refactor: Chitin rebrand — go.mod, imports, README, workflows, docs

- go.mod: github.com/AgentGuardHQ/shellforge → github.com/chitinhq/shellforge
- 14 Go files: update all import paths
- README: badges, brew tap, links → chitinhq; remove AgentGuard Cloud (archived)
- Workflows: release.yml + clawta-dispatch.yml → chitinhq org
- docs: architecture.md, roadmap.md, index.html → Chitin branding
- CLAUDE.md: AgentGuard → Chitin in agent identity

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: jpleva91

.github/workflows/clawta-dispatch.yml

@@ -26,15 +26,15 @@ jobs:
           echo "Task ID:   ${TASK_ID}"
           echo "Type:      ${TASK_TYPE}"
           echo "Priority:  ${TASK_PRIORITY}"
-          gh release download --repo AgentGuardHQ/clawta \
+          gh release download --repo chitinhq/clawta \
             --pattern "clawta-linux-amd64" \
             --output clawta \
             --clobber || echo "WARN: clawta release not yet published"
           chmod +x clawta 2>/dev/null || true
 
       - name: Configure git identity
         run: |
-          git config --global user.email "octi-pulpo@agentguardhq.com"
+          git config --global user.email "octi-pulpo@chitinhq.com"
           git config --global user.name "Octi Pulpo Bot"
 
       - name: Run Clawta agent

.github/workflows/release.yml

@@ -38,7 +38,7 @@ jobs:
           VERSION="${VERSION#v}"
 
           # Download checksums
-          curl -sL "https://github.com/AgentGuardHQ/shellforge/releases/download/v${VERSION}/checksums.txt" -o checksums.txt
+          curl -sL "https://github.com/chitinhq/shellforge/releases/download/v${VERSION}/checksums.txt" -o checksums.txt
 
           DARWIN_ARM64=$(grep darwin_arm64 checksums.txt | awk '{print $1}')
           DARWIN_AMD64=$(grep darwin_amd64 checksums.txt | awk '{print $1}')
@@ -51,28 +51,28 @@ jobs:
 
           class Shellforge < Formula
             desc "Local governed agent runtime — wraps Ollama + AgentGuard governance"
-            homepage "https://github.com/AgentGuardHQ/shellforge"
+            homepage "https://github.com/chitinhq/shellforge"
             version "${VERSION}"
             license "MIT"
 
             on_macos do
               on_arm do
-                url "https://github.com/AgentGuardHQ/shellforge/releases/download/v${VERSION}/shellforge_${VERSION}_darwin_arm64.tar.gz"
+                url "https://github.com/chitinhq/shellforge/releases/download/v${VERSION}/shellforge_${VERSION}_darwin_arm64.tar.gz"
                 sha256 "${DARWIN_ARM64}"
               end
               on_intel do
-                url "https://github.com/AgentGuardHQ/shellforge/releases/download/v${VERSION}/shellforge_${VERSION}_darwin_amd64.tar.gz"
+                url "https://github.com/chitinhq/shellforge/releases/download/v${VERSION}/shellforge_${VERSION}_darwin_amd64.tar.gz"
                 sha256 "${DARWIN_AMD64}"
               end
             end
 
             on_linux do
               on_arm do
-                url "https://github.com/AgentGuardHQ/shellforge/releases/download/v${VERSION}/shellforge_${VERSION}_linux_arm64.tar.gz"
+                url "https://github.com/chitinhq/shellforge/releases/download/v${VERSION}/shellforge_${VERSION}_linux_arm64.tar.gz"
                 sha256 "${LINUX_ARM64}"
               end
               on_intel do
-                url "https://github.com/AgentGuardHQ/shellforge/releases/download/v${VERSION}/shellforge_${VERSION}_linux_amd64.tar.gz"
+                url "https://github.com/chitinhq/shellforge/releases/download/v${VERSION}/shellforge_${VERSION}_linux_amd64.tar.gz"
                 sha256 "${LINUX_AMD64}"
               end
             end
@@ -88,7 +88,7 @@ jobs:
           FORMULA
 
           # Push to homebrew-tap repo
-          git clone "https://x-access-token:${GH_TOKEN}@github.com/AgentGuardHQ/homebrew-tap.git" tap
+          git clone "https://x-access-token:${GH_TOKEN}@github.com/chitinhq/homebrew-tap.git" tap
           mkdir -p tap/Formula
           cp shellforge.rb tap/Formula/shellforge.rb
           cd tap

CLAUDE.md

@@ -1,6 +1,6 @@
 ## Agent Identity
 
-At session start, if you see `[AgentGuard] No agent identity set`, ask the user:
+At session start, if you see `[Chitin] No agent identity set`, ask the user:
 1. **Role**: developer / reviewer / ops / security / planner
 2. **Driver**: human / claude-code / copilot / ci
 

README.md

@@ -5,13 +5,12 @@
 **Governed AI coding CLI and agent runtime — one Go binary, local or cloud.**
 
 [![Go](https://img.shields.io/badge/Go-1.18+-00ADD8?style=for-the-badge&logo=go&logoColor=white)](https://go.dev)
-[![GitHub Pages](https://img.shields.io/badge/Live_Site-agentguardhq.github.io/shellforge-ff6b2b?style=for-the-badge)](https://agentguardhq.github.io/shellforge)
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue?style=for-the-badge)](LICENSE)
-[![AgentGuard](https://img.shields.io/badge/Governed_by-AgentGuard-green?style=for-the-badge)](https://github.com/AgentGuardHQ/agentguard)
+[![Chitin](https://img.shields.io/badge/Governed_by-Chitin-green?style=for-the-badge)](https://github.com/chitinhq/chitin)
 
 *Interactive pair-programming with local models + autonomous multi-task execution — with governance on every tool call.*
 
-[Website](https://agentguardhq.github.io/shellforge) · [Docs](docs/architecture.md) · [Roadmap](docs/roadmap.md) · [AgentGuard](https://github.com/AgentGuardHQ/agentguard)
+[Docs](docs/architecture.md) · [Roadmap](docs/roadmap.md) · [Chitin](https://github.com/chitinhq/chitin)
 
 <img src="https://github.com/user-attachments/assets/a94a8a5e-dfeb-4771-a6ab-465d3c2f01f0" alt="ShellForge — Local Governed Agent Runtime" width="700">
 
@@ -24,11 +23,11 @@
 ### 1. Install ShellForge
 
 ```bash
-brew tap AgentGuardHQ/tap
+brew tap chitinhq/tap
 brew install shellforge
 ```
 
-Or from source: `git clone https://github.com/AgentGuardHQ/shellforge.git && cd shellforge && go build -o shellforge ./cmd/shellforge/`
+Or from source: `git clone https://github.com/chitinhq/shellforge.git && cd shellforge && go build -o shellforge ./cmd/shellforge/`
 
 ### 2. Install Ollama (if you haven't already)
 
@@ -82,12 +81,12 @@ Two modes:
 1. **Interactive REPL** (`shellforge chat`) — pair-program with a local or cloud model. Persistent conversation history, shell escapes, color output.
 2. **Autonomous agents** (`shellforge agent`, `shellforge ralph`) — one-shot tasks or multi-task loops with automatic validation and commit.
 
-Both modes share the same governance layer. Every tool call passes through [AgentGuard](https://github.com/AgentGuardHQ/agentguard) policy enforcement before execution.
+Both modes share the same governance layer. Every tool call passes through [Chitin](https://github.com/chitinhq/chitin) policy enforcement before execution.
 
 ```
 You (chat) or Octi Pulpo (dispatch)
   → ShellForge Agent Loop (tool calling, drift detection)
-    → AgentGuard Governance (allow / deny / correct)
+    → Chitin Governance (allow / deny / correct)
       → Your Environment (files, shell, git)
 ```
 
@@ -134,16 +133,16 @@ Tasks come from a JSON file or Octi Pulpo MCP dispatch. Failed validations skip
 | **Infer** | [Ollama](https://ollama.com) | Local LLM inference (Metal GPU on Mac) |
 | **Optimize** | [RTK](https://github.com/rtk-ai/rtk) | Token compression — 70-90% reduction on shell output |
 | **Execute** | [Goose](https://block.github.io/goose) | AI coding agent with native Ollama support (headless) |
-| **Coordinate** | [Octi Pulpo](https://github.com/AgentGuardHQ/octi-pulpo) | Budget-aware dispatch, episodic memory, model cascading |
-| **Govern** | [AgentGuard](https://github.com/AgentGuardHQ/agentguard) | Policy enforcement on every action — allow/deny/correct |
+| **Coordinate** | [Octi Pulpo](https://github.com/chitinhq/octi) | Budget-aware dispatch, episodic memory, model cascading |
+| **Govern** | [Chitin](https://github.com/chitinhq/chitin) | Policy enforcement on every action — allow/deny/correct |
 | **Sandbox** | [OpenShell](https://github.com/NVIDIA/OpenShell) | Kernel-level isolation (Docker on macOS) |
 | **Scan** | [DefenseClaw](https://github.com/cisco-ai-defense/defenseclaw) | Supply chain scanner — AI Bill of Materials |
 
 ```bash
 shellforge status
 # Ollama        running (qwen3:30b loaded)
 # RTK           v0.4.2
-# AgentGuard    enforce mode (5 rules)
+# Chitin        enforce mode (5 rules)
 # Octi Pulpo    connected (http://localhost:8080)
 # OpenShell     Docker sandbox active
 # DefenseClaw   scanner ready
@@ -193,7 +192,7 @@ The agent loop (used by `chat`, `agent`, and `ralph`) has 8 built-in tools, all
 
 ## Multi-Driver Governance
 
-ShellForge governs any CLI agent driver via AgentGuard hooks. Each driver keeps its own model and agent loop — ShellForge ensures governance is active and spawns the driver as a subprocess.
+ShellForge governs any CLI agent driver via Chitin hooks. Each driver keeps its own model and agent loop — ShellForge ensures governance is active and spawns the driver as a subprocess.
 
 ```bash
 # Run any driver with governance
@@ -235,7 +234,7 @@ See `dags/multi-driver-swarm.yaml` and `dags/workspace-swarm.yaml` for examples.
 └────────────────────┬──────────────────────────────┘
                      │ tool call
           ═══════════╪═══════════
-          ║  AgentGuard          ║
+          ║  Chitin              ║
           ║  Governance Kernel   ║
           ║  allow · deny · audit║
           ║  every. single. call.║
@@ -253,7 +252,7 @@ See `dags/multi-driver-swarm.yaml` and `dags/workspace-swarm.yaml` for examples.
 
 ## Governance
 
-ShellForge's core value. Every tool call passes through `agentguard.yaml` before execution.
+ShellForge's core value. Every tool call passes through `chitin.yaml` before execution.
 
 ```yaml
 # agentguard.yaml — policy-as-code for every agent action
@@ -337,11 +336,10 @@ agents:
 | Project | Role | What It Does |
 |---------|------|--------------|
 | **ShellForge** | Orchestration | Governed agent runtime — CLI drivers + OpenClaw + local models |
-| [**Octi Pulpo**](https://github.com/AgentGuardHQ/octi-pulpo) | Coordination | Swarm brain — shared memory, model routing, budget-aware dispatch |
-| [**AgentGuard**](https://github.com/AgentGuardHQ/agentguard) | Governance | Policy enforcement, telemetry, invariants — on every tool call |
-| [**AgentGuard Cloud**](https://github.com/AgentGuardHQ/agentguard-cloud) | Observability | SaaS dashboard — session replay, compliance, analytics |
+| [**Octi Pulpo**](https://github.com/chitinhq/octi) | Coordination | Swarm brain — shared memory, model routing, budget-aware dispatch |
+| [**Chitin**](https://github.com/chitinhq/chitin) | Governance | Policy enforcement, telemetry, invariants — on every tool call |
 
-ShellForge orchestrates. Octi Pulpo coordinates. AgentGuard governs.
+ShellForge orchestrates. Octi Pulpo coordinates. Chitin governs.
 
 ### Supported Runtimes
 
@@ -368,7 +366,7 @@ See [docs/roadmap.md](docs/roadmap.md) for what's planned.
 
 <div align="center">
 
-**[Website](https://agentguardhq.github.io/shellforge)** · **[Star on GitHub](https://github.com/AgentGuardHQ/shellforge)** · **[AgentGuard](https://github.com/AgentGuardHQ/agentguard)**
+**[Star on GitHub](https://github.com/chitinhq/shellforge)** · **[Chitin](https://github.com/chitinhq/chitin)**
 
 *Built by humans and agents*
 

bench/agent.py

@@ -46,7 +46,7 @@ def install(self) -> None:
         # Clone and build ShellForge
         self.exec_as_agent(
             "cd /tmp &&"
-            " git clone --depth 1 https://github.com/AgentGuardHQ/shellforge.git &&"
+            " git clone --depth 1 https://github.com/chitinhq/shellforge.git &&"
             " cd shellforge &&"
             " go build -o /usr/local/bin/shellforge ./cmd/shellforge/"
         )

cmd/shellforge/main.go

@@ -16,14 +16,14 @@ import (
 "strings"
 "time"
 
-"github.com/AgentGuardHQ/shellforge/internal/agent"
-"github.com/AgentGuardHQ/shellforge/internal/governance"
-"github.com/AgentGuardHQ/shellforge/internal/llm"
-"github.com/AgentGuardHQ/shellforge/internal/logger"
-"github.com/AgentGuardHQ/shellforge/internal/ollama"
-"github.com/AgentGuardHQ/shellforge/internal/ralph"
-"github.com/AgentGuardHQ/shellforge/internal/repl"
-"github.com/AgentGuardHQ/shellforge/internal/scheduler"
+"github.com/chitinhq/shellforge/internal/agent"
+"github.com/chitinhq/shellforge/internal/governance"
+"github.com/chitinhq/shellforge/internal/llm"
+"github.com/chitinhq/shellforge/internal/logger"
+"github.com/chitinhq/shellforge/internal/ollama"
+"github.com/chitinhq/shellforge/internal/ralph"
+"github.com/chitinhq/shellforge/internal/repl"
+"github.com/chitinhq/shellforge/internal/scheduler"
 )
 
 var version = "0.4.8"

cmd/shellforge/status.go

@@ -5,8 +5,8 @@ import (
 	"os/exec"
 	"strings"
 
-	"github.com/AgentGuardHQ/shellforge/internal/governance"
-	"github.com/AgentGuardHQ/shellforge/internal/ollama"
+	"github.com/chitinhq/shellforge/internal/governance"
+	"github.com/chitinhq/shellforge/internal/ollama"
 )
 
 func cmdStatusFull() {

docs/architecture.md

@@ -144,8 +144,8 @@ Octi Pulpo routes tasks to the cheapest capable driver:
 | **Infer** | [Ollama](https://ollama.com) | Local LLM inference (Metal GPU on Mac) |
 | **Optimize** | [RTK](https://github.com/rtk-ai/rtk) | Token compression — 70-90% reduction on shell output |
 | **Execute** | [Goose](https://block.github.io/goose) / [OpenClaw](https://github.com/openclaw/openclaw) | Agent execution + browser automation |
-| **Coordinate** | [Octi Pulpo](https://github.com/AgentGuardHQ/octi-pulpo) | Budget-aware dispatch, episodic memory, model cascading |
-| **Govern** | [AgentGuard](https://github.com/AgentGuardHQ/agentguard) | Policy enforcement on every action |
+| **Coordinate** | [Octi Pulpo](https://github.com/chitinhq/octi) | Budget-aware dispatch, episodic memory, model cascading |
+| **Govern** | [Chitin](https://github.com/chitinhq/chitin) | Policy enforcement on every action |
 | **Sandbox** | [OpenShell](https://github.com/NVIDIA/OpenShell) | Kernel-level isolation (Docker on macOS) |
 | **Scan** | [DefenseClaw](https://github.com/cisco-ai-defense/defenseclaw) | Supply chain scanner — AI Bill of Materials |
 

docs/index.html

@@ -391,7 +391,7 @@
       <li><a href="#stack">Stack</a></li>
       <li><a href="#agents">Agents</a></li>
       <li><a href="#ecosystem">Ecosystem</a></li>
-      <li><a href="https://github.com/AgentGuardHQ/shellforge">GitHub</a></li>
+      <li><a href="https://github.com/chitinhq/shellforge">GitHub</a></li>
     </ul>
   </div>
 </nav>
@@ -412,7 +412,7 @@ <h1>
     </p>
     <div class="hero-badge">Open Source · MIT License · <strong>macOS · Linux · Any GPU</strong></div>
     <div class="hero-actions">
-      <a href="https://github.com/AgentGuardHQ/shellforge" class="btn btn-primary">
+      <a href="https://github.com/chitinhq/shellforge" class="btn btn-primary">
         ⭐ Star on GitHub
       </a>
       <a href="#quickstart" class="btn btn-secondary">
@@ -427,7 +427,7 @@ <h1>
         <div class="terminal-dot g"></div>
       </div>
       <div class="terminal-code">
-        <span class="prompt">$</span> <span class="cmd">brew tap AgentGuardHQ/tap</span><br>
+        <span class="prompt">$</span> <span class="cmd">brew tap chitinhq/tap</span><br>
         <span class="prompt">$</span> <span class="cmd">brew install shellforge</span><br>
         <span class="prompt">$</span> <span class="cmd">shellforge setup</span><br>
         <span class="output">── Step 1/6: Ollama ──</span><br>
@@ -715,10 +715,10 @@ <h4>OpenShell</h4>
     </div>
 
     <p class="teaser-text">
-      <strong>Goose</strong> executes. <strong>AgentGuard</strong> governs. <strong>Ollama</strong> infers.<br>
+      <strong>Goose</strong> executes. <strong>Chitin</strong> governs. <strong>Ollama</strong> infers.<br>
       <strong>RTK</strong> compresses. <strong>Dagu</strong> orchestrates. <strong>OpenShell</strong> sandboxes.<br><br>
       All open source. All local. All on your Mac.<br><br>
-      <em><a href="https://github.com/AgentGuardHQ/shellforge">Star the repo</a> to follow along.</em>
+      <em><a href="https://github.com/chitinhq/shellforge">Star the repo</a> to follow along.</em>
     </p>
   </div>
 </section>
@@ -729,18 +729,18 @@ <h4>OpenShell</h4>
     <h2>Get Started in 60 Seconds</h2>
     <p>Install. Setup. Forge.</p>
     <div class="cta-code" style="text-align: left; line-height: 2;">
-      <span class="prompt">$</span> brew tap AgentGuardHQ/tap<br>
+      <span class="prompt">$</span> brew tap chitinhq/tap<br>
       <span class="prompt">$</span> brew install shellforge<br>
       <span class="prompt">$</span> shellforge setup<br>
       <span class="prompt">$</span> shellforge agent "analyze this repo for test gaps"
     </div>
     <br><br>
     <div class="hero-actions">
-      <a href="https://github.com/AgentGuardHQ/shellforge" class="btn btn-primary">
+      <a href="https://github.com/chitinhq/shellforge" class="btn btn-primary">
         View on GitHub
       </a>
-      <a href="https://github.com/AgentGuardHQ/agentguard" class="btn btn-secondary">
-        AgentGuard Core →
+      <a href="https://github.com/chitinhq/chitin" class="btn btn-secondary">
+        Chitin Core →
       </a>
     </div>
   </div>
@@ -749,7 +749,7 @@ <h2>Get Started in 60 Seconds</h2>
 <footer>
   <div class="container">
     <p>
-      Built by <a href="https://github.com/AgentGuardHQ">AgentGuard</a> ·
+      Built by <a href="https://github.com/chitinhq">Chitin</a> ·
       Open Source · MIT License ·
       Made with 🔥 by humans and agents
     </p>

docs/roadmap.md

@@ -129,10 +129,9 @@ ShellForge orchestrates, Octi Pulpo coordinates, AgentGuard governs. This phase
 - [ ] Leaderboard submission
 
 ### Phase 10 — Production Hardening
-- [ ] AgentGuard Go kernel integration (in-process, not subprocess)
-- [ ] Publish Go module (`github.com/AgentGuardHQ/agentguard/go/pkg/hook`)
+- [ ] Chitin Go kernel integration (in-process, not subprocess)
+- [ ] Publish Go module (`github.com/chitinhq/chitin/go/pkg/hook`)
 - [ ] Move `internal/` types to `pkg/` for external import
-- [ ] Cloud telemetry opt-in (AgentGuard Cloud)
 
 ### Phase 11 — Replace Workspace Bash Swarm ✅ DONE
 - [x] Migrated to API-driven dispatch: Octi Pulpo → ShellForge → Anthropic API
@@ -147,13 +146,13 @@ Bugs identified during v0.6.x development. Fix before v1.0.
 
 | Issue | Package | Severity | Description |
 |-------|---------|----------|-------------|
-| [#69](https://github.com/AgentGuardHQ/shellforge/issues/69) | `agentguard.yaml` | High | Governance gap: plain `rm` and `rm -r` bypass `no-destructive-rm` policy |
-| [#67](https://github.com/AgentGuardHQ/shellforge/issues/67) | `scripts/govern-shell.sh` | Medium | Fragile `sed`-based JSON parsing — denial reason extraction can fail or corrupt |
-| [#65](https://github.com/AgentGuardHQ/shellforge/issues/65) | `internal/scheduler` | Medium | `os.WriteFile` error silently ignored — audit log loss |
-| [#63](https://github.com/AgentGuardHQ/shellforge/issues/63) | `internal/normalizer` | Medium | `classifyShellRisk` prefix match too broad — `catalog_tool` classified as read-only |
-| [#62](https://github.com/AgentGuardHQ/shellforge/issues/62) | `cmd/shellforge` | Medium | `cmdEvaluate` ignores JSON unmarshal error — malformed input defaults to allow |
-| [#61](https://github.com/AgentGuardHQ/shellforge/issues/61) | `internal/intent` | Low | Dead code in `flattenParams` — first assignment immediately overwritten |
-| [#60](https://github.com/AgentGuardHQ/shellforge/issues/60) | all packages | High | Zero test coverage — critical for a governance runtime |
+| [#69](https://github.com/chitinhq/shellforge/issues/69) | `agentguard.yaml` | High | Governance gap: plain `rm` and `rm -r` bypass `no-destructive-rm` policy |
+| [#67](https://github.com/chitinhq/shellforge/issues/67) | `scripts/govern-shell.sh` | Medium | Fragile `sed`-based JSON parsing — denial reason extraction can fail or corrupt |
+| [#65](https://github.com/chitinhq/shellforge/issues/65) | `internal/scheduler` | Medium | `os.WriteFile` error silently ignored — audit log loss |
+| [#63](https://github.com/chitinhq/shellforge/issues/63) | `internal/normalizer` | Medium | `classifyShellRisk` prefix match too broad — `catalog_tool` classified as read-only |
+| [#62](https://github.com/chitinhq/shellforge/issues/62) | `cmd/shellforge` | Medium | `cmdEvaluate` ignores JSON unmarshal error — malformed input defaults to allow |
+| [#61](https://github.com/chitinhq/shellforge/issues/61) | `internal/intent` | Low | Dead code in `flattenParams` — first assignment immediately overwritten |
+| [#60](https://github.com/chitinhq/shellforge/issues/60) | all packages | High | Zero test coverage — critical for a governance runtime |
 
 ---