rename openclient adapter to openclaw, bump to v0.6.0

Breaking: .openclient-system.md -> .openclaw-system.md.
Existing OpenClient users need to re-run ./install.sh openclaw.

Author: codejunkie99

.agent/AGENTS.md

@@ -1,7 +1,7 @@
 # Agent Infrastructure
 
 This folder is the portable brain. Any harness (Claude Code, Cursor, Windsurf,
-OpenCode, OpenClient, Hermes, standalone Python) can mount it and get the
+OpenCode, OpenClaw, Hermes, standalone Python) can mount it and get the
 same memory, skills, and protocols.
 
 ## Memory (read in this order)

README.md

@@ -10,7 +10,7 @@ Follow me on [@AV1DLIVE](https://twitter.com/AV1DLIVE) for updates/collabs on pr
 
 > **One brain, many harnesses.** A portable `.agent/` folder (memory + skills
 > + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode,
-> OpenClient, Hermes, Pi Coding Agent, or a DIY Python loop, and keeps
+> OpenClaw, Hermes, Pi Coding Agent, or a DIY Python loop, and keeps
 > its knowledge when you switch.
 
 <p align="center">
@@ -48,6 +48,16 @@ harnesses.
 - **Protocols** — typed tool schemas, a `permissions.md` that the
   pre-tool-call hook enforces, and a delegation contract for sub-agents.
 
+## What's new in v0.6.0
+
+- **Pi Coding Agent adapter.** `./install.sh pi` drops `AGENTS.md` and
+  symlinks `.pi/skills` to `.agent/skills` so pi sees the full brain
+  with zero duplication. Safe to install alongside hermes/opencode
+  (they all read `AGENTS.md`; we skip the overwrite if one exists).
+- **OpenClient → OpenClaw.** Adapter renamed across the board.
+  Installed file changed: `.openclient-system.md` → `.openclaw-system.md`.
+  Breaking for existing OpenClient users — re-run `./install.sh openclaw`.
+
 ## What's new in v0.5.0
 
 - **Host-agent review protocol.** Python handles filing (cluster, stage,
@@ -79,7 +89,7 @@ brew install agentic-stack
 # drop the brain into any project — the onboarding wizard runs automatically
 cd your-project
 agentic-stack claude-code
-# or: cursor | windsurf | opencode | openclient | hermes | pi | standalone-python
+# or: cursor | windsurf | opencode | openclaw | hermes | pi | standalone-python
 ```
 
 ### Windows (PowerShell)
@@ -103,7 +113,7 @@ brew update && brew upgrade agentic-stack
 git clone https://github.com/codejunkie99/agentic-stack.git
 cd agentic-stack && ./install.sh claude-code         # mac / linux / git-bash
 # or on Windows PowerShell: .\install.ps1 claude-code
-# adapters: claude-code | cursor | windsurf | opencode | openclient | hermes | pi | standalone-python
+# adapters: claude-code | cursor | windsurf | opencode | openclaw | hermes | pi | standalone-python
 ```
 
 ## Onboarding wizard
@@ -208,7 +218,7 @@ adapters/                       # one small shim per harness
 ├── cursor/        (.cursor/rules/*.mdc)
 ├── windsurf/      (.windsurfrules)
 ├── opencode/      (AGENTS.md + opencode.json)
-├── openclient/    (system-prompt include)
+├── openclaw/    (system-prompt include)
 ├── hermes/        (AGENTS.md)
 ├── pi/            (AGENTS.md + .pi/skills symlink)
 └── standalone-python/  (DIY conductor entrypoint)
@@ -232,7 +242,7 @@ onboard_write.py                # atomic file write with backup
 | **Cursor** | `.cursor/rules/*.mdc` | no (manual reflect calls) |
 | **Windsurf** | `.windsurfrules` | no (manual reflect calls) |
 | **OpenCode** | `AGENTS.md` + `opencode.json` | partial (permission rules) |
-| **OpenClient** | system-prompt include | varies by fork |
+| **OpenClaw** | system-prompt include | varies by fork |
 | **Hermes Agent** | `AGENTS.md` (agentskills.io compatible) | partial (own memory) |
 | **Pi Coding Agent** | `AGENTS.md` + `.pi/skills/` | no (extension system) |
 | **Standalone Python** | `run.py` (any LLM) | yes (full control) |

adapters/openclaw/README.md

@@ -0,0 +1,32 @@
+# OpenClaw adapter
+
+## Install
+OpenClaw doesn't have a project-root convention file the way Claude Code
+or Cursor does. Two options:
+
+**Option A (recommended):** Point OpenClaw at the config file:
+
+```bash
+cp adapters/openclaw/config.md ./.openclaw-system.md
+# then configure OpenClaw to load this as its system prompt
+```
+
+**Option B:** Paste the contents of `config.md` into OpenClaw's system
+prompt settings directly.
+
+Or:
+```bash
+./install.sh openclaw
+```
+
+## What it wires up
+A system-prompt include that instructs the agent to treat `.agent/` as
+authoritative on every session.
+
+## Verify
+Ask "Read my lessons file." — it should open `.agent/memory/semantic/LESSONS.md`.
+
+## Notes
+OpenClaw varies by version; some forks support `.openclaw/` folders,
+others use a single config file. Check your version's docs for where to
+point the system prompt.

adapters/openclient/config.md adapters/openclaw/config.mdadapters/openclient/config.md renamed to adapters/openclaw/config.md

@@ -1,6 +1,6 @@
-# OpenClient system prompt (include)
+# OpenClaw system prompt (include)
 
-Paste this into your OpenClient system prompt, or reference it via the
+Paste this into your OpenClaw system prompt, or reference it via the
 `system_prompt_file` option.
 
 ---

adapters/openclient/README.md

@@ -33,7 +33,7 @@ Three modules, one principle: the harness is dumb, the knowledge is in files.
 ## Why the separation matters
 
 You can swap the harness for any of the adapters (Claude Code, Cursor,
-Windsurf, OpenCode, OpenClient, Hermes, standalone Python) and lose
+Windsurf, OpenCode, OpenClaw, Hermes, standalone Python) and lose
 nothing. The brain is portable; only the glue changes.
 
 See `diagram.svg` for a visual.

docs/architecture.md

@@ -1,7 +1,7 @@
 import { interpolate, spring, useCurrentFrame, useVideoConfig } from "remotion";
 import { COLORS, FONT, FONT_MONO } from "../tokens";
 
-const HARNESSES = ["Claude Code", "Cursor", "Windsurf", "OpenCode", "OpenClient", "Hermes", "Python"];
+const HARNESSES = ["Claude Code", "Cursor", "Windsurf", "OpenCode", "OpenClaw", "Hermes", "Python"];
 const BRAIN_LAYERS = [
   { path: "memory/",    color: COLORS.orange },
   { path: "skills/",    color: COLORS.blue   },

docs/demo/src/scenes/Architecture.tsx

@@ -16,7 +16,7 @@ cp /path/to/agentic-stack/install.sh ./
 
 ```bash
 ./install.sh claude-code        # or cursor, windsurf, opencode,
-                                # openclient, hermes, standalone-python
+                                # openclaw, hermes, standalone-python
 ```
 
 Each adapter has its own `README.md` under `adapters/<name>/`.

docs/diagram.svg

@@ -1,18 +1,18 @@
-# OpenClient setup
+# OpenClaw setup
 
 ## What the adapter installs
-- `.openclient-system.md` at project root (to be used as the system prompt)
+- `.openclaw-system.md` at project root (to be used as the system prompt)
 
 ## Install
 ```bash
-./install.sh openclient
+./install.sh openclaw
 ```
 
-Then configure OpenClient to load `.openclient-system.md` as its system
-prompt. The exact steps vary by OpenClient fork/version — check the docs.
+Then configure OpenClaw to load `.openclaw-system.md` as its system
+prompt. The exact steps vary by OpenClaw fork/version — check the docs.
 
 ## How it works
-OpenClient doesn't enforce a project-root convention file; instead, you
+OpenClaw doesn't enforce a project-root convention file; instead, you
 paste the system prompt include (or point the config at it). The content
 mirrors the other adapters: read `.agent/` first, respect permissions,
 log after actions.