AI — Axiom
Overview
Axiom is a LaTeX-specialized AI agent integrated into TeX64. Understands your entire project context and reads/writes files directly while working. Your paper data is never used for AI training. Processed server-side via the OpenAI API.
AI Chat
Conversation with an AI that understands your entire project. Ask natural language questions like "Why is this error happening?" or "Make this section more concise". AI can read your project files (.tex, .bib, .sty, .cls, etc.), file structure, build output, and error messages.
- Image attachments: paste screenshots to share visual context
- Conversation history: up to 80 messages per session, up to 24 simultaneous sessions
- Pause and resume conversations anytime
- Can reference compile logs, BibTeX files, and arXiv papers
AI Completion
Inline code completion and draft generation in your editor. Automatically generates next lines, sections, or equations.
- Generate equations from natural language (e.g., "integral of x squared from 0 to 1" → \int_0^1 x^2 dx)
- Writing assistance: generate paragraphs, abstracts, introductions
- Error detection and fix suggestions
- Rewriting and paraphrasing
- Accept or dismiss with a keystroke
Working With Your Files
Axiom does not just chat — it works directly in your project. It reads your project files, proposes edits as diffs you review and approve, compiles the project, reads build logs, and searches arXiv. These capabilities are available to anyone with AI access (Free, Basic, or Pro).
- Reads project files and lists the file tree (read_file, list_files, list_sections, read_section)
- Proposes edits as diffs you approve before they are applied (replace_lines, insert_lines, delete_lines, apply_patch, replace_section, append_to_section, write_file, create_file)
- Compiles your project and reads the build log (run_command, get_compile_log)
- Searches arXiv and fetches BibTeX entries (arxiv_search, arxiv_bibtex)
- Checks and installs the TeX environment when needed (check_environment, install_environment)
- Edits always require your approval before they are applied
Use Cases
- Multi-file refactoring across chapters
- Automatic compilation error fixes
- Generate boilerplate for new chapters/sections
- Reorganize document structure
- Identify errors in build logs → fix → rebuild
What Axiom Can See
- Project files (.tex, .bib, .sty, .cls, etc.)
- File tree structure
- Build output and compile logs
- Error messages and warnings
- Referenced packages and bibliography
- Images attached to chat
- arXiv search results and BibTeX data
What Axiom Cannot Do
- Cannot access files outside your workspace
- Cannot execute arbitrary system commands (tools are restricted)
- Cannot modify files without your approval
- API keys and tokens are automatically redacted (masked)
Privacy & Data
- Paper data is NEVER used for AI training
- Data only sent when you explicitly use AI features
- HTTPS encryption in transit
- Server-side processing via the OpenAI API
- Deleted after processing (not stored long-term)
- Sensitive data (API keys, tokens) auto-redacted
Plans & Pricing
Free
- AI: ~200,000 tokens / month
- Resets monthly on the anniversary of your sign-in date
Basic — $12/month
- AI agent features
- Monthly AI: ~800,000 tokens / month
Pro — $25/month
- All Basic features + higher monthly quota
- Monthly AI: ~3,000,000 tokens / month
- Axiom 0.9.1 Pro — most capable model (Pro plan only)
View token usage in Account > Usage dashboard. Grace period of 3 days after payment failure.
Models
- Axiom 0.9.1 — standard model, available on all plans
- Axiom 0.9.1 Pro — most capable model, Pro plan only
Technical Details
- Context messages: max 14 (optimized via compression + summarization)
- Chat input limit: 3,200 tokens
- Chat output limit: 512 tokens
- Completion input limit: 1,200 tokens
- Completion output limit: 96 tokens
- Conversation TTL: 3 days (259,200 seconds)
- Rate limit: 30 requests/minute
Tips
- Be specific in your prompts for better results
- Attach images for visual issues
- Let Axiom edit files for complex, multi-step changes
- Review diffs before applying
- Use chat for questions, completion for inline suggestions