ESP32-S3 Bench Guide
ESP32‑S3 N16R8 벤치 가이드: 실시간 핀아웃, 강의, 시뮬레이터 및 벤치 로그
이론 과학 발전을 위한 AI 이론가, 전문 에이전트가 결과 도출·Wolfram 검증·Lean 4 증명 형식화·VS Code 작업 지원
An AI theorist for advancing theoretical science. A team of specialist agents derives results, checks derivations in Wolfram, formalizes proofs in Lean 4, and helps you do good work, in VS Code and th
교육TypeScript · JavaScriptGitHub @LionSR온라인운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
TeXRA — an AI theorist (math, physics, computer science). VS Code extension and terminal CLI.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
An open-source AI theorist for VS Code and the terminal. It attempts real
theory work: deriving results, checking derivations, formalizing proofs in
Lean 4. It takes on open problems in long autonomous runs, with a team of
specialist agents. Apache 2.0, and you bring your own model keys or
subscriptions.README 전문 보기 ↗An open-source AI theorist for VS Code and the terminal. It attempts real theory work: deriving results, checking derivations, formalizing proofs in Lean 4. It takes on open problems in long autonomous runs, with a team of specialist agents. Apache 2.0, and you bring your own model keys or subscriptions.
Development on main targets TeXRA 1.0 (work in progress, not the
currently published release), which reorganizes the interface around
projects, stores application state in SQLite, and runs asynchronous
execution on Effect (see the 1.0 development direction).
Version 1.0 starts with fresh application state and does not migrate previous
JSON settings, session histories, or execution checkpoints; research files in
your project are untouched.
# VS Code (or Cursor, Windsurf, Antigravity)
code --install-extension texra-ai.texra
# Terminal: requires Node.js 22.19.0 or later in 22.x, or Node.js 24 or later
npm install -g @texra-ai/cli
# Or via Homebrew (macOS / Linux)
brew install texra-ai/tap/texra
Set <PROVIDER>_API_KEY to use your own credentials, sign in with a
ChatGPT or Grok subscription, or add the API key for a Kimi Code or
GLM Coding Plan subscription.
Every agent ships bundled, including the document-task agents that the Physicist, Mathematician, and Computer Scientist teams delegate to. Each agent is a YAML file you can read, copy into a custom agent, and modify. There is no TeXRA account; model calls run directly against your configured provider credentials.
TeXRA is sustained by the community. If TeXRA helps your research, consider supporting it via GitHub Sponsors or Buy Me a Coffee to keep it open for everyone.
In VS Code: open a .tex file, click the TeXRA icon, pick
Orchestrator or another agent, type a task. The Setup Wizard runs
on first launch and checks your environment.
In the terminal:
texra chat # interactive tool-use session
texra run polish --input paper.tex # one-shot workflow
texra team run physicist --instruction "Check this derivation" # named team
Run history and agent settings are shared between both surfaces.
Five built-in presets cover the most common research disciplines:
| Team | Built for |
|---|---|
| Physicist | Analytical derivations, numerical experiments, literature search, slide drafting |
| Mathematician | Attacking open problems, proofs, Lean 4 formalization, LaTeX correction |
| Computer Scientist | Algorithm design, code-driven experiments and ablations, tests, literature |
| Lean Project | Mathlib search, tactic simplification, blueprint-driven formalization |
| Software Engineer | An engineer lead delegating implementation, review, debugging, and testing |
Pick a team in Settings → Agents → Teams, or with texra team run <preset>. Or save the agents you have shown as your own team.
Document tasks process selected files and produce reviewable LaTeX diffs:
polish, correct, merge, ocr, transcribe_audio, paper2slide, and
paper2poster, plus the specialist task passes apply, criticize, devise,
enhance, firstread, generic, logic, and notation.
Chat agents work conversationally with file, shell, and search tools:
orchestrator, assistant, research, numerics, review, search,
simplifier, prover, progressCheck, presenter, latexFixer,
latexDiff, creator, setup, the Lean 4 line (lean, leanOrchestrator,
leanBlueprint, leanSearch, leanSimplifier), and the software-engineering
line (engineer, coder, codeReviewer, testEngineer, codeSimplifier).
Every tool call is gated by per-stream approval. Optional YOLO mode skips approval for autonomous runs.
Bring your own keys for OpenAI, Anthropic, Google Gemini, DeepSeek, xAI Grok, Moonshot Kimi, Alibaba Qwen, Zhipu GLM, MiniMax, or any OpenAI-compatible endpoint. Each agent in a team can run a different model — pair a flagship reasoner for orchestration with cheaper, faster models for routine sub-tasks.
In the extension, run TeXRA: Set API Key (stored in the owner-only
~/.texra/secrets/ folder every TeXRA host shares) or add a workspace .env:
OPENAI_API_KEY=…
ANTHROPIC_API_KEY=…
GOOGLE_API_KEY=…
In the CLI, export the same variables in your shell.
latexindent and latexdiff)git, gh, Codex CLI, Lean 4 + lakeThe Setup Wizard checks for and helps install most of the above.
Full docs at texra.ai/guide.
Issues and feature requests: GitHub. Contact: [email protected].
Licensed under the Apache License, Version 2.0. © TeXRA Team 2024–2026.