Moltis

Moltis is an open-source CLI coding agent and agent harness written in Rust by the Moltis organization (formerly maintained under penso/moltis). It is designed to provide high-performance terminal-based code generation, inspection, and automated repository manipulation without heavy runtime dependencies. Moltis operates directly within the developer's terminal, interfacing with large language model backends such as Anthropic Claude. The agent processes instructions by running contextual tool calls, including repository file reading, code generation, testing, and built-in search integrations such as Brave search to pull external context during development sessions. A key architectural differentiator of Moltis is its support for the Agent Client Protocol (ACP) over stdio. This enables Moltis to function either as a standalone CLI tool or as an embedded headless agent engine orchestrated by ACP-compatible developer tools and IDEs. Built in Rust, it emphasizes fast startup times and minimal system overhead compared to Python- or TypeScript-based agent runtimes. Moltis is open source and hosted publicly on GitHub with preconfigured Homebrew tap distribution and standard Rust toolchain builds.

Tags: agent harness, ai agent, cli, developer tools, OpenSource, personal assistant

Visit Moltis

Key features

  • Rust-native architecture — Built with Rust for high execution speed, low memory footprint, and easy single-binary distribution. - Agent Client Protocol (ACP) over stdio — Supports ACP communication over standard I/O to integrate seamlessly into external harnesses and ACP-compliant editors. - External tool integrations — Includes built-in capabilities such as Brave search integration to fetch real-time web documentation and error solutions. - Multi-model backend support — Connects to advanced LLM reasoning engines including Claude models for context analysis and patching. - Homebrew tap distribution — Simplifies package management and updates via standard macOS and Linux Homebrew repositories.

Use cases

Use Case: Interactive Terminal Refactoring Developers launch Moltis directly inside a repository to diagnose test failures, inspect relevant source files, and apply automated multi-file code modifications.

Use Case: ACP-Driven Agent Orchestration Engineers using ACP-enabled developer environments invoke Moltis over stdio as a modular sub-agent for automated code editing and tool invocation.

Use Case: Context-Aware Bug Fixing with Web Search When troubleshooting novel API deprecations or third-party error codes, Moltis uses Brave search to query current web documentation before formulating precise patches.

Who it is for

Moltis is intended for systems developers, command-line power users, and teams looking for a lightweight, Rust-native coding agent that supports standardized agent protocols like ACP. It is less suited for non-technical users who require a fully browser-based GUI or closed enterprise SaaS agent interface.

Install guide

Installation Install Moltis using the official Homebrew tap: bash brew tap moltis-org/tap brew install moltis Alternatively, build directly from source using the Rust toolchain: bash git clone https://github.com/moltis-org/moltis.git cd moltis cargo build --release

First Run Export your required LLM provider API key and any tool keys (such as Brave search if applicable): bash export ANTHROPIC_API_KEY="your_anthropic_api_key_here"

Example Session Launch Moltis directly in your repository to perform automated tasks: bash moltis "Inspect the error handling in src/lib.rs and add unit tests covering edge cases"

Part of CLI Coding Agents

Categories: AI Coding Agents, Assistant, Developer Tools, Life Assistant

Related CLI agents

  • SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
  • Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…
  • Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
  • Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
  • Stratless — Stratless is an open-source agent harness and execution orchestrator developed by the Stratless AI team. It provides a modular infrastructure…
  • Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories