Sephera
Active·★ 78·GPL-3.0·Updated 2026-04-04
★ Trending★ Observability★ Dev Tooling
Fast local-first Rust CLI for codebase metrics, AST-compressed LLM context bundles, and built-in MCP server.
Sephera is a local-first Rust CLI that combines repository metrics and deterministic context export. It provides fast line counting, deterministic context bundles with AST compression, and a built-in MCP server for AI agent integration. It focuses on giving reliable structural signals and focused context for LLMs and humans.
#cli#command-line-tool#context-engineering#developer-tools#llm#llm-agents#mcp#mcp-servers
01
Features
01Fast LOC analysis with per-language totals and terminal table output
02Deterministic context packs with focus-path prioritization, Git diff awareness, and token budgeting
03Tree-sitter AST compression for context excerpts with 50-70% token reduction
04Built-in MCP server for direct AI agent integration
05Repo-level context defaults and named profiles through .sephera.toml
02
Compatibility
Linux
Linux
Verified via docs
macOS
macOS
Verified via docs
Windows
Windows
Verified via docs
03
Quick start
1
$ cargo install sephera
04
Use cases
↳Inspect a repository before refactoring or reviewing changes
↳Build a focused context bundle for LLMs like ChatGPT, Claude, or Gemini
↳Connect AI agents directly to Sephera through the MCP server
05
Alternatives
GitHub MCP Server★ 30.3k
GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).
FunASR★ 16.6k
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
Related searches
Comments
Log in to leave a comment
- RRobin PatelMay 11, 2026
Used for generating codebase context bundles for offline AI analysis, very fast
- OOakley LewisApr 11, 2026
The local-first design means sensitive codebases stay on-premises
- JJustice WilsonApr 4, 2026
AST-compressed LLM context bundling is a smart approach to reducing token overhead
- Justice ChenApr 1, 2026
Fast local-first Rust CLI for codebase metrics gives results without cloud dependency