CLAURST Agentic Coding for Builders who Ship

Claurst is an open-source, multi-provider terminal coding agent built from the ground up in Rust. It started as a clean-room reimplementation of Claude Code's behavior (from spec) and has since evolved into an amazing TUI pair programmer with multi-provider support, a rich UI, plugin system, a companion named Rustle, chat forking, memory consolidation, and much more.

It's fast, it's memory-efficient, it's yours to run however you want, and there's no tracking or telemetry.

[!IMPORTANT] Claurst is now officially in Beta (v0.2.0). The core agent, multi-provider routing, and TUI are stable enough for daily driving — expect rough edges around experimental features (flagged below). Bug reports and PRs welcome.

[!NOTE] Recent Updates (v0.2.0, see the changelog):

• Sandbox and permissions: on macOS, Bash commands run in a Seatbelt sandbox that limits writes to the workspace and blocks network by default (/sandbox-toggle). Bash approvals are matched per command, approvals can be saved for the current project, and --allowed-tools / --disallowed-tools are enforced. See Permission rules and Shell Sandbox.

• Hooks: Claude Code's hooks contract (settings shape, events, JSON stdin/stdout, exit code 2, timeouts), including plugin hooks. See Hooks.

• Skills and instruction files: AGENTS.md and CLAUDE.md files are loaded from the git root down to the working directory, with @include; skills from .claurst/skills, .agents/skills and .claude/skills are listed to the model. See Instruction files and Skills.

• Headless runs: typed stream-json events, documented exit codes, --resume / --continue, and --json-schema for a structured answer. See Headless mode.

• Providers: Anthropic prompt caching and adaptive thinking; ChatGPT (Codex) subscription token refresh, prompt caching and reasoning replay; one retry policy and context compaction for every provider.

• /share support: Use /share to share chat sessions with others via unlisted GitHub Gists. [EXPERIMENTAL]

• Free Mode: Try out Free in '/connect' to get a great agentic coding experience in Claurst for absolutely free (or as good as free gets you :P). [EXPERIMENTAL]

• /goal support: Try out /goal <objective> to see claurst keep working an objective, spanning multiple turns instead of stopping after one normal turn. [EXPERIMENTAL]

• ultracode: The highest effort level — pick it in the effort selector (/effort, where it sits past max on the "Smarter" end with an animated purple spectrum) or just type ultracode anywhere in your prompt. The keyword lights up with a purple gradient (claurst's take on Claude Code's ultrathink) and that turn runs at the model's top reasoning plus a disciplined plan → delegate → integrate → verify workflow that fans bounded packets out across native subagents (Agent), swarms (TeamCreate), and background tasks (TaskCreate). Composes with /goal for sustained multi-turn objectives. [EXPERIMENTAL]

Getting Started