Zeroclaw is an open-source, Rust-based CLI coding agent and workflow engine developed by Zeroclaw Labs. Built for performance and reliability in developer environments, it provides terminal-first interaction for automating complex software engineering tasks, executing tool calls, and maintaining project-level context across extended coding sessions. In day-to-day workflows, Zeroclaw operates as a terminal agent that inspects source repositories, executes file operations, and manages system commands under defined security constraints. It integrates with major LLM backends (including Anthropic Claude via skill definitions) to interpret prompts, decompose tasks, and execute multi-step implementations against local codebases. Zeroclaw differentiates itself through its native Rust foundation, Standard Operating Procedure (SOP) engine, and formal tool verification layer. Unlike Python- or TypeScript-heavy CLI agents, Zeroclaw emphasizes minimal runtime overhead, strict idempotency for webhooks and fan-in triggers, and fine-grained tool authorization controls. Zeroclaw is distributed as open-source software on GitHub. Users configure their own API keys to communicate directly with supported AI providers without middleman service fees.
Rust-native runtime — Delivers minimal resource consumption, fast startup times, and deterministic binary execution. - SOP engine & webhook fan-in — Supports structured Standard Operating Procedures with authenticated webhook triggers and idempotent replay domains. - Claude skills compatibility — Integrates structured skill definitions to extend agent capabilities across custom tools. - Tool verification pipeline — Implements strict configuration surfacing and authorization policies for executing system-level actions. - Security & audit waivers — Includes built-in policy enforcement and audit tracking for enterprise codebases.
Use cases
Use Case: Automated Task Execution in Rust and Polyglot Repositories Developers use Zeroclaw directly from the command line to parse repository architecture, implement features, fix bugs, and execute local test suites autonomously while adhering to strict code verification policies.
Use Case: Event-Driven CI/CD and SOP Automation Engineering teams trigger Zeroclaw via its SOP engine and webhook endpoints to respond to repository events, automating triage, patch generation, and policy enforcement across build pipelines.
Use Case: Controlled Tool and Command Execution Teams working in restricted environments use Zeroclaw's explicit tool withholding and verification gates to ensure agents only execute authorized actions against the local operating system.
Who it is for
Zeroclaw is built for systems engineers, backend developers, and DevOps teams who prefer Rust-based terminal tooling with strong guarantees around execution control and security policies. It is less suitable for casual developers seeking simple GUI-driven code assistants or plug-and-play browser extensions.
Install guide
Installation Install Zeroclaw from source using Cargo (standard Rust installation method): bash git clone https://github.com/zeroclaw-labs/zeroclaw.git cd zeroclaw cargo build --release cp target/release/zeroclaw /usr/local/bin/
First Run Configure your model provider credentials in your shell environment: bash export ANTHROPIC_API_KEY="your-anthropic-api-key" export OPENAI_API_KEY="your-openai-api-key" zeroclaw --version
Example Session Run an interactive coding session inside your project repository: bash cd my-project zeroclaw "Implement a health check endpoint in src/server.rs and verify with cargo test"
Skillreaper — Skillreaper is an open-source skill lifecycle management and auditing tool for AI agent ecosystems, developed by thousandflowers. It analyzes agent…
ActPlane — ActPlane is an open-source agent execution and policy enforcement harness developed by the Eunomia-bpf organization. It functions as a security…
Zosma QA — Zosma QA is an open-source testing-focused agent harness and orchestration framework created by Zosma AI. It provides scaffolding, structured prompt…
Stratless — Stratless is an open-source agent harness and execution orchestrator developed by the Stratless AI team. It provides a modular infrastructure…
Agent Island — Agent Island is an open-source agent orchestration harness created by developer tristan666666 on GitHub. Designed as a framework for running…
Repo Forensics — Repo Forensics is an open-source agent orchestration harness and repository security gating tool developed by Alex Greenshpan (alexgreensh). Designed to…