Perspt Documentation¶

Your Terminal’s Window to the AI World

Perspt is a high-performance terminal-based LLM interface that serves two purposes: a simple CLI for testing and comparing LLM services across 8 providers, and an experimental implementation of the SRBN (Stabilized Recursive Barrier Network) engine from the paper “Stability is All You Need: Lyapunov-Guided Hierarchies for Long-Horizon LLM Reliability” by Vikrant R. and Ronak R. (pre-publication). The SRBN agent plans multi-file projects as directed acyclic graphs, verifies each node with real LSP diagnostics and tests, and commits only when Lyapunov energy converges. The theoretical framework is mature; the implementation is under active development.

Quick Start

Install and chat in 5 minutes.

Quick Start

Agent Mode

Autonomous multi-file coding with the experimental SRBN engine.

Agent Mode Tutorial

Dashboard

Monitor agent execution in real-time via browser.

Dashboard

Architecture

9-crate workspace design.

Architecture

Key Features¶

SRBN Agent	Experimental autonomous multi-file coding guided by Lyapunov energy, ownership closure, and sheaf validation (based on SRBN paper)
Multi-Provider	OpenAI, Anthropic, Google Gemini, Groq, Cohere, XAI, DeepSeek, Ollama
LSP Sensors	Real-time type checking via `rust-analyzer`, `ty`, `pyright`, `typescript-language-server`, `gopls`
Test Runner	pytest integration with weighted V_log energy
Per-Tier Models	Assign different models to Architect, Actuator, Verifier, and Speculator tiers
Token Budget	Cost control with usage monitoring and per-request limits
Beautiful TUI	Ratatui-based with diff viewer, task tree, dashboard, and review modal
Security	Starlark policy engine with command sanitization and workspace-bound enforcement
Merkle Ledger	Cryptographic change tracking with session resume and rollback
Headless Mode	Fully autonomous operation with `--yes` for CI/CD and batch workflows