATE.md
  [ok]   handoff: processed/               /home/you/agent-kitchen/.claude/memory-handoffs/processed
  [ok]   memory: cards/                    /home/you/agent-kitchen/memory/cards
  [ok]   publish: hooks/pre-push           /home/you/agent-kitchen/hooks/pre-push
  [ok]   publish: content-guard            /home/you/repos/content-guard

summary: 14 checks, 0 failed, 0 manual

Anything [warn] is fine; [fail] means the install is incomplete. The openclaw and hermes harnesses add their own checks on top.

Privacy

solo-mise makes no network calls. It does not phone home, collect telemetry, or sync anything to a server. Everything happens on your local filesystem against the templates packaged with the install. The only file that touches the network is the pre-push hook, and it runs the local content-guard scanner against your own commits before they leave the machine.

Profiles

Profile	What it installs	When to use
repo (default)	AGENTS.md, CLAUDE.md, .claude/memory-handoffs/, pre-push hook	A project wants the handoff flow and a public-leak guard.
workspace	Full bootstrap file set, memory folders, starter cards, safety files	A user wants a home agent workspace.
openclaw	workspace plus OpenClaw config fragments and doctor checks	An OpenClaw user.
hermes	workspace plus Hermes adapter fragments and doctor checks	A Hermes user. Experimental.
generic	Contract docs and templates, no orchestrator config	A user wants the layout without picking a harness yet.
publisher	content-guard policies, scrub commands, publish gates	A user who publishes blog posts, docs, or social drafts.

The design

One memory owner stays canonical. Side harnesses keep local context, but durable findings move through a shared handoff inbox and into the right destination.

Claude Code / Codex / other harness
        |
        v
<repo>/.claude/memory-handoffs/*.md
        |
        v
solo-mise ingest (or your harness's equivalent)
        |
        v
memory/cards/*.md, TOOLS.md, USER.md, rules/*.md, .learnings/*.md

The ingester is intentionally conservative. Safe card handoffs become cards. Targeted updates append to the right file. Ambiguous material gets kicked out for review instead of being trusted automatically.

For users running multiple agent homes, treat the owner workspace as the hub. Remote or secondary workspaces can write handoffs into their own .claude/memory-handoffs/ directories, then a trusted sync pulls those files into a staging inbox on the owner. That keeps agents informed about what happened elsewhere without creating multiple canonical memories.

Token-heavy terminal work gets the same treatment: make the wrapper explicit, make the escape hatch obvious, and tell every harness what is happening. The TokenJuice starter card documents Claude Code's PreToolUse wrapper path while the upstream PostToolUse fix is still pending, Codex's hook setup, and the savings model: observed output/context compaction can be huge, but billing-token savings depend on whether compacted output is fed into later turns.

Related

• Solomon's Cookbook: the long-form guide and reference docs
• content-guard: the publish-gate scanner used by the pre-push hook
• OpenClaw: the reference memory owner

License

MIT