Migrate from Amp to Tabnine CLI

AGENTS.md

@@ -2,7 +2,7 @@
 
 ## Overview
 
-Ralph is an autonomous AI agent loop that runs Amp repeatedly until all PRD items are complete. Each iteration is a fresh Amp instance with clean context.
+Ralph-tabnine is an autonomous AI agent loop that runs Tabnine CLI repeatedly until all PRD items are complete. Each iteration is a fresh Tabnine CLI instance with clean context.
 
 ## Commands
 
@@ -19,8 +19,8 @@ cd flowchart && npm run build
 
 ## Key Files
 
-- `ralph.sh` - The bash loop that spawns fresh Amp instances
-- `prompt.md` - Instructions given to each Amp instance
+- `ralph.sh` - The bash loop that spawns fresh Tabnine CLI instances
+- `prompt.md` - Instructions given to each Tabnine CLI instance
 - `prd.json.example` - Example PRD format
 - `flowchart/` - Interactive React Flow diagram explaining how Ralph works
 
@@ -37,7 +37,7 @@ npm run dev
 
 ## Patterns
 
-- Each iteration spawns a fresh Amp instance with clean context
+- Each iteration spawns a fresh Tabnine CLI instance with clean context
 - Memory persists via git history, `progress.txt`, and `prd.json`
 - Stories should be small enough to complete in one context window
 - Always update AGENTS.md with discovered patterns for future iterations

README.md

@@ -2,21 +2,21 @@
 
 ![Ralph](ralph.webp)
 
-Ralph is an autonomous AI agent loop that runs [Amp](https://ampcode.com) repeatedly until all PRD items are complete. Each iteration is a fresh Amp instance with clean context. Memory persists via git history, `progress.txt`, and `prd.json`.
+Ralph is an autonomous AI agent loop that runs [Tabnine CLI](https://github.com/codota/tabnine-cli/) repeatedly until all PRD items are complete. Each iteration is a fresh Tabnine CLI instance with clean context. Memory persists via git history, `progress.txt`, and `prd.json`.
 
-Based on [Geoffrey Huntley's Ralph pattern](https://ghuntley.com/ralph/).
+Tabnine CLI is a Gemini-based AI coding assistant that provides similar capabilities to Anthropic's Claude.
 
-[Read my in-depth article on how I use Ralph](https://x.com/ryancarson/status/2008548371712135632)
+Based on [Geoffrey Huntley's Ralph pattern](https://ghuntley.com/ralph/).
 
 ## Prerequisites
 
-- [Amp CLI](https://ampcode.com) installed and authenticated
+- [Tabnine CLI](https://github.com/codota/tabnine-cli/) installed and authenticated
 - `jq` installed (`brew install jq` on macOS)
 - A git repository for your project
 
 ## Setup
 
-### Option 1: Copy to your project
+### Copy to your project
 
 Copy the ralph files into your project:
 
@@ -28,46 +28,17 @@ cp /path/to/ralph/prompt.md scripts/ralph/
 chmod +x scripts/ralph/ralph.sh
 ```
 
-### Option 2: Install skills globally
-
-Copy the skills to your Amp config for use across all projects:
-
-```bash
-cp -r skills/prd ~/.config/amp/skills/
-cp -r skills/ralph ~/.config/amp/skills/
-```
-
-### Configure Amp auto-handoff (recommended)
-
-Add to `~/.config/amp/settings.json`:
-
-```json
-{
-  "amp.experimental.autoHandoff": { "context": 90 }
-}
-```
-
-This enables automatic handoff when context fills up, allowing Ralph to handle large stories that exceed a single context window.
-
 ## Workflow
 
 ### 1. Create a PRD
 
-Use the PRD skill to generate a detailed requirements document:
+Create a detailed requirements document manually or with assistance from Tabnine CLI. See `skills/prd/SKILL.md` for guidelines on creating effective PRDs.
 
-```
-Load the prd skill and create a PRD for [your feature description]
-```
-
-Answer the clarifying questions. The skill saves output to `tasks/prd-[feature-name].md`.
+Save the PRD as `tasks/prd-[feature-name].md`.
 
 ### 2. Convert PRD to Ralph format
 
-Use the Ralph skill to convert the markdown PRD to JSON:
-
-```
-Load the ralph skill and convert tasks/prd-[feature-name].md to prd.json
-```
+Convert the markdown PRD to JSON format using the guidelines in `skills/ralph/SKILL.md`. You can ask Tabnine CLI to help with this conversion.
 
 This creates `prd.json` with user stories structured for autonomous execution.
 
@@ -93,13 +64,13 @@ Ralph will:
 
 | File | Purpose |
 |------|---------|
-| `ralph.sh` | The bash loop that spawns fresh Amp instances |
-| `prompt.md` | Instructions given to each Amp instance |
+| `ralph.sh` | The bash loop that spawns fresh Tabnine CLI instances |
+| `prompt.md` | Instructions given to each Tabnine CLI instance |
 | `prd.json` | User stories with `passes` status (the task list) |
 | `prd.json.example` | Example PRD format for reference |
 | `progress.txt` | Append-only learnings for future iterations |
-| `skills/prd/` | Skill for generating PRDs |
-| `skills/ralph/` | Skill for converting PRDs to JSON |
+| `skills/prd/` | Guidelines for creating PRDs |
+| `skills/ralph/` | Guidelines for converting PRDs to JSON |
 | `flowchart/` | Interactive visualization of how Ralph works |
 
 ## Flowchart
@@ -120,7 +91,7 @@ npm run dev
 
 ### Each Iteration = Fresh Context
 
-Each iteration spawns a **new Amp instance** with clean context. The only memory between iterations is:
+Each iteration spawns a **new Tabnine CLI instance** with clean context. The only memory between iterations is:
 - Git history (commits from previous iterations)
 - `progress.txt` (learnings and context)
 - `prd.json` (which stories are done)
@@ -142,7 +113,7 @@ Too big (split these):
 
 ### AGENTS.md Updates Are Critical
 
-After each iteration, Ralph updates the relevant `AGENTS.md` files with learnings. This is key because Amp automatically reads these files, so future iterations (and future human developers) benefit from discovered patterns, gotchas, and conventions.
+After each iteration, Ralph updates the relevant `AGENTS.md` files with learnings. These files provide context for future iterations and human developers about discovered patterns, gotchas, and conventions.
 
 Examples of what to add to AGENTS.md:
 - Patterns discovered ("this codebase uses X for Y")
@@ -158,7 +129,7 @@ Ralph only works if there are feedback loops:
 
 ### Browser Verification for UI Stories
 
-Frontend stories must include "Verify in browser using dev-browser skill" in acceptance criteria. Ralph will use the dev-browser skill to navigate to the page, interact with the UI, and confirm changes work.
+Frontend stories should include manual browser verification in acceptance criteria. After Ralph implements UI changes, verify the changes work as expected in the browser.
 
 ### Stop Condition
 
@@ -193,4 +164,4 @@ Ralph automatically archives previous runs when you start a new feature (differe
 ## References
 
 - [Geoffrey Huntley's Ralph article](https://ghuntley.com/ralph/)
-- [Amp documentation](https://ampcode.com/manual)
+- [Tabnine CLI](https://github.com/codota/tabnine-cli/)

flowchart/README.md

@@ -1,73 +1,20 @@
-# React + TypeScript + Vite
+# Ralph Flowchart
 
-This template provides a minimal setup to get React working in Vite with HMR and some ESLint rules.
+Interactive visualization showing how Ralph works with Tabnine CLI.
 
-Currently, two official plugins are available:
+Built with React Flow for presentations - click through to reveal each step with animations.
 
-- [@vitejs/plugin-react](https://github.com/vitejs/vite-plugin-react/blob/main/packages/plugin-react) uses [Babel](https://babeljs.io/) (or [oxc](https://oxc.rs) when used in [rolldown-vite](https://vite.dev/guide/rolldown)) for Fast Refresh
-- [@vitejs/plugin-react-swc](https://github.com/vitejs/vite-plugin-react/blob/main/packages/plugin-react-swc) uses [SWC](https://swc.rs/) for Fast Refresh
+## Development
 
-## React Compiler
-
-The React Compiler is not enabled on this template because of its impact on dev & build performances. To add it, see [this documentation](https://react.dev/learn/react-compiler/installation).
-
-## Expanding the ESLint configuration
-
-If you are developing a production application, we recommend updating the configuration to enable type-aware lint rules:
-
-```js
-export default defineConfig([
-  globalIgnores(['dist']),
-  {
-    files: ['**/*.{ts,tsx}'],
-    extends: [
-      // Other configs...
-
-      // Remove tseslint.configs.recommended and replace with this
-      tseslint.configs.recommendedTypeChecked,
-      // Alternatively, use this for stricter rules
-      tseslint.configs.strictTypeChecked,
-      // Optionally, add this for stylistic rules
-      tseslint.configs.stylisticTypeChecked,
-
-      // Other configs...
-    ],
-    languageOptions: {
-      parserOptions: {
-        project: ['./tsconfig.node.json', './tsconfig.app.json'],
-        tsconfigRootDir: import.meta.dirname,
-      },
-      // other options...
-    },
-  },
-])
+```bash
+npm install
+npm run dev
 ```
 
-You can also install [eslint-plugin-react-x](https://github.com/Rel1cx/eslint-react/tree/main/packages/plugins/eslint-plugin-react-x) and [eslint-plugin-react-dom](https://github.com/Rel1cx/eslint-react/tree/main/packages/plugins/eslint-plugin-react-dom) for React-specific lint rules:
+## Build
 
-```js
-// eslint.config.js
-import reactX from 'eslint-plugin-react-x'
-import reactDom from 'eslint-plugin-react-dom'
-
-export default defineConfig([
-  globalIgnores(['dist']),
-  {
-    files: ['**/*.{ts,tsx}'],
-    extends: [
-      // Other configs...
-      // Enable lint rules for React
-      reactX.configs['recommended-typescript'],
-      // Enable lint rules for React DOM
-      reactDom.configs.recommended,
-    ],
-    languageOptions: {
-      parserOptions: {
-        project: ['./tsconfig.node.json', './tsconfig.app.json'],
-        tsconfigRootDir: import.meta.dirname,
-      },
-      // other options...
-    },
-  },
-])
+```bash
+npm run build
 ```
+
+The build output goes to `dist/` and is deployed to GitHub Pages.

flowchart/index.html

@@ -4,7 +4,7 @@
     <meta charset="UTF-8" />
     <link rel="icon" type="image/svg+xml" href="/vite.svg" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-    <title>How Ralph Works with Amp</title>
+    <title>How Ralph Works with Tabnine CLI</title>
   </head>
   <body>
     <div id="root"></div>

flowchart/src/App.tsx

@@ -40,7 +40,7 @@ const allSteps: { id: string; label: string; description: string; phase: Phase }
   { id: '2', label: 'Convert to prd.json', description: 'Break into small user stories', phase: 'setup' },
   { id: '3', label: 'Run ralph.sh', description: 'Starts the autonomous loop', phase: 'setup' },
   // Loop phase
-  { id: '4', label: 'Amp picks a story', description: 'Finds next passes: false', phase: 'loop' },
+  { id: '4', label: 'Tabnine CLI picks a story', description: 'Finds next passes: false', phase: 'loop' },
   { id: '5', label: 'Implements it', description: 'Writes code, runs tests', phase: 'loop' },
   { id: '6', label: 'Commits changes', description: 'If tests pass', phase: 'loop' },
   { id: '7', label: 'Updates prd.json', description: 'Sets passes: true', phase: 'loop' },
@@ -325,7 +325,7 @@ function App() {
   return (
     <div className="app-container">
       <div className="header">
-        <h1>How Ralph Works with Amp</h1>
+        <h1>How Ralph Works with Tabnine CLI</h1>
         <p>Autonomous AI agent loop for completing PRDs</p>
       </div>
       <div className="flow-container">

prd.json.example

@@ -24,7 +24,7 @@
         "Each task card shows colored priority badge (red=high, yellow=medium, gray=low)",
         "Priority visible without hovering or clicking",
         "Typecheck passes",
-        "Verify in browser using dev-browser skill"
+        "Verify in browser"
       ],
       "priority": 2,
       "passes": false,
@@ -39,7 +39,7 @@
         "Shows current priority as selected",
         "Saves immediately on selection change",
         "Typecheck passes",
-        "Verify in browser using dev-browser skill"
+        "Verify in browser"
       ],
       "priority": 3,
       "passes": false,
@@ -54,7 +54,7 @@
         "Filter persists in URL params",
         "Empty state message when no tasks match filter",
         "Typecheck passes",
-        "Verify in browser using dev-browser skill"
+        "Verify in browser"
       ],
       "priority": 4,
       "passes": false,

prompt.md

@@ -20,7 +20,6 @@ You are an autonomous coding agent working on a software project.
 APPEND to progress.txt (never replace, always append):
 ```
 ## [Date/Time] - [Story ID]
-Thread: https://ampcode.com/threads/$AMP_CURRENT_THREAD_ID
 - What was implemented
 - Files changed
 - **Learnings for future iterations:**
@@ -30,8 +29,6 @@ Thread: https://ampcode.com/threads/$AMP_CURRENT_THREAD_ID
 ---
 ```
 
-Include the thread URL so future iterations can use the `read_thread` tool to reference previous work if needed.
-
 The learnings section is critical - it helps future iterations avoid repeating mistakes and understand the codebase better.
 
 ## Consolidate Patterns
@@ -82,14 +79,9 @@ Only update AGENTS.md if you have **genuinely reusable knowledge** that would he
 
 ## Browser Testing (Required for Frontend Stories)
 
-For any story that changes UI, you MUST verify it works in the browser:
-
-1. Load the `dev-browser` skill
-2. Navigate to the relevant page
-3. Verify the UI changes work as expected
-4. Take a screenshot if helpful for the progress log
+For any story that changes UI, you should manually verify it works in the browser after implementation. Document verification results in the progress log.
 
-A frontend story is NOT complete until browser verification passes.
+A frontend story is NOT complete until verification passes.
 
 ## Stop Condition
 

ralph.sh

@@ -59,8 +59,8 @@ for i in $(seq 1 $MAX_ITERATIONS); do
   echo "  Ralph Iteration $i of $MAX_ITERATIONS"
   echo "═══════════════════════════════════════════════════════"
 
-  # Run amp with the ralph prompt
-  OUTPUT=$(cat "$SCRIPT_DIR/prompt.md" | amp --dangerously-allow-all 2>&1 | tee /dev/stderr) || true
+  # Run tabnine with the ralph prompt
+  OUTPUT=$(cat "$SCRIPT_DIR/prompt.md" | tabnine --yolo 2>&1 | tee /dev/stderr) || true
 
   # Check for completion signal
   if echo "$OUTPUT" | grep -q "<promise>COMPLETE</promise>"; then

skills/prd/SKILL.md

@@ -87,7 +87,7 @@ Each story should be small enough to implement in one focused session.
 
 **Important:** 
 - Acceptance criteria must be verifiable, not vague. "Works correctly" is bad. "Button shows confirmation dialog before deleting" is good.
-- **For any story with UI changes:** Always include "Verify in browser using dev-browser skill" as acceptance criteria. This ensures visual verification of frontend work.
+- **For any story with UI changes:** Always include "Verify in browser" as acceptance criteria. This ensures visual verification of frontend work.
 
 ### 4. Functional Requirements
 Numbered list of specific functionalities:
@@ -172,7 +172,7 @@ Add priority levels to tasks so users can focus on what matters most. Tasks can
 - [ ] Each task card shows colored priority badge (red=high, yellow=medium, gray=low)
 - [ ] Priority visible without hovering or clicking
 - [ ] Typecheck passes
-- [ ] Verify in browser using dev-browser skill
+- [ ] Verify in browser
 
 ### US-003: Add priority selector to task edit
 **Description:** As a user, I want to change a task's priority when editing it.
@@ -182,7 +182,7 @@ Add priority levels to tasks so users can focus on what matters most. Tasks can
 - [ ] Shows current priority as selected
 - [ ] Saves immediately on selection change
 - [ ] Typecheck passes
-- [ ] Verify in browser using dev-browser skill
+- [ ] Verify in browser
 
 ### US-004: Filter tasks by priority
 **Description:** As a user, I want to filter the task list to see only high-priority items when I'm focused.
@@ -192,7 +192,7 @@ Add priority levels to tasks so users can focus on what matters most. Tasks can
 - [ ] Filter persists in URL params
 - [ ] Empty state message when no tasks match filter
 - [ ] Typecheck passes
-- [ ] Verify in browser using dev-browser skill
+- [ ] Verify in browser
 
 ## Functional Requirements