gptme is a free and open-source terminal AI agent that combines shell command execution, code writing, file editing, web browsing, and vision capabilities in a single interactive or autonomous workflow. Originally created in 2023 as one of the earliest terminal-based AI coding agents, it provides an unconstrained local alternative to Claude Code, Codex, and Cursor agents with full control over which LLM provider and model to use. The tool runs as a Python CLI that accepts natural language instructions, translates them into tool calls, and executes them locally with real-time streaming output. MCP discovery and dynamic loading allows gptme to connect to databases, APIs, and any MCP-compatible service.
Beyond interactive use, gptme is designed for persistent autonomous operation where AI agents run continuously across sessions. The public Bob reference agent and gptme-agent-template demonstrate autonomous run loops, enhanced context generation, background jobs, and workflows such as monitoring repositories, opening pull requests, reviewing code, and reacting to CI failures. The capability is best treated as an extensible agent framework that still needs human-designed guardrails, budgets, and review gates.
Licensed under MIT with 4.3K+ GitHub stars, gptme remains actively maintained even though the latest tagged GitHub release is v0.31.0 from December 2025. Recent project materials emphasize background jobs, form tools, cost tracking, content-addressable storage, plugin support, context compression, MCP discovery, and the gptme-agent-template for bootstrapping custom autonomous agents. The Python codebase is available on PyPI and supports major hosted providers plus local OpenAI-compatible or llama.cpp-style backends.
