kuberwastaken/claurst

Agentic Coding for Builders who Ship

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 30 minutes ago
Added to GitGenius on September 1st, 2026
Created on March 31st, 2026
Open Issues & Pull Requests: 31 (+0)
GitHub issues: Enabled
Number of forks: 7,750
Total Stargazers: 10,292 (+0)
Total Subscribers: 114 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 2.4 hours
Mean response time: 2.3 days
90th percentile: 4.6 days
Tracked items: 146

How this project is maintained

Around half of the issues opened in the past year never receive a reply. Only 14% of issues opened in the past year have been closed. Three people close 93% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 17
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 72 days
Stale 30+ days: 8
Stale 90+ days: 5

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • bug (2)
  • enhancement (1)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Claurst is a terminal-based agentic coding assistant built in Rust that supports multiple AI providers.

The tool addresses the need for a local, privacy-respecting coding agent that works in the terminal. It began as a clean-room reimplementation of Claude Code's behavior and has evolved into a multi-provider agent with a rich terminal user interface. The approach routes requests to different AI providers, maintains conversation context with memory consolidation, and includes features like chat forking and a plugin system. The tool runs entirely on the user's machine with no tracking or telemetry.

Claurst suits developers who want an agentic coding experience without cloud lock-in or privacy concerns. It works well for those comfortable with terminal interfaces and who value local execution and control over their tools. The project explicitly positions itself as an alternative to Claude Code, offering similar agentic behavior but as an open-source, self-hosted option with multi-provider flexibility. The tool includes experimental features like goal-oriented multi-turn workflows, effort levels ranging up to ultracode for complex reasoning tasks, and session sharing via GitHub Gists.

Development activity shows active experimentation with new capabilities. The project maintains a clear distinction between stable core features and experimental additions, flagging the latter transparently in documentation. Recent work has focused on expanding the agent's reasoning capabilities through effort levels and multi-turn objective handling, while also adding collaborative features like session sharing. The codebase remains under active iteration with beta status, indicating the maintainers are refining core functionality while remaining open to community feedback and contributions.