> ## Documentation Index > Fetch the complete documentation index at: https://repr.dev/docs/llms.txt > Use this file to discover all available pages before exploring further. # repr generate > Generate stories from commits The `generate` command is the core of repr. It analyzes your git history and uses an LLM to write stories—turning raw commits into professional narratives. ## Usage ```bash theme={null} repr generate [OPTIONS] ``` ## Options | Option | Description | Default | | ------------------------- | ------------------------------------------------------------------------------ | ----------------------- | | `--local`, `-l` | Use local LLM (Ollama/LocalAI) | Auto (if not signed in) | | `--cloud` | Use cloud LLM (requires login) | Auto (if signed in) | | `--template `, `-t` | Template: `resume`, `changelog`, `narrative`, `interview` | `resume` | | `--repo ` | Only generate for specific repository | All tracked repos | | `--commits ` | Comma-separated commit SHAs to generate from | Recent commits | | `--since ` | Generate from commits since date (e.g., `2024-01-01`, `monday`, `2 weeks ago`) | - | | `--days ` | Generate from commits in the last N days | 90 | | `--batch-size ` | Number of commits to group into one story | 5 | | `--dry-run` | Preview what would be sent without saving | - | | `--prompt `, `-p` | Append custom instructions to the LLM | - | ## How It Works 1. **Selects commits** - From specific SHAs (`--commits`), a timeframe (`--since`, `--days`), or defaults to last 90 days 2. **Analyzes changes** - Reads diffs to understand what actually changed 3. **Generates narrative** - LLM writes a story using your chosen template 4. **Saves locally** - Story saved to `~/.repr/stories/.md` All generation happens locally by default. Diffs never leave your machine unless you use `--cloud`. ## Examples ### Basic Generation Generate using local LLM: ```bash theme={null} repr generate --local ``` Output: ```text theme={null} Generating stories (local LLM)... myproject • Built OAuth2 integration with Google and GitHub providers • Implemented Redis caching layer for session management • Fixed race condition in authentication flow Generated 3 stories Stories saved to: ~/.repr/stories ``` ### Use a Specific Template Generate interview-ready stories with STAR format: ```bash theme={null} repr generate --template interview --local ``` This creates stories structured as: * **Situation:** Context and problem * **Task:** What needed to be done * **Action:** How you solved it * **Result:** Measurable impact Perfect for behavioral interviews. ### Generate from a Specific Timeframe Control the time range for commit selection: ```bash theme={null} # Last 30 days repr generate --days 30 --local # Since a specific date repr generate --since 2024-01-01 --local # Natural language dates repr generate --since "2 weeks ago" --local repr generate --since monday --local repr generate --since "last month" --local ``` Supported date formats: * **ISO dates**: `2024-01-01`, `2024-06-15` * **Day names**: `monday`, `tuesday`, etc. (previous occurrence) * **Relative**: `3 days ago`, `2 weeks ago`, `1 month ago` * **Keywords**: `yesterday`, `today`, `last week`, `last month` ### Generate from Specific Commits Target exact commits instead of using recent history: ```bash theme={null} # List commits to find SHAs repr commits --limit 20 # Generate from selected commits repr generate --commits abc1234,def5678,ghi9012 --local ``` ### Generate for One Project Focus on a single repository: ```bash theme={null} repr generate --repo ~/code/important-project --template resume ``` ### Add Custom Context Guide the LLM with additional instructions: ```bash theme={null} repr generate --local --prompt "Focus on performance optimizations and scalability improvements" ``` This appends your instructions to the system prompt, influencing how the LLM writes your stories. ### Preview Before Generating See what would be sent to the LLM without actually generating: ```bash theme={null} repr generate --dry-run ``` Output: ```text theme={null} Dry Run Preview Commits to analyze: 23 Template: resume Estimated tokens: ~45,000 Sample commits: • abc1234 Implement user authentication • def5678 Add Redis caching • ghi9012 Fix session timeout bug ... and 20 more ``` Useful for checking token limits before expensive cloud generation. ## Templates Comparison | Template | Best For | Style | Example | | ----------- | ------------------------------- | ------------------------------------------ | ------------------------------------------- | | `resume` | Portfolios, performance reviews | Action verbs, impact-focused | "Optimized database queries by 40%..." | | `changelog` | Release notes, sprint summaries | Categorized bullets (Added/Fixed/Changed) | "Fixed: Race condition in auth flow" | | `narrative` | Blog posts, case studies | Storytelling, problem-solving journey | "We started by identifying a bottleneck..." | | `interview` | Job interviews, promotions | STAR format (Situation/Task/Action/Result) | "**Result:** Reduced failures by 60%" | ## Batch Sizes The `--batch-size` option controls how many commits are grouped into one story: * **Small (3-5)**: More stories, focused scope. Good for daily/weekly reviews. * **Medium (5-10)**: Balanced. Good for feature work. * **Large (10-20)**: Comprehensive stories. Good for project summaries. ```bash theme={null} # Daily micro-stories repr generate --batch-size 3 --local # Big-picture project narrative repr generate --batch-size 15 --template narrative --local ``` ## Privacy Modes ### Local-Only (Maximum Privacy) ```bash theme={null} repr generate --local ``` * ✅ Diffs processed by local LLM (Ollama/LocalAI) * ✅ Zero data leaves your machine * ✅ Works in air-gapped environments * ✅ Free, no API costs ### Cloud (Managed) ```bash theme={null} repr generate --cloud ``` * ⚠️ Requires `repr login` * ⚠️ Diffs sent to repr.dev for processing * ✅ No local LLM needed * ✅ Fast, optimized models ### BYOK (Bring Your Own Key) ```bash theme={null} repr llm add openai repr generate ``` * ✅ Diffs sent directly to your API provider (OpenAI, Anthropic, etc.) * ✅ repr.dev never sees your data * ✅ Your API key, your costs * ✅ Keys stored in OS keychain ## Token Limits For cloud generation, repr enforces limits to control costs: * **Max commits per batch:** 50 (configurable) * **Token limit:** \~100k tokens per batch If you exceed limits, repr will: 1. Show you the split plan 2. Ask for confirmation 3. Process in multiple batches ```bash theme={null} repr generate --cloud ``` Output: ```text theme={null} ⚠ 87 commits exceeds 50-commit limit Will split into 2 batches: Batch 1: commits 1-50 (est. 45k tokens) Batch 2: commits 51-87 (est. 32k tokens) Continue with generation? [Y/n] ``` ## Troubleshooting ### "Local LLM not found" Install Ollama and pull a model: ```bash theme={null} brew install ollama ollama pull llama3.2 repr llm test ``` ### "No repositories tracked" Initialize repr first: ```bash theme={null} repr init ~/code ``` ### Generation is slow * Use `--batch-size 3` for smaller stories * Try a lighter model: `ollama pull phi3` * Use cloud generation instead ### Stories are too technical/brief Add a custom prompt: ```bash theme={null} repr generate --local --prompt "Write in accessible language for non-technical stakeholders. Focus on business impact." ``` ## Related Commands * `repr stories` - View generated stories * `repr story view ` - Read a specific story * `repr review` - Interactive review workflow * `repr push` - Publish stories to repr.dev