A fast Rust CLI for codebase metrics, AST-compressed LLM context bundles, and a built-in MCP server.
Sephera is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view Reim-developer/Sephera --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Sephera is a command-line tool that helps developers quickly understand their codebase. It can count lines of code, create compact summaries for AI tools, analyze dependencies, and connect directly to AI agents via the Model Context Protocol.
Sephera is a Rust-based CLI tool designed to help developers understand and interact with their codebases efficiently. It provides four main commands: 'loc' for fast, language-aware line counting; 'context' for generating deterministic Markdown or JSON bundles with AST compression, focus paths, and Git diff awareness; 'graph' for dependency graph analysis via Tree-sitter import extraction; and 'mcp' for a built-in MCP server that exposes these workflows to AI agents. Sephera supports URL mode, allowing analysis of remote repositories without cloning. It is intentionally narrow in scope, focusing on practical tasks rather than being an agent runtime or hosted service.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 114 days ago.
78 GitHub stars indicate community interest.
0 open issues signal maintenance load.
GPL-3.0 license detected.
Quickly count lines of code in a local or remote repository with language-aware metrics.
Generate a token-budgeted context bundle for LLMs, with AST compression to reduce size.
Trace reverse dependencies to understand the impact of changing a shared module.
Expose codebase analysis workflows to AI agents via the built-in MCP server.
Analyze dependency graphs and export them in multiple formats (JSON, Markdown, XML, DOT).
The tool runs locally and does not send data externally unless configured to do so via MCP or URL mode. Ensure you trust the repositories you analyze via URL mode.
78
Stars
9
Forks
0
Issues
GPL-3.0
License
Run large language models locally with a simple CLI. Supports Llama, Mistral, Gemma, and 100+ models with one command.
Universal memory layer for AI agents that enables personalized, context-aware interactions.
An open-source framework to turn HTML, CSS, and animations into deterministic MP4 videos.
A fast Rust CLI for codebase metrics, AST-compressed LLM context bundles, and a built-in MCP server.
Rust developers building or maintaining large codebases., AI/ML engineers preparing context for large language models., DevOps engineers needing quick codebase metrics and dependency analysis.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
The tool runs locally and does not send data externally unless configured to do so via MCP or URL mode. Ensure you trust the repositories you analyze via URL mode.
Similar or complementary options to evaluate include Ollama, mem0, hyperframes.
Jun 6, 2026
1 security/trust notes recorded.
Setup difficulty is 3/5.