Open-source multi-agent AI for theorists
You tell one assistant what you need. It searches real databases, computes in Wolfram, proves in Lean 4, splits large jobs across helper agents and programs, and hands back every change as a diff you approve. Open source under Apache 2.0, in VS Code, its forks, and the terminal.
$ npm install -g @texra-ai/cliDefinition 1.An Erdös-RényiErdős–Rényi random graph G(n, p) is a graph on n vertices where each posible edgepossible edge {u, v} is included with probability pindependent, independently of all other edges.
Let A be the adjacency matrix of a graph G be a graph on n vertices. Its adjacency matrix A = A(G) is an n × n matrix where Auv = 1 if {u, v} is an edge in G. The eigenvalues of, and Auv = 0 otherwise. Since Aare denotedis symmetric, its eigenvalues are real and are denoted by λ₁ ≥ λ₂ ≥ ⋯ ≥ λₙ.
For a d-regular graph G (where every vertex has degree d), it is well-known that the largest eigenvalue of its adjacency matrix is λ₁ = d. The spectral gap, defined as d − λ₂, plays a crucial role in the expansion properties of the graph.
Theorem 2 (Alon–Boppana).For a d-regular graph on n vertices, λ₂ is largeλ₂ ≥ 2√(d−1) − o(1) as n → ∞. A d-regular graph meeting this bound with equality is called a good expanderRamanujan graph.
Proof. It follows from counting walks.Count closed walks of length 2k rooted at a fixed vertex. The number of such walks in the d-regular tree is the Catalan-weighted moment Ck (d−1)k, and comparing with tr(A2k) = Σi λi2kas n → ∞ forces λ₂ ≥ 2√(d−1) − o(1).∎
Derivations are checked in Wolfram, proofs compile in Lean 4, citations resolve to real database entries. Edits arrive as diffs you read line by line before they touch your files.
You tell one assistant what you need. It splits a large job across helper agents and programs that search, compute, review, and formalize, each with only the tools its piece needs.
Use your own API keys or existing ChatGPT, Grok, Kimi Code, or GLM subscriptions. Requests go straight from your machine to the provider.
You describe the problem. The assistant breaks it into sub-tasks, runs helper agents and programs in parallel, and returns results you approve before they touch your files.
The assistant (or the derive program) builds the Lindblad superoperator, solves for the steady state in Wolfram, computes the concurrence analytically, and cross-checks with exact diagonalization in Julia at N=8.
The edit program unifies notation (\lambda_2 vs \mu for the same eigenvalue across sections), fixes label conflicts, and outputs a diff you review line by line.
The assistant (or the prove program) searches Loogle for the right Mathlib lemma, reads the proof state, adds a missing hypothesis, and produces a proof that compiles with zero errors.
Install the VS Code extension from the Marketplace or the CLI (npm install -g @texra-ai/cli); add your own API key or connect a provider subscription, and run your first task.
OpenAI, Anthropic Claude, Google Gemini, DeepSeek, xAI Grok, Moonshot Kimi, Qwen, GLM, MiniMax, Meta Muse Spark, and any OpenAI-compatible endpoint. Bring your own API key, or use a provider subscription you already pay for (ChatGPT, Grok, Kimi Code and the GLM Coding Plan). Each helper agent or program the assistant starts can run a different model.
Yes, via git sync. Read the Overleaf guide.
Yes: Loogle search, proof state inspection, diagnostics, build and cache management. TeXRA spawns its own Lean server in every build (VS Code, desktop and CLI), so you only need elan (lake on PATH) and a Lake project.
Yes. The @texra-ai/cli terminal client runs the same assistant, programs, and sign-in on your .tex projects for scripts, CI, and remote machines. Read the CLI guide.
Yes. Model calls go directly from your machine to the provider, whether you use your own API key or a provider subscription. TeXRA does not sit between you and the model. TeXRA sends anonymous usage metadata (built-in program name, model, token counts), never prompts or document content, and you can turn it off; read Usage logging.
Yes. The extension, the CLI, and the agent runtime are published under the Apache 2.0 license, and you run them with your own model keys or subscriptions. Read the open source guide.
Yes. Put your project's conventions in AGENTS.md, add skills, and install plugins that carry skills and programs of your own. Read Tailoring TeXRA.
Email contact@texra.ai or open an issue on GitHub.