Zot is an open-source, terminal-based AI coding agent written in Go by Patrice Eckhart. Built to function directly within developer terminal environments, it provides an agentic coding interface capable of managing codebases, executing tasks, and orchestrating multi-turn conversational coding sessions. In daily use, Zot features an interactive terminal user interface (TUI) optimized for fast startup and session management. It supports session resumption with context usage restoration and transcript tail-rendering. Zot integrates across a wide variety of model providers, including Anthropic, OpenAI (including Responses API), Google Gemini, AWS Bedrock, Google Cloud Vertex AI, Azure OpenAI, and GitHub Copilot, alongside custom user-defined provider configurations. What sets Zot apart is its broad native provider flexibility combined with Model Context Protocol (MCP) support and experimental remote agent pairing capabilities (such as mobile phone pairing). By providing native Go binaries and cross-platform installation scripts, it avoids heavy runtime dependencies while remaining modular across multiple cloud and local model backends. Zot is licensed as open-source software and available publicly on GitHub. Because it operates on a bring-your-own-key model, users only pay standard API access fees directly to their configured model providers without platform markups.
Broad Provider Ecosystem — Native support for Anthropic, OpenAI Responses, Google Gemini, AWS Bedrock, GCP Vertex AI, Azure OpenAI, GitHub Copilot, and custom model endpoints. - Optimized Terminal Interface — TUI with tail-rendered transcripts for quick paint times and context tracking across resumed sessions. - Model Context Protocol (MCP) Support — Extensible tooling integration connecting agent execution to external context sources and tools. - Remote Agent Phone Pairing — Optional remote pairing capabilities allowing developers to manage or monitor agent workflows remotely. - Multimodal Artifact Handling — Handles image generation models and transcript replay with tolerance for assistant-side media artifacts. - Session Lifecycle Management — Built-in commands and tools to resume, inspect, and prune session storage with human-readable size reporting.
Use cases
Use Case: Multi-Cloud Enterprise Model Orchestration Developers operating inside restricted enterprise infrastructure can configure Zot to route agent requests through internal Azure OpenAI, AWS Bedrock, or GCP Vertex AI instances using standard environment credentials without sending source code to third-party subscription proxies.
Use Case: Interactive Terminal Code Generation and Refactoring Engineers working inside terminal environments or SSH sessions can launch Zot's TUI to inspect source trees, draft refactors, generate multi-file edits, and resume interrupted sessions while retaining prior context usage metrics.
Use Case: Remote Tooling via MCP and Device Pairing Developers can augment the core coding agent with custom Model Context Protocol servers for specialized internal tooling while leveraging remote pairing workflows to review or interact with running tasks away from the primary workstation.
Who it is for
Zot is designed for software engineers, DevOps specialists, and command-line power users who want a fast, Go-native coding agent with flexible model provider routing (Bedrock, Vertex, Azure, Anthropic, OpenAI). It is less suited for developers who prefer all-in-one GUI IDE plugins or hosted, turn-key coding assistant SaaS platforms.
Install guide
Installation Install Zot using the official installer script or compile via Go: bash # Via installation script (macOS/Linux) curl -fsSL https://raw.githubusercontent.com/patriceckhart/zot/main/install.sh | bash # Or build directly via Go go install github.com/patriceckhart/zot/cmd/zot@latest
First Run Configure your preferred model provider credentials in your environment. For example, to use Anthropic or OpenAI: bash # Set API key for Anthropic export ANTHROPIC_API_KEY="your-anthropic-api-key" # Or set OpenAI API key export OPENAI_API_KEY="your-openai-api-key" Launch the agent inside your target repository: bash zot
Example Session Start an interactive session and issue a task: bash # Launch Zot TUI inside project directory zot # Example prompt within the agent prompt > Analyze the packages/ directory and write unit tests for the session pruner.
SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
Agent Runbook — Agent Runbook is an open-source contract-based multi-agent skill framework developed by KnoxOps. It acts as an orchestrator and compiler that…
Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…