brigade-cli 0.8.1__tar.gz → 0.8.2__tar.gz

{brigade_cli-0.8.1 → brigade_cli-0.8.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: brigade-cli
-Version: 0.8.1
+Version: 0.8.2
 Summary: AI agent memory, handoffs, and local guardrails for Codex, Claude Code, OpenCode, Hermes, and OpenClaw.
 Author-email: Solomon Neas <srneas@gmail.com>
 License: MIT
@@ -34,7 +34,7 @@ Dynamic: license-file
 <h1 align="center">Brigade CLI</h1>
 
 <p align="center">
-  <strong>AI agent memory, handoffs, and local guardrails for Codex, Claude Code, OpenCode, Hermes, and OpenClaw.</strong>
+  <strong>AI agent memory, handoffs, and local guardrails for Codex, Claude Code, OpenCode, Antigravity, Pi, Cursor, Aider, Goose, Continue, GitHub Copilot CLI, Qwen Code, Kimi Code, AdaL, OpenHands, Hermes, and OpenClaw.</strong>
 </p>
 
 <p align="center">
@@ -44,17 +44,13 @@ Dynamic: license-file
   <img src="https://img.shields.io/badge/license-MIT-green?style=for-the-badge" alt="MIT license">
 </p>
 
-Brigade is a local-first operator CLI for AI agent workspaces. Local-first means local data on the operator-controlled machine first, before any external service; that machine can be a laptop, workstation, or VPS. The public GitHub repo is [`escoffier-labs/brigade`](https://github.com/escoffier-labs/brigade), the PyPI package is [`brigade-cli`](https://pypi.org/project/brigade-cli/), and the command is `brigade`.
+Your agents run loops. Brigade keeps the receipts.
 
-Brigade helps AI agent tools work from the same memory without turning that memory into a junk drawer.
+Harness agents ship smart models with empty heads. Every session they wake up knowing nothing about your machine, your rules, or what they learned yesterday, and whatever each one figures out scatters across tools and dies there.
 
-## Mise En Place
-
-Mise en place, pronounced "Meez", means everything is in its place before the work starts.
-
-In a kitchen, that is the chef's first job: prep the station, label the ingredients, sharpen the tools, and make sure service does not depend on hunting for basics mid-rush. For agents, it is the same job: rules, memory, handoff inboxes, tools, guards, receipts, and verification paths set up before the session gets expensive.
+**Brigade is a local control plane for agent memory, work, tools, research, review, and release.** Writer agents like Codex, Claude Code, OpenCode, Antigravity, Pi, Cursor, Aider, Goose, Continue, GitHub Copilot CLI, Qwen Code, Kimi Code, AdaL, and OpenHands leave handoff notes as they work. A memory owner like OpenClaw or Hermes ingests the ones worth keeping. Brigade lints, guards, and routes everything in between, and every consequential action lands a receipt in a plain file you can grep, diff, and prune. Nothing is published, pushed, or saved behind your back, and the shared memory never decays into a junk drawer.
 
-This is the most important part of Brigade. The chef owns the station, and every agent working in it should leave the setup clearer, safer, and easier for the next agent to use.
+It runs on the operator-controlled machine first, before any external service, whether that machine is a laptop, workstation, or VPS: local by default, loud about the exceptions. The GitHub repo is [`escoffier-labs/brigade`](https://github.com/escoffier-labs/brigade), the PyPI package is [`brigade-cli`](https://pypi.org/project/brigade-cli/), and the command is `brigade`.
 
 ## Current Status
 
@@ -66,6 +62,8 @@ It is still early-stage and being actively fleshed out. The current focus is har
 
 Want an agent to set this up for you? Point it at this repository. The root [`AGENTS.md`](AGENTS.md) tells agents how to install Brigade, verify with doctor, adapt your existing homegrown workflow instead of replacing it, keep local generated folders out of commits, and stop before any remote or destructive action. The fuller walkthrough is in [`docs/agent-assisted-setup.md`](docs/agent-assisted-setup.md).
 
+New here? Start with [`docs/first-10-minutes.md`](docs/first-10-minutes.md). Maintainers can use [`docs/support-response-templates.md`](docs/support-response-templates.md) for quick first replies to install, quickstart, doctor, commit-scope, and security questions.
+
 Good first install:
 
 ```bash
@@ -85,10 +83,10 @@ brigade operator doctor --target ~/agent-workspace --profile local-operator
 For multiple agent surfaces:
 
 ```bash
-brigade operator quickstart --target ./my-repo --harnesses codex,claude,opencode
+brigade operator quickstart --target ./my-repo --harnesses codex,claude,opencode,antigravity,pi,cursor,aider,goose,continue,copilot,qwen,kimi,adal,openhands
 ```
 
-If you use [OpenClaw](https://github.com/solomonneas/openclaw), [Hermes](https://github.com/NousResearch/hermes-agent), [Codex](https://github.com/openai/codex), Claude Code, [OpenCode](https://github.com/opencode-ai/opencode), or a mix of them, Brigade gives those tools a shared local pattern:
+If you use [OpenClaw](https://github.com/solomonneas/openclaw), [Hermes](https://github.com/NousResearch/hermes-agent), [Codex](https://github.com/openai/codex), Claude Code, [OpenCode](https://github.com/opencode-ai/opencode), Antigravity, Pi, Cursor, or a mix of them, Brigade gives those tools a shared local pattern:
 
 1. agents write handoff notes
 2. the memory ingester scans, lints, and routes them
@@ -115,11 +113,12 @@ flowchart TB
         CODEX["<b>Codex CLI</b><br/>handoff writer"]
         CLAUDE["<b>Claude Code</b><br/>handoff writer"]
         OPEN["<b>OpenCode</b><br/>handoff writer"]
+        MORE["<b>more CLI writers</b><br/>Antigravity · Pi · Cursor<br/>Aider · Goose · Continue<br/>Copilot · Qwen · Kimi · AdaL · OpenHands"]
         HERMES["<b>Hermes</b><br/>writer or owner"]
     end
 
-    CODEX & CLAUDE & OPEN & HERMES == handoff drafts ==> BRIGADE
-    MEMORY -. context .-> CODEX & CLAUDE & OPEN & HERMES
+    CODEX & CLAUDE & OPEN & MORE & HERMES == handoff drafts ==> BRIGADE
+    MEMORY -. context .-> CODEX & CLAUDE & OPEN & MORE & HERMES
 
     subgraph LOCAL [" local operator lanes "]
         WORK["work sessions<br/>tasks · plans · verification"]
@@ -138,7 +137,7 @@ flowchart TB
     class OWNER owner;
     class BRIGADE brigade;
     class MEMORY,STATE state;
-    class WORK,SCAN,RELEASE,CODEX,CLAUDE,OPEN,HERMES lane;
+    class WORK,SCAN,RELEASE,CODEX,CLAUDE,OPEN,MORE,HERMES lane;
 ```
 
 > Brigade was extracted from the [**solos-cookbook**](https://github.com/solomonneas/solos-cookbook), a documented 24/7 multi-agent stack running in production. If you want the full picture of how Brigade fits into a real setup, start there, and a star helps other people find it.
@@ -161,13 +160,21 @@ Agent tools are getting good enough that people use more than one of them. That
 Brigade gives the setup a home base.
 
 - OpenClaw or Hermes can be the main memory owner.
-- Codex, Claude Code, OpenCode, and Hermes can write handoff notes.
+- Codex, Claude Code, OpenCode, Antigravity, Pi, Cursor, Aider, Goose, Continue, GitHub Copilot CLI, Qwen Code, Kimi Code, AdaL, OpenHands, and Hermes can write handoff notes.
 - You can inspect and lint those notes before saving them.
 - Local receipts show what happened during work, scans, and reviews.
 - Risky actions stay manual.
 
 The goal is not to make a giant automation machine. The goal is to make agent memory understandable, reviewable, and portable across harnesses.
 
+## Mise En Place
+
+The name comes from the kitchen. A *brigade de cuisine* is the staff that runs the line, and *mise en place*, pronounced "meez", means everything is in its place before the work starts.
+
+In a kitchen, that is the chef's first job: prep the station, label the ingredients, sharpen the tools, and make sure service does not depend on hunting for basics mid-rush. For agents, it is the same job: rules, memory, handoff inboxes, tools, guards, receipts, and verification paths set up before the session gets expensive.
+
+That is the idea Brigade is built on. The chef owns the station, and every agent working in it should leave the setup clearer, safer, and easier for the next agent to use.
+
 ## Start Small
 
 Install:
@@ -190,7 +197,7 @@ brigade operator quickstart --target ~/agent-workspace --depth workspace --harne
 brigade operator doctor --target ~/agent-workspace --profile local-operator
 ```
 
-Use `--dry-run` first if you want to preview the local files Brigade will write. To wire more than one agent surface, pass a comma-separated list such as `--harnesses codex,claude,opencode`.
+Use `--dry-run` first if you want to preview the local files Brigade will write. To wire more than one agent surface, pass a comma-separated list such as `--harnesses codex,claude,opencode,antigravity,pi,cursor,aider,goose,continue,copilot,qwen,kimi,adal,openhands`.
 
 If you already have a homegrown setup with scripts, handoff folders, crons, or process managers, use the adoption loop before changing it:
 
@@ -210,7 +217,7 @@ brigade operator surfaces import-issues --target ~/agent-workspace --json
 
 `adopt plan` is read-only. `adopt capture` writes a redacted local snapshot under `.brigade/operator/adoption/`. `adopt import-issues` routes adoption gaps into the normal work inbox so the migration shows up in `work brief` and the daily loop. `operator migration status/doctor/import-issues/consolidate` rolls adoption state, surface review state, and pending migration work into one replacement-progress view, then lets a reviewed rollup supersede tiny record-level imports. `operator surfaces capture/list/doctor/review/reviews/import-issues` keeps a separate redacted registry for shell crontab, OpenClaw cron, and PM2 coverage under `.brigade/operator/surfaces/`. Scheduler and process surfaces are reported as counts, status totals, ordinal labels, review decisions, and fingerprints, not raw scheduler lines, job names, process names, command paths, host details, or environment values.
 
-For a fuller first-run walkthrough and troubleshooting checklist, see [`docs/new-user-quickstart.md`](docs/new-user-quickstart.md). If quickstart fails, use the Quickstart setup problem issue form and include the redacted `issue_report` from `brigade operator quickstart --json`.
+For a fuller first-run walkthrough and troubleshooting checklist, see [`docs/new-user-quickstart.md`](docs/new-user-quickstart.md). For the shortest path, use [`docs/first-10-minutes.md`](docs/first-10-minutes.md). If quickstart fails, use the Quickstart setup problem issue form and include the redacted `issue_report` from `brigade operator quickstart --json`.
 
 Write a handoff note:
 
@@ -231,12 +238,27 @@ That is the simplest useful version of Brigade: shared handoffs, local review, d
 
 ## How Memory Handoffs Work
 
-Each writer harness gets its own local inbox:
-
-- `.codex/memory-handoffs/`
-- `.claude/memory-handoffs/`
-- `.opencode/memory-handoffs/`
-- `.hermes/memory-handoffs/`
+Each writer harness gets its own local inbox. Use `brigade handoff draft --inbox <id>` to write to the matching inbox, or select the harness with `brigade operator quickstart --harnesses ...`.
+
+| Writer | `--inbox` / harness id | Local inbox | Brigade support |
+|---|---|---|---|
+| Codex CLI | `codex` | `.codex/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Claude Code | `claude` | `.claude/memory-handoffs/` | handoff template, ingest source, tools, skills |
+| OpenCode | `opencode` | `.opencode/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Antigravity | `antigravity` | `.antigravity/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Pi | `pi` | `.pi/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Cursor | `cursor` | `.cursor/memory-handoffs/` | handoff template, ingest source, dogfood adapter, rules, skills |
+| Aider | `aider` | `.aider/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Goose | `goose` | `.goose/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Continue | `continue` | `.continue/memory-handoffs/` | handoff template, ingest source, dogfood adapter, rules, skills |
+| GitHub Copilot CLI | `copilot` | `.copilot/memory-handoffs/` | handoff template, ingest source, dogfood adapter, instructions, skills |
+| Qwen Code | `qwen` | `.qwen/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Kimi Code | `kimi` | `.kimi/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| AdaL | `adal` | `.adal/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| OpenHands | `openhands` | `.openhands/memory-handoffs/` | handoff template, ingest source, dogfood adapter, instructions, skills |
+| Hermes | `hermes` | `.hermes/memory-handoffs/` | handoff template, ingest source, owner adapter fragments |
+
+OpenClaw is usually the canonical memory owner rather than a writer inbox. Add it with `--harnesses openclaw,...` when the workspace should own durable memory.
 
 The memory owner, usually OpenClaw or Hermes, can ingest handoffs into the permanent memory files. Brigade keeps the handoff format consistent so different tools can contribute without each one inventing its own note style.
 
@@ -246,6 +268,17 @@ flowchart LR
         C[".codex/memory-handoffs/"]
         CL[".claude/memory-handoffs/"]
         O[".opencode/memory-handoffs/"]
+        A[".antigravity/memory-handoffs/"]
+        P[".pi/memory-handoffs/"]
+        CU[".cursor/memory-handoffs/"]
+        AI[".aider/memory-handoffs/"]
+        G[".goose/memory-handoffs/"]
+        CO[".continue/memory-handoffs/"]
+        GH[".copilot/memory-handoffs/"]
+        Q[".qwen/memory-handoffs/"]
+        K[".kimi/memory-handoffs/"]
+        AD[".adal/memory-handoffs/"]
+        OH[".openhands/memory-handoffs/"]
         H[".hermes/memory-handoffs/"]
     end
 
@@ -254,14 +287,14 @@ flowchart LR
     OWNER["OpenClaw / Hermes<br/>memory owner"]
     MEM["durable memory<br/>cards · docs · learnings"]
 
-    C & CL & O & H --> DRAFT --> REVIEW
+    C & CL & O & A & P & CU & AI & G & CO & GH & Q & K & AD & OH & H --> DRAFT --> REVIEW
     REVIEW -->|safe targeted note| OWNER --> MEM
     REVIEW -->|needs judgment| INBOX["review inbox"]
 
     classDef local fill:#eff6ff,stroke:#2563eb,color:#1e3a8a;
     classDef review fill:#fff7ed,stroke:#ea580c,color:#7c2d12;
     classDef memory fill:#ecfdf5,stroke:#059669,color:#064e3b;
-    class C,CL,O,H,DRAFT local;
+    class C,CL,O,A,P,CU,AI,G,CO,GH,Q,K,AD,OH,H,DRAFT local;
     class REVIEW,INBOX review;
     class OWNER,MEM memory;
 ```
@@ -364,7 +397,7 @@ For memory:
 - scan handoff drafts with Content Guard before they become durable memory
 - track which local inboxes the ingestor should watch
 - reconcile ingester receipts so skipped, failed, routed, and promoted notes stay visible
-- support OpenClaw, Hermes, Codex, Claude Code, and OpenCode conventions
+- support OpenClaw, Hermes, Codex, Claude Code, OpenCode, Antigravity, Pi, Cursor, Aider, Goose, Continue, GitHub Copilot CLI, Qwen Code, Kimi Code, AdaL, and OpenHands conventions
 
 For local work:
 
@@ -480,7 +513,7 @@ flowchart LR
 
     SOURCE --> CATALOG --> PROJECT
     CATALOG --> APPROVAL --> RUN
-    PROJECT -. local generated .-> HARNESSES[".codex · .claude<br/>.opencode · .mcp"]
+    PROJECT -. local generated .-> HARNESSES[".codex · .claude<br/>.opencode · .antigravity · .pi · .cursor<br/>.aider · .goose · .continue · .copilot<br/>.qwen · .kimi · .adal · .openhands · .mcp"]
 
     classDef source fill:#ecfdf5,stroke:#059669,color:#064e3b;
     classDef local fill:#eff6ff,stroke:#2563eb,color:#1e3a8a;
@@ -595,7 +628,7 @@ OpenClaw can be the memory owner. Brigade gives nearby tools a way to contribute
 
 ```mermaid
 flowchart LR
-    WRITERS["Codex · Claude · OpenCode<br/>writer inboxes"]
+    WRITERS["Codex · Claude · OpenCode<br/>Antigravity · Pi · Cursor writer inboxes"]
     BRIGADE["Brigade<br/>draft · lint · source coverage"]
     OPENCLAW["OpenClaw<br/>memory owner"]
     MEMORY["canonical memory"]
@@ -615,7 +648,7 @@ flowchart LR
 A repo-adjacent setup is:
 
 ```bash
-brigade init --target ./my-repo --depth repo --harnesses openclaw,codex,claude,opencode
+brigade init --target ./my-repo --depth repo --harnesses openclaw,codex,claude,opencode,antigravity,pi,cursor,aider,goose,continue,copilot,qwen,kimi,adal,openhands
 brigade handoff sources init --target ./my-repo
 brigade handoff doctor --target ./my-repo
 ```
@@ -738,7 +771,7 @@ The full technical walkthrough still exists; it is just not the README anymore.
 
 ## Tiny Glossary
 
-- **Harness**: an agent tool such as OpenClaw, Hermes, Codex, Claude Code, or OpenCode.
+- **Harness**: an agent tool such as OpenClaw, Hermes, Codex, Claude Code, OpenCode, Antigravity, Pi, or Cursor.
 - **Handoff**: a note an agent writes for later review.
 - **Inbox**: the local folder where handoff notes wait.
 - **Memory owner**: the place that keeps durable shared memory.

{brigade_cli-0.8.1 → brigade_cli-0.8.2}/README.md

@@ -5,7 +5,7 @@
 <h1 align="center">Brigade CLI</h1>
 
 <p align="center">
-  <strong>AI agent memory, handoffs, and local guardrails for Codex, Claude Code, OpenCode, Hermes, and OpenClaw.</strong>
+  <strong>AI agent memory, handoffs, and local guardrails for Codex, Claude Code, OpenCode, Antigravity, Pi, Cursor, Aider, Goose, Continue, GitHub Copilot CLI, Qwen Code, Kimi Code, AdaL, OpenHands, Hermes, and OpenClaw.</strong>
 </p>
 
 <p align="center">
@@ -15,17 +15,13 @@
   <img src="https://img.shields.io/badge/license-MIT-green?style=for-the-badge" alt="MIT license">
 </p>
 
-Brigade is a local-first operator CLI for AI agent workspaces. Local-first means local data on the operator-controlled machine first, before any external service; that machine can be a laptop, workstation, or VPS. The public GitHub repo is [`escoffier-labs/brigade`](https://github.com/escoffier-labs/brigade), the PyPI package is [`brigade-cli`](https://pypi.org/project/brigade-cli/), and the command is `brigade`.
+Your agents run loops. Brigade keeps the receipts.
 
-Brigade helps AI agent tools work from the same memory without turning that memory into a junk drawer.
+Harness agents ship smart models with empty heads. Every session they wake up knowing nothing about your machine, your rules, or what they learned yesterday, and whatever each one figures out scatters across tools and dies there.
 
-## Mise En Place
-
-Mise en place, pronounced "Meez", means everything is in its place before the work starts.
-
-In a kitchen, that is the chef's first job: prep the station, label the ingredients, sharpen the tools, and make sure service does not depend on hunting for basics mid-rush. For agents, it is the same job: rules, memory, handoff inboxes, tools, guards, receipts, and verification paths set up before the session gets expensive.
+**Brigade is a local control plane for agent memory, work, tools, research, review, and release.** Writer agents like Codex, Claude Code, OpenCode, Antigravity, Pi, Cursor, Aider, Goose, Continue, GitHub Copilot CLI, Qwen Code, Kimi Code, AdaL, and OpenHands leave handoff notes as they work. A memory owner like OpenClaw or Hermes ingests the ones worth keeping. Brigade lints, guards, and routes everything in between, and every consequential action lands a receipt in a plain file you can grep, diff, and prune. Nothing is published, pushed, or saved behind your back, and the shared memory never decays into a junk drawer.
 
-This is the most important part of Brigade. The chef owns the station, and every agent working in it should leave the setup clearer, safer, and easier for the next agent to use.
+It runs on the operator-controlled machine first, before any external service, whether that machine is a laptop, workstation, or VPS: local by default, loud about the exceptions. The GitHub repo is [`escoffier-labs/brigade`](https://github.com/escoffier-labs/brigade), the PyPI package is [`brigade-cli`](https://pypi.org/project/brigade-cli/), and the command is `brigade`.
 
 ## Current Status
 
@@ -37,6 +33,8 @@ It is still early-stage and being actively fleshed out. The current focus is har
 
 Want an agent to set this up for you? Point it at this repository. The root [`AGENTS.md`](AGENTS.md) tells agents how to install Brigade, verify with doctor, adapt your existing homegrown workflow instead of replacing it, keep local generated folders out of commits, and stop before any remote or destructive action. The fuller walkthrough is in [`docs/agent-assisted-setup.md`](docs/agent-assisted-setup.md).
 
+New here? Start with [`docs/first-10-minutes.md`](docs/first-10-minutes.md). Maintainers can use [`docs/support-response-templates.md`](docs/support-response-templates.md) for quick first replies to install, quickstart, doctor, commit-scope, and security questions.
+
 Good first install:
 
 ```bash
@@ -56,10 +54,10 @@ brigade operator doctor --target ~/agent-workspace --profile local-operator
 For multiple agent surfaces:
 
 ```bash
-brigade operator quickstart --target ./my-repo --harnesses codex,claude,opencode
+brigade operator quickstart --target ./my-repo --harnesses codex,claude,opencode,antigravity,pi,cursor,aider,goose,continue,copilot,qwen,kimi,adal,openhands
 ```
 
-If you use [OpenClaw](https://github.com/solomonneas/openclaw), [Hermes](https://github.com/NousResearch/hermes-agent), [Codex](https://github.com/openai/codex), Claude Code, [OpenCode](https://github.com/opencode-ai/opencode), or a mix of them, Brigade gives those tools a shared local pattern:
+If you use [OpenClaw](https://github.com/solomonneas/openclaw), [Hermes](https://github.com/NousResearch/hermes-agent), [Codex](https://github.com/openai/codex), Claude Code, [OpenCode](https://github.com/opencode-ai/opencode), Antigravity, Pi, Cursor, or a mix of them, Brigade gives those tools a shared local pattern:
 
 1. agents write handoff notes
 2. the memory ingester scans, lints, and routes them
@@ -86,11 +84,12 @@ flowchart TB
         CODEX["<b>Codex CLI</b><br/>handoff writer"]
         CLAUDE["<b>Claude Code</b><br/>handoff writer"]
         OPEN["<b>OpenCode</b><br/>handoff writer"]
+        MORE["<b>more CLI writers</b><br/>Antigravity · Pi · Cursor<br/>Aider · Goose · Continue<br/>Copilot · Qwen · Kimi · AdaL · OpenHands"]
         HERMES["<b>Hermes</b><br/>writer or owner"]
     end
 
-    CODEX & CLAUDE & OPEN & HERMES == handoff drafts ==> BRIGADE
-    MEMORY -. context .-> CODEX & CLAUDE & OPEN & HERMES
+    CODEX & CLAUDE & OPEN & MORE & HERMES == handoff drafts ==> BRIGADE
+    MEMORY -. context .-> CODEX & CLAUDE & OPEN & MORE & HERMES
 
     subgraph LOCAL [" local operator lanes "]
         WORK["work sessions<br/>tasks · plans · verification"]
@@ -109,7 +108,7 @@ flowchart TB
     class OWNER owner;
     class BRIGADE brigade;
     class MEMORY,STATE state;
-    class WORK,SCAN,RELEASE,CODEX,CLAUDE,OPEN,HERMES lane;
+    class WORK,SCAN,RELEASE,CODEX,CLAUDE,OPEN,MORE,HERMES lane;
 ```
 
 > Brigade was extracted from the [**solos-cookbook**](https://github.com/solomonneas/solos-cookbook), a documented 24/7 multi-agent stack running in production. If you want the full picture of how Brigade fits into a real setup, start there, and a star helps other people find it.
@@ -132,13 +131,21 @@ Agent tools are getting good enough that people use more than one of them. That
 Brigade gives the setup a home base.
 
 - OpenClaw or Hermes can be the main memory owner.
-- Codex, Claude Code, OpenCode, and Hermes can write handoff notes.
+- Codex, Claude Code, OpenCode, Antigravity, Pi, Cursor, Aider, Goose, Continue, GitHub Copilot CLI, Qwen Code, Kimi Code, AdaL, OpenHands, and Hermes can write handoff notes.
 - You can inspect and lint those notes before saving them.
 - Local receipts show what happened during work, scans, and reviews.
 - Risky actions stay manual.
 
 The goal is not to make a giant automation machine. The goal is to make agent memory understandable, reviewable, and portable across harnesses.
 
+## Mise En Place
+
+The name comes from the kitchen. A *brigade de cuisine* is the staff that runs the line, and *mise en place*, pronounced "meez", means everything is in its place before the work starts.
+
+In a kitchen, that is the chef's first job: prep the station, label the ingredients, sharpen the tools, and make sure service does not depend on hunting for basics mid-rush. For agents, it is the same job: rules, memory, handoff inboxes, tools, guards, receipts, and verification paths set up before the session gets expensive.
+
+That is the idea Brigade is built on. The chef owns the station, and every agent working in it should leave the setup clearer, safer, and easier for the next agent to use.
+
 ## Start Small
 
 Install:
@@ -161,7 +168,7 @@ brigade operator quickstart --target ~/agent-workspace --depth workspace --harne
 brigade operator doctor --target ~/agent-workspace --profile local-operator
 ```
 
-Use `--dry-run` first if you want to preview the local files Brigade will write. To wire more than one agent surface, pass a comma-separated list such as `--harnesses codex,claude,opencode`.
+Use `--dry-run` first if you want to preview the local files Brigade will write. To wire more than one agent surface, pass a comma-separated list such as `--harnesses codex,claude,opencode,antigravity,pi,cursor,aider,goose,continue,copilot,qwen,kimi,adal,openhands`.
 
 If you already have a homegrown setup with scripts, handoff folders, crons, or process managers, use the adoption loop before changing it:
 
@@ -181,7 +188,7 @@ brigade operator surfaces import-issues --target ~/agent-workspace --json
 
 `adopt plan` is read-only. `adopt capture` writes a redacted local snapshot under `.brigade/operator/adoption/`. `adopt import-issues` routes adoption gaps into the normal work inbox so the migration shows up in `work brief` and the daily loop. `operator migration status/doctor/import-issues/consolidate` rolls adoption state, surface review state, and pending migration work into one replacement-progress view, then lets a reviewed rollup supersede tiny record-level imports. `operator surfaces capture/list/doctor/review/reviews/import-issues` keeps a separate redacted registry for shell crontab, OpenClaw cron, and PM2 coverage under `.brigade/operator/surfaces/`. Scheduler and process surfaces are reported as counts, status totals, ordinal labels, review decisions, and fingerprints, not raw scheduler lines, job names, process names, command paths, host details, or environment values.
 
-For a fuller first-run walkthrough and troubleshooting checklist, see [`docs/new-user-quickstart.md`](docs/new-user-quickstart.md). If quickstart fails, use the Quickstart setup problem issue form and include the redacted `issue_report` from `brigade operator quickstart --json`.
+For a fuller first-run walkthrough and troubleshooting checklist, see [`docs/new-user-quickstart.md`](docs/new-user-quickstart.md). For the shortest path, use [`docs/first-10-minutes.md`](docs/first-10-minutes.md). If quickstart fails, use the Quickstart setup problem issue form and include the redacted `issue_report` from `brigade operator quickstart --json`.
 
 Write a handoff note:
 
@@ -202,12 +209,27 @@ That is the simplest useful version of Brigade: shared handoffs, local review, d
 
 ## How Memory Handoffs Work
 
-Each writer harness gets its own local inbox:
-
-- `.codex/memory-handoffs/`
-- `.claude/memory-handoffs/`
-- `.opencode/memory-handoffs/`
-- `.hermes/memory-handoffs/`
+Each writer harness gets its own local inbox. Use `brigade handoff draft --inbox <id>` to write to the matching inbox, or select the harness with `brigade operator quickstart --harnesses ...`.
+
+| Writer | `--inbox` / harness id | Local inbox | Brigade support |
+|---|---|---|---|
+| Codex CLI | `codex` | `.codex/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Claude Code | `claude` | `.claude/memory-handoffs/` | handoff template, ingest source, tools, skills |
+| OpenCode | `opencode` | `.opencode/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Antigravity | `antigravity` | `.antigravity/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Pi | `pi` | `.pi/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Cursor | `cursor` | `.cursor/memory-handoffs/` | handoff template, ingest source, dogfood adapter, rules, skills |
+| Aider | `aider` | `.aider/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Goose | `goose` | `.goose/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Continue | `continue` | `.continue/memory-handoffs/` | handoff template, ingest source, dogfood adapter, rules, skills |
+| GitHub Copilot CLI | `copilot` | `.copilot/memory-handoffs/` | handoff template, ingest source, dogfood adapter, instructions, skills |
+| Qwen Code | `qwen` | `.qwen/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| Kimi Code | `kimi` | `.kimi/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| AdaL | `adal` | `.adal/memory-handoffs/` | handoff template, ingest source, dogfood adapter, tools, skills |
+| OpenHands | `openhands` | `.openhands/memory-handoffs/` | handoff template, ingest source, dogfood adapter, instructions, skills |
+| Hermes | `hermes` | `.hermes/memory-handoffs/` | handoff template, ingest source, owner adapter fragments |
+
+OpenClaw is usually the canonical memory owner rather than a writer inbox. Add it with `--harnesses openclaw,...` when the workspace should own durable memory.
 
 The memory owner, usually OpenClaw or Hermes, can ingest handoffs into the permanent memory files. Brigade keeps the handoff format consistent so different tools can contribute without each one inventing its own note style.
 
@@ -217,6 +239,17 @@ flowchart LR
         C[".codex/memory-handoffs/"]
         CL[".claude/memory-handoffs/"]
         O[".opencode/memory-handoffs/"]
+        A[".antigravity/memory-handoffs/"]
+        P[".pi/memory-handoffs/"]
+        CU[".cursor/memory-handoffs/"]
+        AI[".aider/memory-handoffs/"]
+        G[".goose/memory-handoffs/"]
+        CO[".continue/memory-handoffs/"]
+        GH[".copilot/memory-handoffs/"]
+        Q[".qwen/memory-handoffs/"]
+        K[".kimi/memory-handoffs/"]
+        AD[".adal/memory-handoffs/"]
+        OH[".openhands/memory-handoffs/"]
         H[".hermes/memory-handoffs/"]
     end
 
@@ -225,14 +258,14 @@ flowchart LR
     OWNER["OpenClaw / Hermes<br/>memory owner"]
     MEM["durable memory<br/>cards · docs · learnings"]
 
-    C & CL & O & H --> DRAFT --> REVIEW
+    C & CL & O & A & P & CU & AI & G & CO & GH & Q & K & AD & OH & H --> DRAFT --> REVIEW
     REVIEW -->|safe targeted note| OWNER --> MEM
     REVIEW -->|needs judgment| INBOX["review inbox"]
 
     classDef local fill:#eff6ff,stroke:#2563eb,color:#1e3a8a;
     classDef review fill:#fff7ed,stroke:#ea580c,color:#7c2d12;
     classDef memory fill:#ecfdf5,stroke:#059669,color:#064e3b;
-    class C,CL,O,H,DRAFT local;
+    class C,CL,O,A,P,CU,AI,G,CO,GH,Q,K,AD,OH,H,DRAFT local;
     class REVIEW,INBOX review;
     class OWNER,MEM memory;
 ```
@@ -335,7 +368,7 @@ For memory:
 - scan handoff drafts with Content Guard before they become durable memory
 - track which local inboxes the ingestor should watch
 - reconcile ingester receipts so skipped, failed, routed, and promoted notes stay visible
-- support OpenClaw, Hermes, Codex, Claude Code, and OpenCode conventions
+- support OpenClaw, Hermes, Codex, Claude Code, OpenCode, Antigravity, Pi, Cursor, Aider, Goose, Continue, GitHub Copilot CLI, Qwen Code, Kimi Code, AdaL, and OpenHands conventions
 
 For local work:
 
@@ -451,7 +484,7 @@ flowchart LR
 
     SOURCE --> CATALOG --> PROJECT
     CATALOG --> APPROVAL --> RUN
-    PROJECT -. local generated .-> HARNESSES[".codex · .claude<br/>.opencode · .mcp"]
+    PROJECT -. local generated .-> HARNESSES[".codex · .claude<br/>.opencode · .antigravity · .pi · .cursor<br/>.aider · .goose · .continue · .copilot<br/>.qwen · .kimi · .adal · .openhands · .mcp"]
 
     classDef source fill:#ecfdf5,stroke:#059669,color:#064e3b;
     classDef local fill:#eff6ff,stroke:#2563eb,color:#1e3a8a;
@@ -566,7 +599,7 @@ OpenClaw can be the memory owner. Brigade gives nearby tools a way to contribute
 
 ```mermaid
 flowchart LR
-    WRITERS["Codex · Claude · OpenCode<br/>writer inboxes"]
+    WRITERS["Codex · Claude · OpenCode<br/>Antigravity · Pi · Cursor writer inboxes"]
     BRIGADE["Brigade<br/>draft · lint · source coverage"]
     OPENCLAW["OpenClaw<br/>memory owner"]
     MEMORY["canonical memory"]
@@ -586,7 +619,7 @@ flowchart LR
 A repo-adjacent setup is:
 
 ```bash
-brigade init --target ./my-repo --depth repo --harnesses openclaw,codex,claude,opencode
+brigade init --target ./my-repo --depth repo --harnesses openclaw,codex,claude,opencode,antigravity,pi,cursor,aider,goose,continue,copilot,qwen,kimi,adal,openhands
 brigade handoff sources init --target ./my-repo
 brigade handoff doctor --target ./my-repo
 ```
@@ -709,7 +742,7 @@ The full technical walkthrough still exists; it is just not the README anymore.
 
 ## Tiny Glossary
 
-- **Harness**: an agent tool such as OpenClaw, Hermes, Codex, Claude Code, or OpenCode.
+- **Harness**: an agent tool such as OpenClaw, Hermes, Codex, Claude Code, OpenCode, Antigravity, Pi, or Cursor.
 - **Handoff**: a note an agent writes for later review.
 - **Inbox**: the local folder where handoff notes wait.
 - **Memory owner**: the place that keeps durable shared memory.

{brigade_cli-0.8.1 → brigade_cli-0.8.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "brigade-cli"
-version = "0.8.1"
+version = "0.8.2"
 description = "AI agent memory, handoffs, and local guardrails for Codex, Claude Code, OpenCode, Hermes, and OpenClaw."
 readme = "README.md"
 requires-python = ">=3.10"

{brigade_cli-0.8.1 → brigade_cli-0.8.2}/src/brigade/__init__.py

@@ -1,3 +1,3 @@
 """Brigade: local operator-system CLI for agent workspaces."""
 
-__version__ = "0.8.1"
+__version__ = "0.8.2"